BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Wei Guo

Wei Guo contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
physics.flu-dynComputer Visioncond-mat.othermath.NANumerical AnalysisArtificial IntelligenceInformation RetrievalMachine Learningcond-mat.mes-hallcond-mat.mtrl-scicond-mat.quant-gaseess.SPInformation Theorymath.ITNetworking and Internet Architecturephysics.app-phphysics.opticsastro-ph.SRcond-mat.supr-conCryptography and SecurityDatabasesDistributed, Parallel, and Cluster Computinghep-phnlin.CDphysics.acc-phphysics.class-phphysics.ins-detphysics.soc-phquant-phQuantitative MethodsSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
40works
0followers
31topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

40 published item(s)

preprint2026arXiv

TurboGR: An Accelerated Training System for Large-Scale Generative Recommendation

Generative recommendation (GR) has emerged as a promising paradigm that replaces fragmented, scenario-specific architectures with unified Transformer-based models, exhibiting scaling-law behavior where recommendation quality improves systematically with increased model capacity and training data. However, deploying GR at scale on Ascend NPUs faces fundamental system-level challenges. These challenges are further exacerbated on Ascend NPUs due to the absence of high-performance implementations for jagged operators and the architectural mismatch between irregular sparse primitives and NPU's dense-computation-optimized design. In this paper, we present \model, an Ascend-affinity training system for generative recommendation that systematically addresses these bottlenecks through three core innovations: (i) Ascend-affinity jagged acceleration, including fusion operators that eliminate padding redundancy and dynamic load balancing that reduces inter-device imbalance from 47\% to 2.4\%; (ii) distributed communication optimization, comprising hierarchical sparse parallelism, semi-asynchronous training with proven convergence guarantees, and fine-grained pipeline orchestration that sustains 94\% NPU utilization; and (iii) negative sampling optimization via asynchronous offloading, jaggedness-aware FP16 quantization, and intra-batch logit sharing that expand the effective negative space without additional embedding lookups. Evaluated on the KuaiRand-27K dataset, \model supports training at up to 0.2B parameters and achieves 54.71\% MFU with near-linear scalability (0.97).

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

PointRAFT: 3D deep learning for high-throughput prediction of potato tuber weight from partial point clouds

Potato yield is a key indicator for optimizing cultivation practices in agriculture. Potato yield can be estimated on harvesters using RGB-D cameras, which capture three-dimensional (3D) information of individual tubers moving along the conveyor belt. However, point clouds reconstructed from RGB-D images are incomplete due to self-occlusion, leading to systematic underestimation of tuber weight. To address this, we introduce PointRAFT, a high-throughput point cloud regression network that directly predicts continuous 3D shape properties, such as tuber weight, from partial point clouds. Rather than reconstructing full 3D geometry, PointRAFT infers target values directly from raw 3D data. Its key architectural novelty is an object height embedding that incorporates tuber height as an additional geometric cue, improving weight prediction under practical harvesting conditions. PointRAFT was trained and evaluated on 26,688 partial point clouds collected from 859 potato tubers across four cultivars and three growing seasons on an operational harvester in Japan. On a test set of 5,254 point clouds from 172 tubers, PointRAFT achieved a mean absolute error of 12.0 g and a root mean squared error of 17.2 g, substantially outperforming a linear regression baseline and a standard PointNet++ regression network. With an average inference time of 6.3 ms per point cloud, PointRAFT supports processing rates of up to 150 tubers per second, meeting the high-throughput requirements of commercial potato harvesters. Beyond potato weight estimation, PointRAFT provides a versatile regression network applicable to a wide range of 3D phenotyping and robotic perception tasks. The code, network weights, and a subset of the dataset are publicly available at https://github.com/pieterblok/pointraft.git.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Disentangling Past-Future Modeling in Sequential Recommendation via Dual Networks

Sequential recommendation (SR) plays an important role in personalized recommender systems because it captures dynamic and diverse preferences from users' real-time increasing behaviors. Unlike the standard autoregressive training strategy, future data (also available during training) has been used to facilitate model training as it provides richer signals about user's current interests and can be used to improve the recommendation quality. However, these methods suffer from a severe training-inference gap, i.e., both past and future contexts are modeled by the same encoder when training, while only historical behaviors are available during inference. This discrepancy leads to potential performance degradation. To alleviate the training-inference gap, we propose a new framework DualRec, which achieves past-future disentanglement and past-future mutual enhancement by a novel dual network. Specifically, a dual network structure is exploited to model the past and future context separately. And a bi-directional knowledge transferring mechanism enhances the knowledge learnt by the dual network. Extensive experiments on four real-world datasets demonstrate the superiority of our approach over baseline methods. Besides, we demonstrate the compatibility of DualRec by instantiating using RNN, Transformer, and filter-MLP as backbones. Further empirical analysis verifies the high utility of modeling future contexts under our DualRec framework. The code of DualRec is publicly available at https://github.com/zhy99426/DualRec.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

6G-enabled Edge AI for Metaverse: Challenges, Methods, and Future Research Directions

