Researcher profile

Yu Zheng

Yu Zheng contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

37works

0followers

27topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

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

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

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.

preprint2026arXiv

SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference

LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized. We propose \textbf{SPECTRE} (Parallel \textbf{SPEC}ulative Decoding with a Multi-\textbf{T}enant \textbf{RE}mote Drafter), a serving framework that reuses underutilized tail-model services as remote drafters for heavily loaded large-model services through speculative decoding. SPECTRE enables draft generation and target-side verification to run in parallel, and makes such parallelism effective through three techniques: a hybrid ordinary-parallel speculative decoding strategy guided by a threshold derived from throughput analysis, speculative priority scheduling to preserve draft--target overlap under multi-tenant traffic, and draft-side prompt compression to reduce draft latency. We implement SPECTRE in \texttt{SGLang} and evaluate it across multiple draft--target model pairs, reasoning benchmarks, real-world long-context workloads, and a wide range of batch sizes. Results show that SPECTRE consistently improves large-model serving throughput while causing only minor interference to the native workloads of tail-model services. In large-model deployments, including Qwen3-235B-A22B with TP=8, SPECTRE achieves up to \textbf{2.28$\times$ speedup} over autoregressive decoding and up to an additional \textbf{66\% relative improvement} over the strongest speculative decoding baselines. Talk is cheap, we show you the code: https://github.com/sgl-project/sglang/pull/22272.

preprint2023arXiv

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

Recommender system is one of the most important information services on today's Internet. Recently, graph neural networks have become the new state-of-the-art approach to recommender systems. In this survey, we conduct a comprehensive review of the literature on graph neural network-based recommender systems. We first introduce the background and the history of the development of both recommender systems and graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist of two categories, spectral models and spatial ones. We then discuss the motivation of applying graph neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural property of data, and the enhanced supervision signal. We then systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency. Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions on the open problems and promising future directions in this area. We summarize the representative papers along with their code repositories in \url{https://github.com/tsinghua-fib-lab/GNN-Recommender-Systems}.

preprint2022arXiv

A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling

Data insufficiency problems (i.e., data missing and label scarcity) caused by inadequate services and infrastructures or imbalanced development levels of cities have seriously affected the urban computing tasks in real scenarios. Prior transfer learning methods inspire an elegant solution to the data insufficiency, but are only concerned with one kind of insufficiency issue and fail to give consideration to both sides. In addition, most previous cross-city transfer methods overlook inter-city data privacy which is a public concern in practical applications. To address the above challenging problems, we propose a novel Cross-city Federated Transfer Learning framework (CcFTL) to cope with the data insufficiency and privacy problems. Concretely, CcFTL transfers the relational knowledge from multiple rich-data source cities to the target city. Besides, the model parameters specific to the target task are firstly trained on the source data and then fine-tuned to the target city by parameter transfer. With our adaptation of federated training and homomorphic encryption settings, CcFTL can effectively deal with the data privacy problem among cities. We take the urban region profiling as an application of smart cities and evaluate the proposed method with a real-world study. The experiments demonstrate the notable superiority of our framework over several competitive state-of-the-art methods.

preprint2022arXiv

Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i.e. annotations of object centers). In order to remedy the information loss from box annotations to centers, our method, namely Back to Reality (BR), makes use of synthetic 3D shapes to convert the weak labels into fully-annotated virtual scenes as stronger supervision, and in turn utilizes the perfect virtual labels to complement and refine the real labels. Specifically, we first assemble 3D shapes into physically reasonable virtual scenes according to the coarse scene layout extracted from position-level annotations. Then we go back to reality by applying a virtual-to-real domain adaptation method, which refine the weak labels and additionally supervise the training of detector with the virtual scenes. Furthermore, we propose a more challenging benckmark for indoor 3D object detection with more diversity in object sizes to better show the potential of BR. With less than 5% of the labeling labor, we achieve comparable detection performance with some popular fully-supervised approaches on the widely used ScanNet dataset. Code is available at: https://github.com/wyf-ACCEPT/BackToReality

preprint2022arXiv

Configuration-Aware Safe Control for Mobile Robotic Arm with Control Barrier Functions

Collision avoidance is a widely investigated topic in robotic applications. When applying collision avoidance techniques to a mobile robot, how to deal with the spatial structure of the robot still remains a challenge. In this paper, we design a configuration-aware safe control law by solving a Quadratic Programming (QP) with designed Control Barrier Functions (CBFs) constraints, which can safely navigate a mobile robotic arm to a desired region while avoiding collision with environmental obstacles. The advantage of our approach is that it correctly and in an elegant way incorporates the spatial structure of the mobile robotic arm. This is achieved by merging geometric restrictions among mobile robotic arm links into CBFs constraints. Simulations on a rigid rod and the modeled mobile robotic arm are performed to verify the feasibility and time-efficiency of proposed method. Numerical results about the time consuming for different degrees of freedom illustrate that our method scales well with dimension.

