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

Won-Yong Shin

Won-Yong Shin contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceMachine LearningInformation RetrievalInformation Theorymath.ITNetworking and Internet ArchitectureNeural and Evolutionary ComputingSocial and Information NetworksDistributed, Parallel, and Cluster Computingphysics.comp-phComputation and LanguageComputational Engineering, Finance, and Scienceeess.SYMultiagent SystemsMultimediaphysics.app-phphysics.atom-phphysics.chem-phSystems and Control

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
0followers
19topics
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

12 published item(s)

preprint2026arXiv

Hyperbolic Heterogeneous Graph Transformer

In heterogeneous graphs, we can observe complex structures such as tree-like or hierarchical structures. Recently, the hyperbolic space has been widely adopted in many studies to effectively learn these complex structures. Although these methods have demonstrated the advantages of the hyperbolic space in learning heterogeneous graphs, most existing methods still have several challenges. They rely heavily on tangent-space operations, which often lead to mapping distortions during frequent transitions. Moreover, their message-passing architectures mainly focus on local neighborhood information, making it difficult to capture global hierarchical structures and long-range dependencies between different types of nodes. To address these limitations, we propose Hyperbolic Heterogeneous Graph Transformer (HypHGT), which effectively and efficiently learns heterogeneous graph representations entirely within the hyperbolic space. Unlike previous message-passing based hyperbolic heterogeneous GNNs, HypHGT naturally captures both local and global dependencies through transformer-based architecture. Furthermore, the proposed relation-specific hyperbolic attention mechanism in HypHGT, which operates with linear time complexity, enables efficient computation while preserving the heterogeneous information across different relation types. This design allows HypHGT to effectively capture the complex structural properties and semantic information inherent in heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness and efficiency of HypHGT, and the results demonstrate that it consistently outperforms state-of-the-art methods in node classification task, with significantly reduced training time and memory usage.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Semi-Supervised Neural Super-Resolution for Mesh-Based Simulations

Mesh-based simulations provide high-fidelity solutions to partial differential equations (PDEs), but achieving such accuracy typically requires fine meshes, leading to substantial computational overhead. Super-resolution techniques aim to mitigate this cost by reconstructing high-resolution (HR), high-fidelity solutions from low-cost, low-resolution (LR) counterparts. However, training neural networks for super-resolution often demands large amounts of expensive HR supervision data. To address this challenge, we propose SuperMeshNet, an HR data-efficient super-resolution framework for mesh-based simulations aided by message passing neural networks (MPNNs). At its core, SuperMeshNet introduces complementary learning, a semi-supervised approach that effectively leverages both 1) a small amount of paired LR-HR data and 2) abundant unpaired LR data via two jointly trained, complementary MPNN-based models. Additionally, our model is enriched by inductive biases, which are empirically shown to further improve super-resolution performance. Extensive experiments demonstrate that SuperMeshNet requires 90% less HR data to achieve even lower root mean square error (RMSE) than that of the fully supervised benchmark without the inductive biases. The source code and datasets are available at https://github.com/jykim-git/SuperMeshNet.git.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Teaching Molecular Dynamics to a Non-Autoregressive Ionic Transport Predictor

Unlike most static material properties widely studied in the machine learning literature, ionic transport properties are inherently dynamic, making their fast and accurate prediction from static atomic structures challenging. The current standard approach, molecular dynamics (MD) simulations, suffers from prohibitively high computational cost. Recent autoregressive learning-based MD acceleration methods requiring sequential inference remain slow and prone to error accumulation; in contrast, existing non-autoregressive material property prediction models are less accurate because they fail to exploit dynamics. Moreover, existing methods typically benefit from datasets either with or without atomic trajectories, but not both. To overcome these limitations, we propose a non-autoregressive learning framework based on auxiliary modality learning, which treats atomic trajectories as an auxiliary modality during training but does not require them at inference. This enables the predictor to learn dynamics without sequential inference while benefiting from both types of datasets. As a result, our framework achieves over 200 times speedup compared to autoregressive models on the dataset with atomic trajectories while substantially reducing prediction error relative to non-autoregressive benchmarks across both types of datasets. Our code is available at https://github.com/jykim-git/MD.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TRACE: Tourism Recommendation with Accountable Citation Evidence