6G-enabled edge intelligence opens up a new era of Internet of Everything and makes it possible to interconnect people-devices-cloud anytime, anywhere. More and more next-generation wireless network smart service applications are changing our way of life and improving our quality of life. As the hottest new form of next-generation Internet applications, Metaverse is striving to connect billions of users and create a shared world where virtual and reality merge. However, limited by resources, computing power, and sensory devices, Metaverse is still far from realizing its full vision of immersion, materialization, and interoperability. To this end, this survey aims to realize this vision through the organic integration of 6G-enabled edge AI and Metaverse. Specifically, we first introduce three new types of edge-Metaverse architectures that use 6G-enabled edge AI to solve resource and computing constraints in Metaverse. Then we summarize technical challenges that these architectures face in Metaverse and the existing solutions. Furthermore, we explore how the edge-Metaverse architecture technology helps Metaverse to interact and share digital data. Finally, we discuss future research directions to realize the true vision of Metaverse with 6G-enabled edge AI.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A conservative low rank tensor method for the Vlasov dynamics

In this paper, we propose a conservative low rank tensor method to approximate nonlinear Vlasov solutions. The low rank approach is based on our earlier work (arxiv: 2106.08834). It takes advantage of the fact that the differential operators in the Vlasov equation are tensor friendly, based on which we propose to dynamically and adaptively build up low rank solution basis by adding new basis functions from discretization of the differential equation, and removing basis from a singular value decomposition (SVD)-type truncation procedure. For the discretization, we adopt a high order finite difference spatial discretization together with a second order strong stability preserving multi-step time discretization. While the SVD truncation will remove the redundancy in representing the high dimensional Vlasov solution, it will destroy the conservation properties of the associated full conservative scheme. In this paper, we develop a conservative truncation procedure with conservation of mass, momentum and kinetic energy densities. The conservative truncation is achieved by an orthogonal projection onto a subspace spanned by $1$, $v$ and $v^2$ in the velocity space associated with a weighted inner product. Then the algorithm performs a weighted SVD truncation of the remainder, which involves a scaling, followed by the standard SVD truncation and rescaling back. The algorithm is further developed in high dimensions with hierarchical Tucker tensor decomposition of high dimensional Vlasov solutions, overcoming the curse of dimensionality. An extensive set of nonlinear Vlasov examples are performed to show the effectiveness and conservation property of proposed conservative low rank approach. Comparison is performed against the non-conservative low rank tensor approach on conservation history of mass, momentum and energy.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Local Macroscopic Conservative (LoMaC) low rank tensor method for the Vlasov dynamics

In this paper, we propose a novel Local Macroscopic Conservative (LoMaC) low rank tensor method for simulating the Vlasov-Poisson (VP) system. The LoMaC property refers to the exact local conservation of macroscopic mass, momentum and energy at the discrete level. This is a follow-up work of our previous development of a conservative low rank tensor approach for Vlasov dynamics (arXiv:2201.10397). In that work, we applied a low rank tensor method with a conservative singular value decomposition (SVD) to the high dimensional VP system to mitigate the curse of dimensionality, while maintaining the local conservation of mass and momentum. However, energy conservation is not guaranteed, which is a critical property to avoid unphysical plasma self-heating or cooling. The new ingredient in the LoMaC low rank tensor algorithm is that we simultaneously evolve the macroscopic conservation laws of mass, momentum and energy using a flux-difference form with kinetic flux vector splitting; then the LoMaC property is realized by projecting the low rank kinetic solution onto a subspace that shares the same macroscopic observables by a conservative orthogonal projection. The algorithm is extended to the high dimensional problems by hierarchical Tuck decomposition of solution tensors and a corresponding conservative projection algorithm. Extensive numerical tests on the VP system are showcased for the algorithm's efficacy.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A temporal chrominance trigger for clean-label backdoor attack against anti-spoof rebroadcast detection

We propose a stealthy clean-label video backdoor attack against Deep Learning (DL)-based models aiming at detecting a particular class of spoofing attacks, namely video rebroadcast attacks. The injected backdoor does not affect spoofing detection in normal conditions, but induces a misclassification in the presence of a specific triggering signal. The proposed backdoor relies on a temporal trigger altering the average chrominance of the video sequence. The backdoor signal is designed by taking into account the peculiarities of the Human Visual System (HVS) to reduce the visibility of the trigger, thus increasing the stealthiness of the backdoor. To force the network to look at the presence of the trigger in the challenging clean-label scenario, we choose the poisoned samples used for the injection of the backdoor following a so-called Outlier Poisoning Strategy (OPS). According to OPS, the triggering signal is inserted in the training samples that the network finds more difficult to classify. The effectiveness of the proposed backdoor attack and its generality are validated experimentally on different datasets and anti-spoofing rebroadcast detection architectures.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Boiling and cavitation caused by transient heat transfer in superfluid helium-4

Superfluid helium-4 (He II) has been widely utilized as a coolant in various scientific and engineering applications due to its superior heat transfer capability. An important parameter required in the design of many He II based cooling systems is the peak heat flux $q^*$, which refers to the threshold heat flux above which boiling spontaneously occurs in He II. Past experimental and numerical studies showed that $q^*$ increases when the heating time $t_h$ is reduced, which leads to an intuitive expectation that very high $q^*$ may be achievable at sufficiently small $t_h$. Knowledge on how $q^*$ actually behaves at small $t_h$ is important for applications such as laser ablation in He II. Here we present a numerical study on the evolution of the thermodynamic state of the He II in front of a planar heater by solving the He II two-fluid equations of motion. For an applied heat flux, we determine the heating time beyond which the He II near the heater transits to the vapor phase. As such, a curve correlating $q^*$ and $t_h$ can be obtained, which nicely reproduces some relevant experimental data. Surprisingly, we find that there exists a critical peak heat flux $q^*_c$, above which boiling occurs nearly instantaneously regardless of $t_h$. We reveal that the boiling in this regime is essentially cavitation caused by the combined effects of the first-sound and the second-sound waves in He II. Based on this physical picture, an analytical model for $q^*_c$ is developed, which reproduces the simulated $q^*_c$ values at various He II bath temperatures and hydrostatic head pressures. This work represents a major progress in our understanding of transient heat transfer in He II.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation

Multi-types of behaviors (e.g., clicking, adding to cart, purchasing, etc.) widely exist in most real-world recommendation scenarios, which are beneficial to learn users' multi-faceted preferences. As dependencies are explicitly exhibited by the multiple types of behaviors, effectively modeling complex behavior dependencies is crucial for multi-behavior prediction. The state-of-the-art multi-behavior models learn behavior dependencies indistinguishably with all historical interactions as input. However, different behaviors may reflect different aspects of user preference, which means that some irrelevant interactions may play as noises to the target behavior to be predicted. To address the aforementioned limitations, we introduce multi-interest learning to the multi-behavior recommendation. More specifically, we propose a novel Coarse-to-fine Knowledge-enhanced Multi-interest Learning (CKML) framework to learn shared and behavior-specific interests for different behaviors. CKML introduces two advanced modules, namely Coarse-grained Interest Extracting (CIE) and Fine-grained Behavioral Correlation (FBC), which work jointly to capture fine-grained behavioral dependencies. CIE uses knowledge-aware information to extract initial representations of each interest. FBC incorporates a dynamic routing scheme to further assign each behavior among interests. Additionally, we use the self-attention mechanism to correlate different behavioral information at the interest level. Empirical results on three real-world datasets verify the effectiveness and efficiency of our model in exploiting multi-behavior data. Further experiments demonstrate the effectiveness of each module and the robustness and superiority of the shared and specific modelling paradigm for multi-behavior data.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Cross Pairwise Ranking for Unbiased Item Recommendation

Most recommender systems optimize the model on observed interaction data, which is affected by the previous exposure mechanism and exhibits many biases like popularity bias. The loss functions, such as the mostly used pointwise Binary Cross-Entropy and pairwise Bayesian Personalized Ranking, are not designed to consider the biases in observed data. As a result, the model optimized on the loss would inherit the data biases, or even worse, amplify the biases. For example, a few popular items take up more and more exposure opportunities, severely hurting the recommendation quality on niche items -- known as the notorious Mathew effect. In this work, we develop a new learning paradigm named Cross Pairwise Ranking (CPR) that achieves unbiased recommendation without knowing the exposure mechanism. Distinct from inverse propensity scoring (IPS), we change the loss term of a sample -- we innovatively sample multiple observed interactions once and form the loss as the combination of their predictions. We prove in theory that this way offsets the influence of user/item propensity on the learning, removing the influence of data biases caused by the exposure mechanism. Advantageous to IPS, our proposed CPR ensures unbiased learning for each training instance without the need of setting the propensity scores. Experimental results demonstrate the superiority of CPR over state-of-the-art debiasing solutions in both model generalization and training efficiency. The codes are available at https://github.com/Qcactus/CPR.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Dynamic Clustering and Power Control for Two-Tier Wireless Federated Learning

Federated learning (FL) has been recognized as a promising distributed learning paradigm to support intelligent applications at the wireless edge, where a global model is trained iteratively through the collaboration of the edge devices without sharing their data. However, due to the relatively large communication cost between the devices and parameter server (PS), direct computing based on the information from the devices may not be resource efficient. This paper studies the joint communication and learning design for the over-the-air computation (AirComp)-based two-tier wireless FL scheme, where the lead devices first collect the local gradients from their nearby subordinate devices, and then send the merged results to the PS for the second round of aggregation. We establish a convergence result for the proposed scheme and derive the upper bound on the optimality gap between the expected and optimal global loss values. Next, based on the device distance and data importance, we propose a hierarchical clustering method to build the two-tier structure. Then, with only the instantaneous channel state information (CSI), we formulate the optimality gap minimization problem and solve it by using an efficient alternating minimization method. Numerical results show that the proposed scheme outperforms the baseline ones.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Efficient Community Detection in Large-Scale Dynamic Networks Using Topological Data Analysis

In this paper, we propose a method that extends the persistence-based topological data analysis (TDA) that is typically used for characterizing shapes to general networks. We introduce the concept of the community tree, a tree structure established based on clique communities from the clique percolation method, to summarize the topological structures in a network from a persistence perspective. Furthermore, we develop efficient algorithms to construct and update community trees by maintaining a series of clique graphs in the form of spanning forests, in which each spanning tree is built on an underlying Euler Tour tree. With the information revealed by community trees and the corresponding persistence diagrams, our proposed approach is able to detect clique communities and keep track of the major structural changes during their evolution given a stability threshold. The results demonstrate its effectiveness in extracting useful structural insights for time-varying social networks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Extending the WILDS Benchmark for Unsupervised Adaptation

Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data and can often be obtained from distributions beyond the source distribution as well. However, existing distribution shift benchmarks with unlabeled data do not reflect the breadth of scenarios that arise in real-world applications. In this work, we present the WILDS 2.0 update, which extends 8 of the 10 datasets in the WILDS benchmark of distribution shifts to include curated unlabeled data that would be realistically obtainable in deployment. These datasets span a wide range of applications (from histology to wildlife conservation), tasks (classification, regression, and detection), and modalities (photos, satellite images, microscope slides, text, molecular graphs). The update maintains consistency with the original WILDS benchmark by using identical labeled training, validation, and test sets, as well as the evaluation metrics. On these datasets, we systematically benchmark state-of-the-art methods that leverage unlabeled data, including domain-invariant, self-training, and self-supervised methods, and show that their success on WILDS is limited. To facilitate method development and evaluation, we provide an open-source package that automates data loading and contains all of the model architectures and methods used in this paper. Code and leaderboards are available at https://wilds.stanford.edu.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