preprint2022arXiv

DA$^2$ Dataset: Toward Dexterity-Aware Dual-Arm Grasping

In this paper, we introduce DA$^2$, the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects. The dataset contains about 9M pairs of parallel-jaw grasps, generated from more than 6000 objects and each labeled with various grasp dexterity measures. In addition, we propose an end-to-end dual-arm grasp evaluation model trained on the rendered scenes from this dataset. We utilize the evaluation model as our baseline to show the value of this novel and nontrivial dataset by both online analysis and real robot experiments. All data and related code will be open-sourced at https://sites.google.com/view/da2dataset.

preprint2022arXiv

Deep AutoAugment

While recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA). DeepAA progressively builds a multi-layer data augmentation pipeline from scratch by stacking augmentation layers one at a time until reaching convergence. For each augmentation layer, the policy is optimized to maximize the cosine similarity between the gradients of the original and augmented data along the direction with low variance. Our experiments show that even without default augmentations, we can learn an augmentation policy that achieves strong performance with that of previous works. Extensive ablation studies show that the regularized gradient matching is an effective search method for data augmentation policies. Our code is available at: https://github.com/MSU-MLSys-Lab/DeepAA .

preprint2022arXiv

DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning

Optimizing the combustion efficiency of a thermal power generating unit (TPGU) is a highly challenging and critical task in the energy industry. We develop a new data-driven AI system, namely DeepThermal, to optimize the combustion control strategy for TPGUs. At its core, is a new model-based offline reinforcement learning (RL) framework, called MORE, which leverages historical operational data of a TGPU to solve a highly complex constrained Markov decision process problem via purely offline training. In DeepThermal, we first learn a data-driven combustion process simulator from the offline dataset. The RL agent of MORE is then trained by combining real historical data as well as carefully filtered and processed simulation data through a novel restrictive exploration scheme. DeepThermal has been successfully deployed in four large coal-fired thermal power plants in China. Real-world experiments show that DeepThermal effectively improves the combustion efficiency of TPGUs. We also report the superior performance of MORE by comparing with the state-of-the-art algorithms on the standard offline RL benchmarks.

preprint2022arXiv

Disentangling Long and Short-Term Interests for Recommendation

Modeling user's long-term and short-term interests is crucial for accurate recommendation. However, since there is no manually annotated label for user interests, existing approaches always follow the paradigm of entangling these two aspects, which may lead to inferior recommendation accuracy and interpretability. In this paper, to address it, we propose a Contrastive learning framework to disentangle Long and Short-term interests for Recommendation (CLSR) with self-supervision. Specifically, we first propose two separate encoders to independently capture user interests of different time scales. We then extract long-term and short-term interests proxies from the interaction sequences, which serve as pseudo labels for user interests. Then pairwise contrastive tasks are designed to supervise the similarity between interest representations and their corresponding interest proxies. Finally, since the importance of long-term and short-term interests is dynamically changing, we propose to adaptively aggregate them through an attention-based network for prediction. We conduct experiments on two large-scale real-world datasets for e-commerce and short-video recommendation. Empirical results show that our CLSR consistently outperforms all state-of-the-art models with significant improvements: GAUC is improved by over 0.01, and NDCG is improved by over 4%. Further counterfactual evaluations demonstrate that stronger disentanglement of long and short-term interests is successfully achieved by CLSR. The code and data are available at https://github.com/tsinghua-fib-lab/CLSR.

preprint2022arXiv

Disordered Hyperuniform Quasi-1D Materials

Carbon nanotubes are quasi-one-dimensional systems that possess superior transport, mechanical, optical, and chemical properties. In this work, we generalize the notion of disorder hyperuniformity, a recently discovered exotic state of matter with hidden long-range order, to quasi-one-dimensional materials. As a proof of concept, we then apply the generalized framework to quantify the density fluctuations in amorphous carbon nanotubes containing randomly distributed Stone-Wales defects. We demonstrate that all of these amorphous nanotubes are hyperuniform, i.e., the infinite-wavelength density fluctuations of these systems are completely suppressed, regardless of the diameter, rolling axis, number of rolling sheets, and defect fraction of the nanotubes. We find that these amorphous nanotubes are energetically more stable than nanotubes with periodically distributed Stone-Wales defects. Moreover, certain semiconducting defect-free carbon nanotubes become metallic as sufficiently large amounts of defects are randomly introduced. This structural study of amorphous nanotubes strengthens our fundamental understanding of these systems, and suggests possible exotic physical properties, as endowed by their disordered hyperuniformity. Our findings also shed light on the effect of dimensionality reduction on the hyperuniformity property of materials.