Tourism is a high-stakes setting for conversational recommender systems (CRS): a plausible-sounding suggestion can waste real money and trip time once a traveler acts on it. Existing CRS benchmarks primarily evaluate systems with a single Recall@k score over entity mentions, and tourism-specific resources add spatial or knowledge-graph context, yet none of them couple multi-turn recommendation with verbatim review-span evidence and rejection recovery. This leaves an evaluation gap for tourism recommendation that is simultaneously trustworthy, verifiable, and adaptive: recommend the right point of interest (POI) for multi-aspect preferences (such as cuisine, price, atmosphere, walking distance), justify each suggestion with verifiable evidence from prior visitors so the traveler can act without trial and error, and recover when the first recommendation is rejected mid-dialogue. We introduce TRACE, where each item is a multi-turn tourism recommendation dialogue with review-span citations and explicit rejection turns: 10,000 dialogues over 2,400 Yelp POIs and 34,208 reviews across eight U.S. cities, paired with 14 retrieval, planning, and LLM baselines, along with 25 metrics organized under Accuracy, Grounding, and Recovery. Across these baselines, TRACE reveals the Three-Competency Gap: LLM Zero-Shot leads in closed-set Recall@1 and rejection recovery but cites less densely than retrievers; non-LLM retrievers achieve surface-verbatim grounding but with low accuracy; Multi-Review Synthesis fails at recovery. The Grounding Score agrees with human citation precision (Spearman rho=+0.80, p<10^-20), and paired t-tests reproduce the per-baseline ranking (p<0.01 on the dominant contrasts). TRACE reframes accountable tourism recommendation as a joint target (right POI, verifiable evidence, adaptive repair) rather than a single-axis leaderboard.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Grad-Align+: Empowering Gradual Network Alignment Using Attribute Augmentation

Network alignment (NA) is the task of discovering node correspondences across different networks. Although NA methods have achieved remarkable success in a myriad of scenarios, their satisfactory performance is not without prior anchor link information and/or node attributes, which may not always be available. In this paper, we propose Grad-Align+, a novel NA method using node attribute augmentation that is quite robust to the absence of such additional information. Grad-Align+ is built upon a recent state-of-the-art NA method, the so-called Grad-Align, that gradually discovers only a part of node pairs until all node pairs are found. Specifically, Grad-Align+ is composed of the following key components: 1) augmenting node attributes based on nodes&#39; centrality measures, 2) calculating an embedding similarity matrix extracted from a graph neural network into which the augmented node attributes are fed, and 3) gradually discovering node pairs by calculating similarities between cross-network nodes with respect to the aligned cross-network neighbor-pair. Experimental results demonstrate that Grad-Align+ exhibits (a) superiority over benchmark NA methods, (b) empirical validation of our theoretical findings, and (c) the effectiveness of our attribute augmentation module.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

META-CODE: Community Detection via Exploratory Learning in Topologically Unknown Networks

The discovery of community structures in social networks has gained considerable attention as a fundamental problem for various network analysis tasks. However, due to privacy concerns or access restrictions, the network structure is often unknown, thereby rendering established community detection approaches ineffective without costly data acquisition. To tackle this challenge, we present META-CODE, a novel end-to-end solution for detecting overlapping communities in networks with unknown topology via exploratory learning aided by easy-to-collect node metadata. Specifically, META-CODE consists of three steps: 1) initial network inference, 2) node-level community-affiliation embedding based on graph neural networks (GNNs) trained by our new reconstruction loss, and 3) network exploration via community-affiliation-based node queries, where Steps 2 and 3 are performed iteratively. Experimental results demonstrate that META-CODE exhibits (a) superiority over benchmark methods for overlapping community detection, (b) the effectiveness of our training model, and (c) fast network exploration.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

SiReN: Sign-Aware Recommendation Using Graph Neural Networks

In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy. However, such attempts have focused mostly on utilizing only the information of positive user-item interactions with high ratings. Thus, there is a challenge on how to make use of low rating scores for representing users&#39; preferences since low ratings can be still informative in designing NE-based recommender systems. In this study, we present SiReN, a new sign-aware recommender system based on GNN models. Specifically, SiReN has three key components: 1) constructing a signed bipartite graph for more precisely representing users&#39; preferences, which is split into two edge-disjoint graphs with positive and negative edges each, 2) generating two embeddings for the partitioned graphs with positive and negative edges via a GNN model and a multi-layer perceptron (MLP), respectively, and then using an attention model to obtain the final embeddings, and 3) establishing a sign-aware Bayesian personalized ranking (BPR) loss function in the process of optimization. Through comprehensive experiments, we empirically demonstrate that SiReN consistently outperforms state-of-the-art NE-aided recommendation methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Transport Capacity Optimization for Resource Allocation in Tera-IoT Networks

We present a new adaptive resource optimization strategy that jointly allocates the subwindow and transmit power in multi-device terahertz (THz) band Internet of Things (Tera-IoT) networks. Unlike the prior studies focusing mostly on maximizing the sum distance, we incorporate both rate and transmission distance into the objective function of our problem formulation with key features of THz bands, including the spreading and molecular absorption losses. More specifically, as a performance metric of Tera-IoT networks, we adopt the transport capacity (TC), which is defined as the sum of the rate-distance products over all users. This metric has been widely adopted in large-scale ad hoc networks, and would also be appropriate for evaluating the performance of various Tera-IoT applications. We then formulate an optimization problem that aims at maximizing the TC. Moreover, motivated by the importance of the transmission distance that is very limited due to the high path loss in THz bands, our optimization problem is extended to the case of allocating the subwindow, transmit power, and transmission distance. We show how to solve our problems via an effective two-stage resource allocation strategy. We demonstrate the superiority of our adaptive solution over benchmark methods via intensive numerical evaluations for various environmental setups of large-scale Tera-IoT networks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Two-Stage Deep Anomaly Detection with Heterogeneous Time Series Data