High order chiral Lagrangians with vector mesons in different approaches

The chiral Lagrangians with vector mesons are constructed in different approaches, including the next-to-leading order Lagrangian in the vector-field approach, the next-to-next-to-leading order Lagrangians in the tensor-field and the hidden local symmetry approaches. Some redundant terms are found at the next-to-leading order in the tensor-field and the hidden local symmetry approaches. The corresponding relations between the next-to-next-to-leading order pseudoscalar mesonic low-energy constants and the ones in the hidden local symmetry approach are obtained at tree level. The equivalence between the tensor-field approach and the hidden local symmetry approach is also discussed.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Improved-Flow Warp Module for Remote Sensing Semantic Segmentation

Remote sensing semantic segmentation aims to assign automatically each pixel on aerial images with specific label. In this letter, we proposed a new module, called improved-flow warp module (IFWM), to adjust semantic feature maps across different scales for remote sensing semantic segmentation. The improved-flow warp module is applied along with the feature extraction process in the convolutional neural network. First, IFWM computes the offsets of pixels by a learnable way, which can alleviate the misalignment of the multi-scale features. Second, the offsets help with the low-resolution deep feature up-sampling process to improve the feature accordance, which boosts the accuracy of semantic segmentation. We validate our method on several remote sensing datasets, and the results prove the effectiveness of our method..

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Investigation on the self-starting Mamyshev oscillator with low threshold

We have demonstrated a mode-locked Mamyshev oscillator based on a single-mode-fibre configuration with low threshould. The influences of spectral filters and the pump power on the output laser characteristics have been investigated. In the case with spectral-filter central wavelength far away from the peak of gain spectrum, the laser pulses have deviated slightly from similariton evolution with gain-shaping under high pump power. Moreover, self-starting mode-locking operation has been realized when the pump power was only 520 mW, which might benefit from the appropriate polarization conditions and small spectral filter separation. The laser can generate 1.89-nJ ultra-short pulses with 20-dB spectral width of 54.6 nm. The pulse duration can be compressed externally to 64.69 fs with the peak power of 21.3 kW.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Joint Device Selection and Power Control for Wireless Federated Learning

This paper studies the joint device selection and power control scheme for wireless federated learning (FL), considering both the downlink and uplink communications between the parameter server (PS) and the terminal devices. In each round of model training, the PS first broadcasts the global model to the terminal devices in an analog fashion, and then the terminal devices perform local training and upload the updated model parameters to the PS via over-the-air computation (AirComp). First, we propose an AirComp-based adaptive reweighing scheme for the aggregation of local updated models, where the model aggregation weights are directly determined by the uplink transmit power values of the selected devices and which enables the joint learning and communication optimization simply by the device selection and power control. Furthermore, we provide a convergence analysis for the proposed wireless FL algorithm and the upper bound on the expected optimality gap between the expected and optimal global loss values is derived. With instantaneous channel state information (CSI), we formulate the optimality gap minimization problems under both the individual and sum uplink transmit power constraints, respectively, which are shown to be solved by the semidefinite programming (SDR) technique. Numerical results reveal that our proposed wireless FL algorithm achieves close to the best performance by using the ideal FedAvg scheme with error-free model exchange and full device participation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction

CTR prediction is essential for modern recommender systems. Ranging from early factorization machines to deep learning based models in recent years, existing CTR methods focus on capturing useful feature interactions or mining important behavior patterns. Despite the effectiveness, we argue that these methods suffer from the risk of label sparsity (i.e., the user-item interactions are highly sparse with respect to the feature space), label noise (i.e., the collected user-item interactions are usually noisy), and the underuse of domain knowledge (i.e., the pairwise correlations between samples). To address these challenging problems, we propose a novel Multi-Interest Self-Supervised learning (MISS) framework which enhances the feature embeddings with interest-level self-supervision signals. With the help of two novel CNN-based multi-interest extractors,self-supervision signals are discovered with full considerations of different interest representations (point-wise and union-wise), interest dependencies (short-range and long-range), and interest correlations (inter-item and intra-item). Based on that, contrastive learning losses are further applied to the augmented views of interest representations, which effectively improves the feature representation learning. Furthermore, our proposed MISS framework can be used as an plug-in component with existing CTR prediction models and further boost their performances. Extensive experiments on three large-scale datasets show that MISS significantly outperforms the state-of-the-art models, by up to 13.55% in AUC, and also enjoys good compatibility with representative deep CTR models.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Nonlinear beam self-maintaining effect in graded-index multimode fiber

Multimode fiber systems are desirable for industrial and scientific applications. As an interesting effect for the laser beam propagation in a multimode fiber, nonlinear Kerr beam cleanup has attracted considerable research interest due to the spatial beam compressing. However, its physical mechanisms, especially the influences of input conditions on its performances, remain unclear. Here, we report a new self-organized regime for the multimode beam propagation in a graded-index multimode fiber: when the input laser has a dominant mode in which most of the laser energy is concentrated, the beam profile can be maintaining in a well-defined structure similar to the input dominant mode in nonlinear regime, while it will evolve to an irregular pattern in linear regime. The existence and universality of this nonlinear beam self-maintaining effect have been verified by the experimental and numerical data. Our results also provide evidence that nonlinear Kerr effects can be the driving mechanism and nonlinear Kerr beam cleanup is a specific case of this effect. Further research into this spatial beam shaping effect may provide a new perspective to understand other multimode fiber nonlinearities.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurance

The separation assurance task will be extremely challenging for air traffic controllers in a complex and high density airspace environment. Deep reinforcement learning (DRL) was used to develop an autonomous separation assurance framework in our previous work where the learned model advised speed maneuvers. In order to improve the safety of this model in unseen environments with uncertainties, in this work we propose a safety module for DRL in autonomous separation assurance applications. The proposed module directly addresses both model uncertainty and state uncertainty to improve safety. Our safety module consists of two sub-modules: (1) the state safety sub-module is based on the execution-time data augmentation method to introduce state disturbances in the model input state; (2) the model safety sub-module is a Monte-Carlo dropout extension that learns the posterior distribution of the DRL model policy. We demonstrate the effectiveness of the two sub-modules in an open-source air traffic simulator with challenging environment settings. Through extensive numerical experiments, our results show that the proposed sub-safety modules help the DRL agent significantly improve its safety performance in an autonomous separation assurance task.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Single electrons on solid neon as a solid-state qubit platform

Progress toward the realization of quantum computers requires persistent advances in their constituent building blocks - qubits. Novel qubit platforms that simultaneously embody long coherence, fast operation, and large scalability offer compelling advantages in the construction of quantum computers and many other quantum information systems. Electrons, ubiquitous elementary particles of nonzero charge, spin, and mass, have commonly been perceived as paradigmatic local quantum information carriers. Despite superior controllability and configurability, their practical performance as qubits via either motional or spin states depends critically on their material environment. Here we report our experimental realization of a new qubit platform based upon isolated single electrons trapped on an ultraclean solid neon surface in vacuum. By integrating an electron trap in a circuit quantum electrodynamics architecture, we achieve strong coupling between the motional states of a single electron and a single microwave photon in an on-chip superconducting resonator. Qubit gate operations and dispersive readout are implemented to measure the energy relaxation time $T_1$ of $15~μ$s and phase coherence time $T_2$ over $200~$ns. These results indicate that the electron-on-solid-neon qubit already performs near the state of the art as a charge qubit.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Universal anomalous turbulent diffusion in quantum fluids

In classical viscous fluids, turbulent eddies are known to be responsible for the rapid spreading of embedded particles. But in an inviscid quantum fluid where the turbulence is induced by a chaotic tangle of quantized vortices, dispersion of the particles is achieved via a non-classical mechanism, i.e., their binding to the evolving quantized vortices. However, there is limited existing knowledge on how the vortices diffuse and spread in turbulent quantum fluids. Here we report a systematic numerical study of the apparent diffusion of vortices in a random vortex tangle in superfluid helium-4 using full Biot-Savart simulation. We reveal that the vortices in pure superfluid exhibit a universal anomalous diffusion (superdiffusion) at small times, which transits to normal diffusion at large times. This behavior is found to be caused by a generic scaling property of the vortex velocity, which should exist in all quantum fluids where the Biot-Savart law governs the vortex motion. Our simulation at finite temperatures also nicely reproduces recent experimental observations. The knowledge obtained from this study may form the foundation for understanding turbulent transport and universal vortex dynamics in various condensed-matter and cosmic quantum fluids.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Velocity circulation intermittency in finite-temperature turbulent superfluid helium

We study intermittency of circulation moments in turbulent superfluid helium by using experimental grid turbulence and numerical simulations of the Hall-Vinen-Bekarevich-Khalatnikov model. More precisely, we compute the velocity circulation $Γ_r$ in loops of size $r$ laying in the inertial range. For both, experimental and numerical data, the circulation variance shows a clear Kolmogorov scaling $\langle Γ_r^2 \rangle \sim r^{8/3}$ in the inertial range, independently of the temperature. Scaling exponents of high-order moments are comparable, within error bars, to previously reported anomalous circulation exponents in classical turbulence and low-temperature quantum turbulence numerical simulations.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

a dynamo-based prediction of solar cycle 25

Solar activity cycle varies in amplitude. The last Cycle 24 is the weakest in the past century. Sun's activity dominates Earth's space environment. The frequency and intensity of the Sun's activity are accordant with the solar cycle. Hence there are practical needs to know the amplitude of the upcoming Cycle 25. The dynamo-based solar cycle predictions not only provide predictions, but also offer an effective way to evaluate our understanding of the solar cycle. In this article we apply the method of the first successful dynamo-based prediction developed for Cycle 24 to the prediction of Cycle 25, so that we can verify whether the previous success is repeatable. The prediction shows that Cycle 25 would be about 10% stronger than Cycle 24 with an amplitude of 126 (international sunspot number version 2.0). The result suggests that Cycle 25 will not enter the Maunder-like grand solar minimum as suggested by some publications. Solar behavior in about four to five years will give a verdict whether the prediction method captures the key mechanism for solar cycle variability, which is assumed as the polar field around the cycle minimum in the model.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

A Low Rank Tensor Representation of Linear Transport and Nonlinear Vlasov Solutions and Their Associated Flow Maps