preprint2022arXiv

DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias

Recommender systems are prone to be misled by biases in the data. Models trained with biased data fail to capture the real interests of users, thus it is critical to alleviate the impact of bias to achieve unbiased recommendation. In this work, we focus on an essential bias in micro-video recommendation, duration bias. Specifically, existing micro-video recommender systems usually consider watch time as the most critical metric, which measures how long a user watches a video. Since videos with longer duration tend to have longer watch time, there exists a kind of duration bias, making longer videos tend to be recommended more against short videos. In this paper, we empirically show that commonly-used metrics are vulnerable to duration bias, making them NOT suitable for evaluating micro-video recommendation. To address it, we further propose an unbiased evaluation metric, called WTG (short for Watch Time Gain). Empirical results reveal that WTG can alleviate duration bias and better measure recommendation performance. Moreover, we design a simple yet effective model named DVR (short for Debiased Video Recommendation) that can provide unbiased recommendation of micro-videos with varying duration, and learn unbiased user preferences via adversarial learning. Extensive experiments based on two real-world datasets demonstrate that DVR successfully eliminates duration bias and significantly improves recommendation performance with over 30% relative progress. Codes and datasets are released at https://github.com/tsinghua-fib-lab/WTG-DVR.

preprint2022arXiv

Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection

Anomaly detection from graph data has drawn much attention due to its practical significance in many critical applications including cybersecurity, finance, and social networks. Existing data mining and machine learning methods are either shallow methods that could not effectively capture the complex interdependency of graph data or graph autoencoder methods that could not fully exploit the contextual information as supervision signals for effective anomaly detection. To overcome these challenges, in this paper, we propose a novel method, Self-Supervised Learning for Graph Anomaly Detection (SL-GAD). Our method constructs different contextual subgraphs (views) based on a target node and employs two modules, generative attribute regression and multi-view contrastive learning for anomaly detection. While the generative attribute regression module allows us to capture the anomalies in the attribute space, the multi-view contrastive learning module can exploit richer structure information from multiple subgraphs, thus abling to capture the anomalies in the structure space, mixing of structure, and attribute information. We conduct extensive experiments on six benchmark datasets and the results demonstrate that our method outperforms state-of-the-art methods by a large margin.

preprint2022arXiv

Graph Self-Supervised Learning: A Survey

Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field.

preprint2022arXiv

HyperDet3D: Learning a Scene-conditioned 3D Object Detector

A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects. In this paper, we propose HyperDet3D to explore scene-conditioned prior knowledge for 3D object detection. Existing methods strive for better representation of local elements and their relations without scene-conditioned knowledge, which may cause ambiguity merely based on the understanding of individual points and object candidates. Instead, HyperDet3D simultaneously learns scene-agnostic embeddings and scene-specific knowledge through scene-conditioned hypernetworks. More specifically, our HyperDet3D not only explores the sharable abstracts from various 3D scenes, but also adapts the detector to the given scene at test time. We propose a discriminative Multi-head Scene-specific Attention (MSA) module to dynamically control the layer parameters of the detector conditioned on the fusion of scene-conditioned knowledge. Our HyperDet3D achieves state-of-the-art results on the 3D object detection benchmark of the ScanNet and SUN RGB-D datasets. Moreover, through cross-dataset evaluation, we show the acquired scene-conditioned prior knowledge still takes effect when facing 3D scenes with domain gap.

preprint2022arXiv

Towards Unsupervised Deep Graph Structure Learning

In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated when noisy connections occur in the original graph structures; besides, the dependence on explicit structures prevents GNNs from being applied to general unstructured scenarios. To address these issues, recently emerged deep graph structure learning (GSL) methods propose to jointly optimize the graph structure along with GNN under the supervision of a node classification task. Nonetheless, these methods focus on a supervised learning scenario, which leads to several problems, i.e., the reliance on labels, the bias of edge distribution, and the limitation on application tasks. In this paper, we propose a more practical GSL paradigm, unsupervised graph structure learning, where the learned graph topology is optimized by data itself without any external guidance (i.e., labels). To solve the unsupervised GSL problem, we propose a novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph. To provide persistent guidance, we design a novel bootstrapping mechanism that upgrades the anchor graph with learned structures during model learning. We also design a series of graph learners and post-processing schemes to model the structures to learn. Extensive experiments on eight benchmark datasets demonstrate the significant effectiveness of our proposed SUBLIME and high quality of the optimized graphs.

preprint2021arXiv

Attack-Resilient Weighted $\ell_1$ Observer with Prior Pruning

Security related questions for Cyber Physical Systems (CPS) have attracted much research attention in searching for novel methods for attack-resilient control and/or estimation. Specifically, false data injection attacks (FDIAs) have been shown to be capable of bypassing bad data detection (BDD), while arbitrarily compromising the integrity of state estimators and robust controller even with very sparse measurements corruption. Moreover, based on the inherent sparsity of pragmatic attack signals, $\ell_1$-minimization scheme has been used extensively to improve the design of attack-resilient estimators. For this, the theoretical maximum for the percentage of compromised nodes that can be accommodated has been shown to be $50\%$. In order to guarantee correct state recoveries for larger percentage of attacked nodes, researchers have begun to incorporate prior information into the underlying resilient observer design framework. For the most pragmatic cases, this prior information is often obtained through some data-driven machine learning process. Existing results have shown strong positive correlation between the tolerated attack percentages and the precision of the prior information. In this paper, we present a pruning method to improve the precision of the prior information, given corresponding stochastic uncertainty characteristics of the underlying machine learning model. Then a weighted $\ell_1$-minimization is proposed based on the pruned prior. The theoretical and simulation results show that the pruning method significantly improves the observer performance for much larger attack percentages, even when moderately accurate machine learning model used.