We introduce a data-driven anomaly detection framework using a manufacturing dataset collected from a factory assembly line. Given heterogeneous time series data consisting of operation cycle signals and sensor signals, we aim at discovering abnormal events. Motivated by our empirical findings that conventional single-stage benchmark approaches may not exhibit satisfactory performance under our challenging circumstances, we propose a two-stage deep anomaly detection (TDAD) framework in which two different unsupervised learning models are adopted depending on types of signals. In Stage I, we select anomaly candidates by using a model trained by operation cycle signals; in Stage II, we finally detect abnormal events out of the candidates by using another model, which is suitable for taking advantage of temporal continuity, trained by sensor signals. A distinguishable feature of our framework is that operation cycle signals are exploited first to find likely anomalous points, whereas sensor signals are leveraged to filter out unlikely anomalous points afterward. Our experiments comprehensively demonstrate the superiority over single-stage benchmark approaches, the model-agnostic property, and the robustness to difficult situations.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Personalized Preference Learning Framework for Caching in Mobile Networks

This paper comprehensively studies a content-centric mobile network based on a preference learning framework, where each mobile user is equipped with a finite-size cache. We consider a practical scenario where each user requests a content file according to its own preferences, which is motivated by the existence of heterogeneity in file preferences among different users. Under our model, we consider a single-hop-based device-to-device (D2D) content delivery protocol and characterize the average hit ratio for the following two file preference cases: the personalized file preferences and the common file preferences. By assuming that the model parameters such as user activity levels, user file preferences, and file popularity are unknown and thus need to be inferred, we present a collaborative filtering (CF)-based approach to learn these parameters. Then, we reformulate the hit ratio maximization problems into a submodular function maximization and propose two computationally efficient algorithms including a greedy approach to efficiently solve the cache allocation problems. We analyze the computational complexity of each algorithm. Moreover, we analyze the corresponding level of the approximation that our greedy algorithm can achieve compared to the optimal solution. Using a real-world dataset, we demonstrate that the proposed framework employing the personalized file preferences brings substantial gains over its counterpart for various system parameters.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Interference-Aware Opportunistic Random Access in Dense IoT Networks

It is a challenging task to design a random access protocol that achieves the optimal throughput in multi-cell random access with decentralized transmission due to the difficulty of coordination. In this paper, we present a decentralized interference-aware opportunistic random access (IA-ORA) protocol that enables us to obtain the optimal throughput scaling in an ultra-dense multi-cell random access network with one access point (AP) and a number of users. In sharp contrast to opportunistic scheduling for cellular multiple access where users are selected by base stations, under the IA-ORA protocol, each user opportunistically transmits with a predefined physical layer (PHY) data rate in a decentralized manner if not only the desired signal power to the serving AP is sufficiently large but also the generating interference leakage power to the other APs is sufficiently small (i.e., two threshold conditions are fulfilled). As a main result, it is shown that the optimal aggregate throughput scaling (i.e., the MAC throughput of $\frac{1}{e}$ in a cell and the power gain) is achieved in a high signal-to-noise ratio regime if the number of per-cell users exceeds some level. Additionally, it is numerically demonstrated via computer simulations that under practical settings, the proposed IA-ORA protocol outperforms conventional opportunistic random access protocols in terms of aggregate throughput.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

On Capacity Scaling of Underwater Networks: An Information-Theoretic Perspective

Capacity scaling laws are analyzed in an underwater acoustic network with $n$ regularly located nodes on a square. A narrow-band model is assumed where the carrier frequency is allowed to scale as a function of $n$. In the network, we characterize an attenuation parameter that depends on the frequency scaling as well as the transmission distance. A cut-set upper bound on the throughput scaling is then derived in extended networks. Our result indicates that the upper bound is inversely proportional to the attenuation parameter, thus resulting in a highly power-limited network. Interestingly, it is seen that unlike the case of wireless radio networks, our upper bound is intrinsically related to the attenuation parameter but not the spreading factor. Furthermore, we describe an achievable scheme based on the simple nearest neighbor multi-hop (MH) transmission. It is shown under extended networks that the MH scheme is order-optimal as the attenuation parameter scales exponentially with $\sqrt{n}$ (or faster). Finally, these scaling results are extended to a random network realization.

0 citations0 reviewsNo code linkedOpen access