We propose a low-rank tensor approach to approximate linear transport and nonlinear Vlasov solutions and their associated flow maps. The approach takes advantage of the fact that the differential operators in the Vlasov equation is tensor friendly, based on which we propose a novel way to dynamically and adaptively build up low-rank solution basis by adding new basis functions from discretization of the PDE, and removing basis from an SVD-type truncation procedure. For the discretization, we adopt a high order finite difference spatial discretization and a second order strong stability preserving multi-step time discretization. We apply the same procedure to evolve the dynamics of the flow map in a low-rank fashion, which proves to be advantageous when the flow map enjoys the low rank structure, while the solution suffers from high rank or displays filamentation structures. Hierarchical Tucker decomposition is adopted for high dimensional problems. An extensive set of linear and nonlinear Vlasov test examples are performed to show the high order spatial and temporal convergence of the algorithm with mesh refinement up to SVD-type truncation, the significant computational savings of the proposed low-rank approach especially for high dimensional problems, the improved performance of the flow map approach for solutions with filamentations.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data

Interactive response time is important in analytical pipelines for users to explore a sufficient number of possibilities and make informed business decisions. We consider a forecasting pipeline with large volumes of high-dimensional time series data. Real-time forecasting can be conducted in two steps. First, we specify the part of data to be focused on and the measure to be predicted by slicing, dicing, and aggregating the data. Second, a forecasting model is trained on the aggregated results to predict the trend of the specified measure. While there are a number of forecasting models available, the first step is the performance bottleneck. A natural idea is to utilize sampling to obtain approximate aggregations in real time as the input to train the forecasting model. Our scalable real-time forecasting system FlashP (Flash Prediction) is built based on this idea, with two major challenges to be resolved in this paper: first, we need to figure out how approximate aggregations affect the fitting of forecasting models, and forecasting results; and second, accordingly, what sampling algorithms we should use to obtain these approximate aggregations and how large the samples are. We introduce a new sampling scheme, called GSW sampling, and analyze error bounds for estimating aggregations using GSW samples. We introduce how to construct compact GSW samples with the existence of multiple measures to be analyzed. We conduct experiments to evaluate our solution and compare it with alternatives on real data.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Light propagation and observed light propagation

Light propagation is viewed as a process involving mutual creation of electric and magnetic fields. This viewpoint is used to argue that the conventional retarded solutions to electromagnetic wave equations (whose source is a current density in this work) are wrong, and to solve the wave equations in a different way by tracking every step in the said process. It turns out that the solutions to the wave equations, or the emitted fields from the current density, have equally weighted advanced and retarded components. After these components are explained for their mathematical and physical origins, it is then pointed out that the emitted fields are related but not identical to those fields observed in light observation. The latter fields are calculated and found, as expected, to be retarded.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Spatiotemporal Differences of COVID-19 Infection among Healthcare Workers and Patients in China from January to March 2020

Studying the spatiotemporal differences in coronavirus disease (COVID-19) between social groups such as healthcare workers (HCWs) and patients can aid in formulating epidemic containment policies. Most previous studies of the spatiotemporal characteristics of COVID-19 were conducted in a single group and did not explore the differences between groups. To fill this research gap, this study assessed the spatiotemporal characteristics and differences among patients and HCWs infection in Wuhan, Hubei (excluding Wuhan), and China (excluding Hubei). The temporal difference was greater in Wuhan than in the rest of Hubei, and was greater in Hubei (excluding Wuhan) than in the rest of China. The incidence was high in healthcare workers in the early stages of the epidemic. Therefore, it is important to strengthen the protective measures for healthcare workers in the early stage of the epidemic. The spatial difference was less in Wuhan than in the rest of Hubei, and less in Hubei (excluding Wuhan) than in the rest of China. The spatial distribution of healthcare worker infections can be used to infer the spatial distribution of the epidemic in the early stage and to formulate control measures accordingly.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

5G Radio Access Network Architecture for Terrestrial Broadcast Services

The 3rd Generation Partnership Project (3GPP) has defined based on the Long Term Evolution (LTE) enhanced Multicast Broadcast Multimedia Service (eMBMS) a set of new features to support the distribution of Terrestrial Broadcast services in Release 14. On the other hand, a new 5th Generation (5G) system architecture and radio access technology, 5G New Radio (NR), are being standardised from Release 15 onwards, which so far have only focused on unicast connectivity. This may change in Release 17 given a new Work Item set to specify basic Radio Access Network (RAN) functionalities for the provision of multicast/broadcast communications for NR. This work initially excludes some of the functionalities originally supported for Terrestrial Broadcast services under LTE e.g. free to air, receive-only mode, large-area single frequency networks, etc. This paper proposes an enhanced Next Generation RAN architecture based on 3GPP Release 15 with a series of architectural and functional enhancements, to support an efficient, flexible and dynamic selection between unicast and multicast/broadcast transmission modes and also the delivery of Terrestrial Broadcast services. The paper elaborates on the Cloud-RAN based architecture and proposes new concepts such as the RAN Broadcast/Multicast Areas that allows a more flexible deployment in comparison to eMBMS. High-level assessment methodologies including complexity analysis and inspection are used to evaluate the feasibility of the proposed architecture design and compare it with the 3GPP architectural requirements.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A cryogenic-helium pipe flow facility with unique double-line molecular tagging velocimetry capability