preprint2021arXiv

Crowd-sensing Enhanced Parking Patrol using Trajectories of Sharing Bikes

Illegal vehicle parking is a common urban problem faced by major cities in the world, as it incurs traffic jams, which lead to air pollution and traffic accidents. The government highly relies on active human efforts to detect illegal parking events. However, such an approach is extremely ineffective to cover a large city since the police have to patrol over the entire city roads. The massive and high-quality sharing bike trajectories from Mobike offer us a unique opportunity to design a ubiquitous illegal parking detection approach, as most of the illegal parking events happen at curbsides and have significant impact on the bike users. The detection result can guide the patrol schedule, i.e. send the patrol policemen to the region with higher illegal parking risks, and further improve the patrol efficiency. Inspired by this idea, three main components are employed in the proposed framework: 1)~{\em trajectory pre-processing}, which filters outlier GPS points, performs map-matching, and builds trajectory indexes; 2)~{\em illegal parking detection}, which models the normal trajectories, extracts features from the evaluation trajectories, and utilizes a distribution test-based method to discover the illegal parking events; and 3)~{\em patrol scheduling}, which leverages the detection result as reference context, and models the scheduling task as a multi-agent reinforcement learning problem to guide the patrol police. Finally, extensive experiments are presented to validate the effectiveness of illegal parking detection, as well as the improvement of patrol efficiency.

preprint2021arXiv

Disentangling User Interest and Conformity for Recommendation with Causal Embedding

Recommendation models are usually trained on observational interaction data. However, observational interaction data could result from users' conformity towards popular items, which entangles users' real interest. Existing methods tracks this problem as eliminating popularity bias, e.g., by re-weighting training samples or leveraging a small fraction of unbiased data. However, the variety of user conformity is ignored by these approaches, and different causes of an interaction are bundled together as unified representations, hence robustness and interpretability are not guaranteed when underlying causes are changing. In this paper, we present DICE, a general framework that learns representations where interest and conformity are structurally disentangled, and various backbone recommendation models could be smoothly integrated. We assign users and items with separate embeddings for interest and conformity, and make each embedding capture only one cause by training with cause-specific data which is obtained according to the colliding effect of causal inference. Our proposed methodology outperforms state-of-the-art baselines with remarkable improvements on two real-world datasets on top of various backbone models. We further demonstrate that the learned embeddings successfully capture the desired causes, and show that DICE guarantees the robustness and interpretability of recommendation.

preprint2021arXiv

Focus the electromagnetic field to $10^{-6} λ$ for ultra-high enhancement of field-matter interaction

Focusing electromagnetic field to enhance the interaction with matter has been promoting researches and applications of nano electronics and photonics. Usually, the evanescent-wave coupling is adopted in various nano structures and materials to confine the electromagnetic field into a subwavelength space. Here, based on the direct coupling with confined electron oscillations in a nanowire, we demonstrate an extreme localization of microwave field down to 10$^{-6}λ$. A hybrid nanowire-bowtie antenna is further designed to focus the free-space microwave to this deep-subwavelength space. Detected by the nitrogen vacancy center in diamond, the field intensity and microwave-spin interaction strength are enhanced by 2.0$\times$10$^{8}$ and 1.4$\times$10$^{4}$ times, respectively. Such an extreme concentration of microwave field will further promote integrated quantum information processing, sensing and microwave photonics in a nanoscale system.

preprint2021arXiv

Quantifying Microstructural Evolution via Time-Dependent Reduced-Dimension Metrics Based on Hierarchical $n$-Point Polytope Functions

We devise reduced-dimension metrics for effectively measuring the distance between two points (i.e., microstructures) in the microstructure space and quantifying the pathway associated with microstructural evolution, based on a recently introduced set of hierarchical $n$-point polytope functions $P_n$. The $P_n$ functions provide the probability of finding particular $n$-point configurations associated with regular $n$-polytopes in the material system, and a special sub-set of the standard $n$-point correlation functions $S_n$ that effectively decomposes the structural features in the systems into regular polyhedral basis with different symmetry. The $n$-th order metric $Ω_n$ is defined as the $\mathbb{L}_1$ norm associated with the $P_n$ functions of two distinct microstructures. By choosing a reference initial state (i.e., a microstructure associated with $t_0 = 0$), the $Ω_n(t)$ set quantifies the evolution of distinct polyhedral symmetries and can in principle capture emerging polyhedral symmetries that are not apparent in the initial state. To demonstrate their utility, we apply the $Ω_n$ metrics to a 2D binary system undergoing spinodal decomposition to extract the phase separation dynamics via the temporal scaling behavior of the corresponding $Ω_n(t)$, which reveals mechanisms governing the evolution. Moreover, we employ $Ω_n(t)$ to analyze pattern evolution during vapor-deposition of phase-separating alloy films with different surface contact angles, which exhibit rich evolution dynamics including both unstable and oscillating patterns. The $Ω_n$ metrics have potential applications in establishing quantitative processing-structure-property relationships, as well as real-time processing control and optimization of complex heterogeneous material systems.

