2 citations · 3 across the 15 of their papers we have counts for
17 papers
WCCS: Efficient Wedge Conductance Community Search over Large Temporal Bipartite Graphs (Full Paper)
Longlong Lin, Wei Chen, Pingpeng Yuan +3
Bipartite graphs are ubiquitous for modeling complex interactions between two distinct entity types across numerous practical applications such as e-commerce, academic networks, an…
OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation
Yuze Dai, Zhihan Zhang, Yan Zhao +6
Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text. However, real-world TAGs are often imperfect, with quality iss…
Revisiting Maximum -Biplex Search Through -Bounded-Degree Deletion
Donghang Cui, Ronghua Li, Qiangqiang Dai +1
Biplex, as a relaxation of the biclique model, has emerged as an important cohesive subgraph model for bipartite graph analysis. The maximum -biplex search problem aims to ident…
MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA
Yilong Zuo, Xunkai Li, Jing Yuan +3
Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts. Exi…
Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing
Yue Yu, Yang Jiao, Jiayu Wang +2
Instruction-based image editing has made notable progress with recent advances in generative models. However, the quality of the edited result is still influenced by the randomly s…
RNSG: A Range-Aware Graph Index for Efficient Range-Filtered Approximate Nearest Neighbor Search
Zhiqiu Zou, Ziqi Yin, Rong-Hua Li +3
Range-filtered approximate nearest neighbor (RFANN) search is a fundamental operation in modern data systems. Given a set of objects, each with a vector and a numerical attribute,…
DOGMA: Weaving Structural Information into Data-centric Single-cell Transcriptomics Analysis
Ru Zhang, Xunkai Li, Yaxin Deng +7
Recently, data-centric AI methodology has been a dominant paradigm in single-cell transcriptomics analysis, which treats data representation rather than model complexity as the fun…
OpenDDI: A Comprehensive Benchmark for DDI Prediction
Xinmo Jin, Bowen Fan, Xunkai Li +9
Drug-Drug Interactions (DDIs) significantly influence therapeutic efficacy and patient safety. As experimental discovery is resource-intensive and time-consuming, efficient computa…
OptiMAG: Structure-Semantic Alignment via Unbalanced Optimal Transport
Yilong Zuo, Xunkai Li, Zhihan Zhang +3
Multimodal Attributed Graphs (MAGs) have been widely adopted for modeling complex systems by integrating multi-modal information, such as text and images, on nodes. However, we ide…
MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning
Xunkai Li, Yuming Ai, Yinlin Zhu +7
Multimodal-attributed graphs (MMAGs) provide a unified framework for modeling complex relational data by integrating heterogeneous modalities with graph structures. While centraliz…
BoostFGL: Boosting Fairness in Federated Graph Learning
Zekai Chen, Kairui Yang, Xunkai Li +6
Federated graph learning (FGL) enables collaborative training of graph neural networks (GNNs) across decentralized subgraphs without exposing raw data. While existing FGL methods o…
A Computationally Efficient Framework for Overlapping Community Detection in Large Bipartite Graphs
Yue Zeng, Rong-Hua Li, Qiangqiang Dai +1
Community detection, which uncovers closely connected vertex groups in networks, is vital for applications in social networks, recommendation systems, and beyond. Real-world networ…
On the Efficient Discovery of Maximum -Defective Biclique
Donghang Cui, Ronghua Li, Qiangqiang Dai +2
The problem of identifying the maximum edge biclique in bipartite graphs has attracted considerable attention in bipartite graph analysis, with numerous real-world applications suc…
Efficient Antagonistic k-plex Enumeration in Signed Graphs
Lantian Xu, Rong-Hua Li, Dong Wen +3
A signed graph is a graph where each edge receives a sign, positive or negative. The signed graph model has been used in many real applications, such as protein complex discovery a…
Scalable Algorithms for Laplacian Pseudo-inverse Computation
Meihao Liao, Rong-Hua Li, Qiangqiang Dai +2
The pseudo-inverse of a graph Laplacian matrix, denoted as , finds extensive application in various graph analysis tasks. Notable examples include the calculation of ele…
Scaling Up Maximal k-plex Enumeration
Qiangqiang Dai, Rong-Hua Li, Hongchao Qin +2
Finding all maximal -plexes on networks is a fundamental research problem in graph analysis due to many important applications, such as community detection, biological graph ana…
Scaling Up Distance-generalized Core Decomposition
Qiangqiang Dai, Rong-Hua Li, Lu Qin +4
Core decomposition is a fundamental operator in network analysis. In this paper, we study the problem of computing distance-generalized core decomposition on a network. A distance-…