Cryogenic helium-4 has extremely small kinetic viscosity, which makes it a promising material for high Reynolds ($Re$) number turbulence research in compact laboratory apparatuses. In its superfluid phase (He II), helium has an extraordinary heat transfer capability and has been utilized in various scientific and engineering applications. In order to unlock the full potential of helium in turbulence research and to improve our understanding of the heat transfer mechanism in He II, a flow facility that allows quantitative study of helium heat-and-mass transfer processes is needed. Here we report our work in assembling and testing a unique helium pipe flow facility that incorporates a novel double-line molecular tracking velocimetry (DL-MTV) system. This flow facility allows us to generate turbulent pipe flows with $Re$ above $10^7$, and it can also be adapted to produce heat-induced counterflow in He II. The DL-MTV system, which is based on the generation and tracking of two parallel thin He$^*_2$ molecular tracer lines with an adjustable separation distance, allows us to measure not only the velocity profile but also both the transverse and longitudinal spatial velocity structure functions. We have also installed a deferential pressure sensor to the flow pipe for pressure drop measurement. The testing results of the flow facility and the measurement devices are presented. We discuss how this facility will allow us to solve some outstanding problems in the helium heat-and-mass transfer topic area.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A semi-Lagrangian discontinuous Galerkin (DG) -- local DG method for solving convection-diffusion equations

In this paper, we propose an efficient high order semi-Lagrangian (SL) discontinuous Galerkin (DG) method for solving linear convection-diffusion equations. The method generalizes our previous work on developing the SLDG method for transport equations (J. Sci. Comput. 73: 514-542, 2017), making it capable of handling additional diffusion and source terms. Within the DG framework, the solution is evolved along the characteristics; while the diffusion term is discretized by the local DG (LDG) method and integrated along characteristics by implicit Runge-Kutta methods together with source terms. The proposed method is named the `SLDG-LDG' method and enjoys many attractive features of the DG and SL methods. These include the uniformly high order accuracy (e.g. third order) in space and in time, compact, mass conservative, and stability under large time stepping size. An $L^2$ stability analysis is provided when the method is coupled with the first order backward Euler discretization. Effectiveness of the method are demonstrated by a group of numerical tests in one and two dimensions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Active Learning with Point Supervision for Cost-Effective Panicle Detection in Cereal Crops

Panicle density of cereal crops such as wheat and sorghum is one of the main components for plant breeders and agronomists in understanding the yield of their crops. To phenotype the panicle density effectively, researchers agree there is a significant need for computer vision-based object detection techniques. Especially in recent times, research in deep learning-based object detection shows promising results in various agricultural studies. However, training such systems usually requires a lot of bounding-box labeled data. Since crops vary by both environmental and genetic conditions, acquisition of huge amount of labeled image datasets for each crop is expensive and time-consuming. Thus, to catalyze the widespread usage of automatic object detection for crop phenotyping, a cost-effective method to develop such automated systems is essential. We propose a point supervision based active learning approach for panicle detection in cereal crops. In our approach, the model constantly interacts with a human annotator by iteratively querying the labels for only the most informative images, as opposed to all images in a dataset. Our query method is specifically designed for cereal crops which usually tend to have panicles with low variance in appearance. Our method reduces labeling costs by intelligently leveraging low-cost weak labels (object centers) for picking the most informative images for which strong labels (bounding boxes) are required. We show promising results on two publicly available cereal crop datasets - Sorghum and Wheat. On Sorghum, 6 variants of our proposed method outperform the best baseline method with more than 55% savings in labeling time. Similarly, on Wheat, 3 variants of our proposed methods outperform the best baseline method with more than 50% of savings in labeling time.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

An adaptive multiresolution interior penalty discontinuous Galerkin method for wave equations in second order form

In this paper, we propose a class of adaptive multiresolution (also called adaptive sparse grid) discontinuous Galerkin (DG) methods for simulating scalar wave equations in second order form in space. The two key ingredients of the schemes include an interior penalty DG formulation in the adaptive function space and two classes of multiwavelets for achieving multiresolution. In particular, the orthonormal Alpert's multiwavelets are used to express the DG solution in terms of a hierarchical structure, and the interpolatory multiwavelets are further introduced to enhance computational efficiency in the presence of variable wave speed or nonlinear source. Some theoretical results on stability and accuracy of the proposed method are presented. Benchmark numerical tests in 2D and 3D are provided to validate the performance of the method.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

An adaptive multiresolution ultra-weak discontinuous Galerkin method for nonlinear Schrodinger equations

This paper develops a high order adaptive scheme for solving nonlinear Schrodinger equations. The solutions to such equations often exhibit solitary wave and local structures, which makes adaptivity essential in improving the simulation efficiency. Our scheme uses the ultra-weak discontinuous Galerkin (DG) formulation and belongs to the framework of adaptive multiresolution schemes. Various numerical experiments are presented to demonstrate the excellent capability of capturing the soliton waves and the blow-up phenomenon.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey

In light of growing challenges in agriculture with ever growing food demand across the world, efficient crop management techniques are necessary to increase crop yield. Precision agriculture techniques allow the stakeholders to make effective and customized crop management decisions based on data gathered from monitoring crop environments. Plant phenotyping techniques play a major role in accurate crop monitoring. Advancements in deep learning have made previously difficult phenotyping tasks possible. This survey aims to introduce the reader to the state of the art research in deep plant phenotyping.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Fully Coupled Two-Fluid Dynamics in Superfluid $^4$He: Anomalous Anisotropic Velocity Fluctuations in Counterflow