preprint2021arXiv

Site-Controlled Telecom Single-Photon Emitters in Atomically-thin MoTe2

Quantum emitters (QEs) in two-dimensional transition metal dichalcogenides (2D TMDCs) have advanced to the forefront of quantum communication and transduction research due to their unique potentials in accessing valley pseudo-spin degree of freedom (DOF) and facile integration into quantum-photonic, electronic and sensing platforms via the layer-by-layer-assembly approach. To date, QEs capable of operating in O-C telecommunication bands have not been demonstrated in TMDCs. Here we report a deterministic creation of such telecom QEs emitting over the 1080 to 1550 nm wavelength range via coupling of 2D molybdenum ditelluride (MoTe2) to strain inducing nano-pillar arrays. Our Hanbury Brown and Twiss experiment conducted at 10 K reveals clear photon antibunching with 90% single photon purity. Ultra-long lifetimes, 4-6 orders of magnitude longer than that of the 2D exciton, are also observed. Polarization analysis further reveals that while some QEs display cross-linearly polarized doublets with ~1 meV splitting resulting from the strain induced anisotropic exchange interaction, valley degeneracy is preserved in other QEs. Valley Zeeman splitting as well as restoring of valley symmetry in cross-polarized doublets are observed under 8T magnetic field. In contrast to other telecom QEs, our QEs which offer the potential to access valley DOF through single photons, could lead to unprecedented advantages in optical fiber-based quantum networks.

preprint2020arXiv

Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

To leverage deep learning for image aesthetics assessment, one critical but unsolved issue is how to seamlessly incorporate the information of image aspect ratios to learn more robust models. In this paper, an adaptive fractional dilated convolution (AFDC), which is aspect-ratio-embedded, composition-preserving and parameter-free, is developed to tackle this issue natively in convolutional kernel level. Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integers dilated kernels is used to cope with the misalignment of fractional sampling. Moreover, we provide a concise formulation for mini-batch training and utilize a grouping strategy to reduce computational overhead. As a result, it can be easily implemented by common deep learning libraries and plugged into popular CNN architectures in a computation-efficient manner. Our experimental results demonstrate that our proposed method achieves state-of-the-art performance on image aesthetics assessment over the AVA dataset.

preprint2020arXiv

Diversity and Sparsity: A New Perspective on Index Tracking

We address the problem of partial index tracking, replicating a benchmark index using a small number of assets. Accurate tracking with a sparse portfolio is extensively studied as a classic finance problem. However in practice, a tracking portfolio must also be diverse in order to minimise risk -- a requirement which has only been dealt with by ad-hoc methods before. We introduce the first index tracking method that explicitly optimises both diversity and sparsity in a single joint framework. Diversity is realised by a regulariser based on pairwise similarity of assets, and we demonstrate that learning similarity from data can outperform some existing heuristics. Finally, we show that the way we model diversity leads to an easy solution for sparsity, allowing both constraints to be optimised easily and efficiently. we run out-of-sample backtesting for a long interval of 15 years (2003 -- 2018), and the results demonstrate the superiority of the proposed algorithm.

preprint2020arXiv

Efficient Suspected Infected Crowds Detection Based on Spatio-Temporal Trajectories

Virus transmission from person to person is an emergency event facing the global public. Early detection and isolation of potentially susceptible crowds can effectively control the epidemic of its disease. Existing metrics can not correctly address the infected rate on trajectories. To solve this problem, we propose a novel spatio-temporal infected rate (IR) measure based on human moving trajectories that can adequately describe the risk of being infected by a given query trajectory of a patient. Then, we manage source data through an efficient spatio-temporal index to make our system more scalable, and can quickly query susceptible crowds from massive trajectories. Besides, we design several pruning strategies that can effectively reduce calculations. Further, we design a spatial first time (SFT) index, which enables us to quickly query multiple trajectories without much I/O consumption and data redundancy. The performance of the solutions is demonstrated in experiments based on real and synthetic trajectory datasets that have shown the effectiveness and efficiency of our solutions.

preprint2020arXiv

Federated Extra-Trees with Privacy Preserving

It is commonly observed that the data are scattered everywhere and difficult to be centralized. The data privacy and security also become a sensitive topic. The laws and regulations such as the European Union's General Data Protection Regulation (GDPR) are designed to protect the public's data privacy. However, machine learning requires a large amount of data for better performance, and the current circumstances put deploying real-life AI applications in an extremely difficult situation. To tackle these challenges, in this paper we propose a novel privacy-preserving federated machine learning model, named Federated Extra-Trees, which applies local differential privacy in the federated trees model. A secure multi-institutional machine learning system was developed to provide superior performance by processing the modeling jointly on different clients without exchanging any raw data. We have validated the accuracy of our work by conducting extensive experiments on public datasets and the efficiency and robustness were also verified by simulating the real-world scenarios. Overall, we presented an extensible, scalable and practical solution to handle the data island problem.

preprint2020arXiv

Fine-Grained Urban Flow Inference

The ubiquitous deployment of monitoring devices in urban flow monitoring systems induces a significant cost for maintenance and operation. A technique is required to reduce the number of deployed devices, while preventing the degeneration of data accuracy and granularity. In this paper, we present an approach for inferring the real-time and fine-grained crowd flows throughout a city based on coarse-grained observations. This task exhibits two challenges: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a model entitled UrbanFM which consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs that uses a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influence of different external factors. This structure provides outstanding effectiveness and efficiency for small scale upsampling. However, the single-pass upsampling used by UrbanFM is insufficient at higher upscaling rates. Therefore, we further present UrbanPy, a cascading model for progressive inference of fine-grained urban flows by decomposing the original tasks into multiple subtasks. Compared to UrbanFM, such an enhanced structure demonstrates favorable performance for larger-scale inference tasks.

preprint2020arXiv

Gated Neural Networks for Option Pricing: Rationality by Design

We propose a neural network approach to price EU call options that significantly outperforms some existing pricing models and comes with guarantees that its predictions are economically reasonable. To achieve this, we introduce a class of gated neural networks that automatically learn to divide-and-conquer the problem space for robust and accurate pricing. We then derive instantiations of these networks that are 'rational by design' in terms of naturally encoding a valid call option surface that enforces no arbitrage principles. This integration of human insight within data-driven learning provides significantly better generalisation in pricing performance due to the encoded inductive bias in the learning, guarantees sanity in the model's predictions, and provides econometrically useful byproduct such as risk neutral density.

preprint2020arXiv

Locally Decodable Codes with Randomized Encoding

We initiate a study of locally decodable codes with randomized encoding. Standard locally decodable codes are error correcting codes with a deterministic encoding function and a randomized decoding function, such that any desired message bit can be recovered with good probability by querying only a small number of positions in the corrupted codeword. This allows one to recover any message bit very efficiently in sub-linear or even logarithmic time. Besides this straightforward application, locally decodable codes have also found many other applications such as private information retrieval, secure multiparty computation, and average-case complexity. However, despite extensive research, the tradeoff between the rate of the code and the number of queries is somewhat disappointing. For example, the best known constructions still need super-polynomially long codeword length even with a logarithmic number of queries, and need a polynomial number of queries to achieve a constant rate. In this paper, we show that by using a randomized encoding, in several models we can achieve significantly better rate-query tradeoff. In addition, our codes work for both the standard Hamming errors, and the more general and harder edit errors.

preprint2020arXiv

Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks

Being able to predict the crowd flows in each and every part of a city, especially in irregular regions, is strategically important for traffic control, risk assessment, and public safety. However, it is very challenging because of interactions and spatial correlations between different regions. In addition, it is affected by many factors: i) multiple temporal correlations among different time intervals: closeness, period, trend; ii) complex external influential factors: weather, events; iii) meta features: time of the day, day of the week, and so on. In this paper, we formulate crowd flow forecasting in irregular regions as a spatio-temporal graph (STG) prediction problem in which each node represents a region with time-varying flows. By extending graph convolution to handle the spatial information, we propose using spatial graph convolution to build a multi-view graph convolutional network (MVGCN) for the crowd flow forecasting problem, where different views can capture different factors as mentioned above. We evaluate MVGCN using four real-world datasets (taxicabs and bikes) and extensive experimental results show that our approach outperforms the adaptations of state-of-the-art methods. And we have developed a crowd flow forecasting system for irregular regions that can now be used internally.

preprint2020arXiv

Price-aware Recommendation with Graph Convolutional Networks

In recent years, much research effort on recommendation has been devoted to mining user behaviors, i.e., collaborative filtering, along with the general information which describes users or items, e.g., textual attributes, categorical demographics, product images, and so on. Price, an important factor in marketing --- which determines whether a user will make the final purchase decision on an item --- surprisingly, has received relatively little scrutiny. In this work, we aim at developing an effective method to predict user purchase intention with the focus on the price factor in recommender systems. The main difficulties are two-fold: 1) the preference and sensitivity of a user on item price are unknown, which are only implicitly reflected in the items that the user has purchased, and 2) how the item price affects a user's intention depends largely on the product category, that is, the perception and affordability of a user on item price could vary significantly across categories. Towards the first difficulty, we propose to model the transitive relationship between user-to-item and item-to-price, taking the inspiration from the recently developed Graph Convolution Networks (GCN). The key idea is to propagate the influence of price on users with items as the bridge, so as to make the learned user representations be price-aware. For the second difficulty, we further integrate item categories into the propagation progress and model the possible pairwise interactions for predicting user-item interactions. We conduct extensive experiments on two real-world datasets, demonstrating the effectiveness of our GCN-based method in learning the price-aware preference of users. Further analysis reveals that modeling the price awareness is particularly useful for predicting user preference on items of unexplored categories.