We investigate the thermal counterflow of the superfluid $^4$He by numerically simulating three-dimensional fully coupled dynamics of the two fluids, namely quantized vortices and a normal fluid. We analyze the velocity fluctuations of the laminar normal fluid arising from the mutual friction with the quantum turbulence of the superfluid component. The streamwise fluctuations exhibit higher intensity and longer-range autocorrelation, as compared to transverse ones. The anomalous fluctuations are consistent with visualization experiments [Mastracci et al., Phys. Rev. Fluids, Vol. 4, 083305 (2019)], and our results confirm their analysis with simple models on the anisotropic fluctuations. This success validates the model of the fully coupled dynamics and paves the way for solving some outstanding problems in this two-fluid system.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems

Given the convenience of collecting information through online services, recommender systems now consume large scale data and play a more important role in improving user experience. With the recent emergence of Graph Neural Networks (GNNs), GNN-based recommender models have shown the advantage of modeling the recommender system as a user-item bipartite graph to learn representations of users and items. However, such models are expensive to train and difficult to perform frequent updates to provide the most up-to-date recommendations. In this work, we propose to update GNN-based recommender models incrementally so that the computation time can be greatly reduced and models can be updated more frequently. We develop a Graph Structure Aware Incremental Learning framework, GraphSAIL, to address the commonly experienced catastrophic forgetting problem that occurs when training a model in an incremental fashion. Our approach preserves a user's long-term preference (or an item's long-term property) during incremental model updating. GraphSAIL implements a graph structure preservation strategy which explicitly preserves each node's local structure, global structure, and self-information, respectively. We argue that our incremental training framework is the first attempt tailored for GNN based recommender systems and demonstrate its improvement compared to other incremental learning techniques on two public datasets. We further verify the effectiveness of our framework on a large-scale industrial dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Molecular Tagging Velocimetry in Superfluid Helium-4: Progress, Issues, and Future Development

Helium-4 in the superfluid phase (He II) is a two-fluid system that exhibits fascinating quantum hydrodynamics with important scientific and engineering applications. However, the lack of high-precision flow measurement tools in He II has impeded the progress in understanding and utilizing its hydrodynamics. In recent years, there have been extensive efforts in developing quantitative flow visualization techniques applicable to He II. In particular, a powerful molecular tagging velocimetry (MTV) technique, based on tracking thin lines of He$^*_2$ excimer molecules created via femtosecond laser-field ionization in helium, has been developed in our lab. This technique allows unambiguous measurement of the normal-fluid velocity field in the two-fluid system. Nevertheless, there are two limitations of this technique: 1) only the velocity component perpendicular to the tracer line can be measured; and 2) there is an inherent error in determining the perpendicular velocity. In this paper, we discuss how these issues can be resolved by advancing the MTV technique. We also discuss two novel schemes for tagging and producing He$^*_2$ tracers. The first method allows the creation of a tagged He$^*_2$ tracer line without the use of an expensive femtosecond laser. The second method enables full-space velocity field measurement through tracking small clouds of He$^*_2$ molecules created via neutron-$^3$He absorption reactions in He II.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Stereoscopic molecular tagging for superconducting accelerator-cavity quench spot detection

Superconducting radio-frequency (SRF) cavities cooled by superfluid helium-4 (He II) are building blocks of many modern particle accelerators due to their high quality factor. However, Joule heating from sub-millimeter surface defects on cavities can lead to cavity quenching, which limits the maximum acceleration gradient of the accelerators. Developing a non-contacting detection technology to accurately locate these surface defects is the key to improve the performance of SRF cavities and hence the accelerators. In a recent proof-of-concept experiment (Phys. Rev. Applied, 11, 044003 (2019)), we demonstrated that a molecular tagging velocimetry (MTV) technique based on the tracking of a He$_2^*$ molecular tracer line created nearby a surface hot spot in He II can be utilized to locate the hot spot. In order to make this technique practically useful, here we describe our further development of a stereoscopic MTV setup for tracking the tracer line's motion in three-dimensional (3D) space. We simulate a quench spot by applying a transient voltage pulse to a small heater mounted on a substrate plate. Images of the drifted tracer line, taken with two cameras from orthogonal directions, are used to reconstruct the line profile in 3D space. A new algorithm for analyzing the 3D line profile is developed, which incorporates the finite size effect of the heater. We show that the center location of the heater can be reproduced on the substrate surface with an uncertainty of only a few hundred microns, thereby proving the practicability of this method.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Torquing the Condensate: Angular Momentum Transport in Bose-Einstein Condensates by Solitonic "Corkscrew"

When rotating classical fluid drops merge together, angular momentum can be advected from one to another due to the viscous shear flow at the drop interface. It remains elusive what the corresponding mechanism is in inviscid quantum fluids such as Bose-Einstein condensates (BECs). Here we report our theoretical study of an initially static BEC merging with a rotating BEC in three-dimensional space along the rotational axis. We show that a soliton sheet resembling a "corkscrew" spontaneously emerges at the interface. Rapid angular momentum transfer at a constant rate universally proportional to the initial angular momentum density is observed. Strikingly, this transfer does not necessarily involve fluid advection or drifting of the quantized vortices. We reveal that the solitonic corkscrew can exert a torque that directly creates angular momentum in the static BEC and annihilates angular momentum in the rotating BEC. Uncovering this intriguing angular momentum transport mechanism may benefit our understanding of various coherent matter-wave systems, spanning from atomtronics on chips to dark matter BECs at cosmic scales.

0 citations0 reviewsNo code linkedOpen access