preprint2020arXiv

ReAD: A Regional Anomaly Detection Framework Based on Dynamic Partition

The detection of the abnormal area from urban data is a significant research problem. However, to the best of our knowledge, previous methods designed on spatio-temporal anomalies are road-based or grid-based, which usually causes the data sparsity problem and affects the detection results. In this paper, we proposed a dynamic region partition method to address the above issues. Besides, we proposed an unsupervised REgional Anomaly Detection framework (ReAD) to detect abnormal regions with arbitrary shapes by jointly considering spatial and temporal properties. Specifically, the proposed framework first generate regions via a dynamic region partition method. It keeps that observations in the same region have adjacent locations and similar non-spatial attribute readings, and could alleviate data sparsity and heterogeneity compared with the grid-based approach. Then, an anomaly metric will be calculated for each region by a regional divergence calculation method. The abnormal regions could be finally detected by a weighted approach or a wavy approach according to the different scenario. Experiments on both the simulated dataset and real-world applications demonstrate the effectiveness and practicability of the proposed framework.

preprint2020arXiv

Revisiting Convolutional Neural Networks for Citywide Crowd Flow Analytics

Citywide crowd flow analytics is of great importance to smart city efforts. It aims to model the crowd flow (e.g., inflow and outflow) of each region in a city based on historical observations. Nowadays, Convolutional Neural Networks (CNNs) have been widely adopted in raster-based crowd flow analytics by virtue of their capability in capturing spatial dependencies. After revisiting CNN-based methods for different analytics tasks, we expose two common critical drawbacks in the existing uses: 1) inefficiency in learning global spatial dependencies, and 2) overlooking latent region functions. To tackle these challenges, in this paper we present a novel framework entitled DeepLGR that can be easily generalized to address various citywide crowd flow analytics problems. This framework consists of three parts: 1) a local feature extraction module to learn representations for each region; 2) a global context module to extract global contextual priors and upsample them to generate the global features; and 3) a region-specific predictor based on tensor decomposition to provide customized predictions for each region, which is very parameter-efficient compared to previous methods. Extensive experiments on two typical crowd flow analytics tasks demonstrate the effectiveness, stability, and generality of our framework.

preprint2020arXiv

Robust optical-levitation-based metrology of nanoparticle's position and mass

Light has shown up an incredibe capability in precision measurement based on opto-mechanic interaction in high vacuum by isolating environment noises. However, there are still obstructions, such as displacement and mass estimation error, highly hampering the improvement of absolute accuracy at the nanoscale. Here, we present a nonlinearity based metrology to precisely measure the position and mass of a nanoparticle with optical levitation under $10^{-5}$ mbar, 6-order of magnitude lower than the electrostatic-force and stochastic-force-based counterparts. By precisely controlling the amplitude of the levitated nanoparticle at the nonlinear regime, we realized a feasible sub-picometer-level position measurement with an uncertainty of $1.0\%$ without the prior information of mass, which can be further applied to weigh the femtogram-level mass with an uncertainty of $2.2\%$. It will also pave the way to construct a well-calibrated opto-mechanic platform in high vacuum for high sensitivity and accuracy measurement in force and acceleration at the nanoscale and the study in quantum superposition at the mesoscopic scale.

preprint2020arXiv

Space Efficient Deterministic Approximation of String Measures

We study approximation algorithms for the following three string measures that are widely used in practice: edit distance (ED), longest common subsequence (LCS), and longest increasing sequence (LIS). All three problems can be solved exactly by standard algorithms that run in polynomial time with roughly $Θ(n)$ space, where $n$ is the input length, and our goal is to design deterministic approximation algorithms that run in polynomial time with significantly smaller space. Towards this, we design several algorithms that achieve $1+ε$ or $1-ε$ approximation for all three problems, where $ε>0$ can be any constant and even slightly sub constant. Our algorithms are flexible and can be adjusted to achieve the following two regimes of parameters: 1) space $n^δ$ for any constant $δ>0$ with running time essentially the same as or slightly more than the standard algorithms; and 2) space $\mathsf{polylog}(n)$ with (a larger) polynomial running time, which puts the approximation versions of the three problems in Steve's class (\textbf{SC}). Our algorithms significantly improve previous results in terms of space complexity, where all known results need to use space at least $Ω(\sqrt{n})$. Some of our algorithms can also be adapted to work in the asymmetric streaming model [SS13], and output the corresponding sequence. Furthermore, our results can be used to improve a recent result by Farhadi et. al. [FHRS20] about approximating ED in the asymmetric streaming model, reducing the running time from being exponential in [FHRS20] to a polynomial. Our algorithms are based on the idea of using recursion as in Savitch's theorem [Sav70], and a careful adaption of previous techniques to make the recursion work. Along the way we also give a new logspace reduction from longest common subsequence to longest increasing sequence, which may be of independent interest.

preprint2020arXiv

Stone-Wales Defects Preserve Hyperuniformity in Amorphous Two-Dimensional Materials

Crystalline two-dimensional (2D) materials such as graphene possess unique physical properties absent in their bulk form, enabling many novel device applications. Yet, little is known about their amorphous counterparts, which can be obtained by introducing the Stone-Wales (SW) topological defects via proton radiation. Here we provide strong numerical evidence that SW defects preserve hyperuniformity in hexagonal 2D materials, a recently discovered new state of matter characterized by vanishing normalized infinite-wavelength density fluctuations, which implies that all amorphous states of these materials are hyperuniform. Specifically, the static structure factor S(k) of these materials possesses the scaling S(k) ~ k^α for small wave number k, where 1<=α(p)<=2 is monotonically decreasing as the SW defect concentration p increases, indicating a transition from type-I to type-II hyperuniformity at p ~= 0.12 induced by the saturation of the SW defects. This hyperuniformity transition marks a structural transition from perturbed lattice structures to truly amorphous structures, and underlies the onset of strong correlation among the SW defects as well as a transition between distinct electronic transport mechanisms associated with different hyperuniformity classes.

preprint2020arXiv

Urban Anomaly Analytics: Description, Detection, and Prediction

Urban anomalies may result in loss of life or property if not handled properly. Automatically alerting anomalies in their early stage or even predicting anomalies before happening are of great value for populations. Recently, data-driven urban anomaly analysis frameworks have been forming, which utilize urban big data and machine learning algorithms to detect and predict urban anomalies automatically. In this survey, we make a comprehensive review of the state-of-the-art research on urban anomaly analytics. We first give an overview of four main types of urban anomalies, traffic anomaly, unexpected crowds, environment anomaly, and individual anomaly. Next, we summarize various types of urban datasets obtained from diverse devices, i.e., trajectory, trip records, CDRs, urban sensors, event records, environment data, social media and surveillance cameras. Subsequently, a comprehensive survey of issues on detecting and predicting techniques for urban anomalies is presented. Finally, research challenges and open problems as discussed.

preprint2019arXiv

Federated Forest

Most real-world data are scattered across different companies or government organizations, and cannot be easily integrated under data privacy and related regulations such as the European Union's General Data Protection Regulation (GDPR) and China' Cyber Security Law. Such data islands situation and data privacy & security are two major challenges for applications of artificial intelligence. In this paper, we tackle these challenges and propose a privacy-preserving machine learning model, called Federated Forest, which is a lossless learning model of the traditional random forest method, i.e., achieving the same level of accuracy as the non-privacy-preserving approach. Based on it, we developed a secure cross-regional machine learning system that allows a learning process to be jointly trained over different regions' clients with the same user samples but different attribute sets, processing the data stored in each of them without exchanging their raw data. A novel prediction algorithm was also proposed which could largely reduce the communication overhead. Experiments on both real-world and UCI data sets demonstrate the performance of the Federated Forest is as accurate as the non-federated version. The efficiency and robustness of our proposed system had been verified. Overall, our model is practical, scalable and extensible for real-life tasks.

Yu Zheng

Quick read

Decide how to stay connected

How to connect with this researcher

Open a focused conversation when the fit is right

See the researcher in context

Building this graph slice

37 published item(s)

SPECTRE: Hybrid Ordinary-Parallel Speculative Serving for Resource-Efficient LLM Inference

A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions

A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling

Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

Configuration-Aware Safe Control for Mobile Robotic Arm with Control Barrier Functions

DA$^2$ Dataset: Toward Dexterity-Aware Dual-Arm Grasping

Deep AutoAugment

DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning

Disentangling Long and Short-Term Interests for Recommendation

Disordered Hyperuniform Quasi-1D Materials

DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias

Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection

Graph Self-Supervised Learning: A Survey

HyperDet3D: Learning a Scene-conditioned 3D Object Detector

Towards Unsupervised Deep Graph Structure Learning

Attack-Resilient Weighted $\ell_1$ Observer with Prior Pruning

Crowd-sensing Enhanced Parking Patrol using Trajectories of Sharing Bikes

Disentangling User Interest and Conformity for Recommendation with Causal Embedding

Focus the electromagnetic field to $10^{-6} λ$ for ultra-high enhancement of field-matter interaction

Quantifying Microstructural Evolution via Time-Dependent Reduced-Dimension Metrics Based on Hierarchical $n$-Point Polytope Functions

Site-Controlled Telecom Single-Photon Emitters in Atomically-thin MoTe2

Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

Diversity and Sparsity: A New Perspective on Index Tracking

Efficient Suspected Infected Crowds Detection Based on Spatio-Temporal Trajectories

Federated Extra-Trees with Privacy Preserving

Fine-Grained Urban Flow Inference

Gated Neural Networks for Option Pricing: Rationality by Design

Locally Decodable Codes with Randomized Encoding

Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks

Price-aware Recommendation with Graph Convolutional Networks

ReAD: A Regional Anomaly Detection Framework Based on Dynamic Partition

Revisiting Convolutional Neural Networks for Citywide Crowd Flow Analytics

Robust optical-levitation-based metrology of nanoparticle&#39;s position and mass

Space Efficient Deterministic Approximation of String Measures

Stone-Wales Defects Preserve Hyperuniformity in Amorphous Two-Dimensional Materials

Urban Anomaly Analytics: Description, Detection, and Prediction

Federated Forest

Robust optical-levitation-based metrology of nanoparticle's position and mass