70 citations · 246 across the 30 of their papers we have counts for
31 papers
MambaTG: Candidate-Aware State Space Modeling for Future Link Prediction on Temporal Graphs
Nguyen Hong Quan, Sitao Luan, Yilun Zheng +1
Future link prediction on temporal graphs involves both repeated interactions between previously connected node pairs and first-time interactions between pairs with no prior intera…
ControBench: An Interaction-Aware Benchmark for Controversial Discourse Analysis on Social Networks
Ta Thanh Thuy, Jiaqi Zhu, Xuan Liu +6
Understanding how people argue across ideological divides online is important for studying political polarization, misinformation, and content moderation. Existing datasets capture…
GD4: Graph-based Discrete Denoising Diffusion for MIMO Detection
Qincheng Lu, Sitao Luan, Xiao-Wen Chang
In wireless communications, recovering the optimal solution to the multiple-input multiple-output (MIMO) detection problem is NP-hard. Obtaining high-quality suboptimal solutions w…
EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
Sicheng Lyu, Yu Gu, Xinyu Wang +5
Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modif…
Exploring Heterophily in Graph-level Tasks
Qinhan Hou, Yilun Zheng, Xichun Zhang +2
While heterophily has been widely studied in node-level tasks, its impact on graph-level tasks remains unclear. We present the first analysis of heterophily in graph-level learning…
RL Fine-Tuning Heals OOD Forgetting in SFT
Hangzhan Jin, Sitao Luan, Tianwei Ni +5
Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) is a standard post-training recipe for improving Large Language Models (LLM) reasoning, but why it works remain…
FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis
Yilun Zheng, Sha Li, Fangkun Wu +9
Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own, often for humor, provocation, or controversy. Detecting and an…
Rethinking Structure Learning For Graph Neural Networks
Yilun Zheng, Zhuofan Zhang, Ziming Wang +4
To improve the performance of Graph Neural Networks (GNNs), Graph Structure Learning (GSL) has been extensively applied to reconstruct or refine original graph structures, effectiv…
Is Graph Convolution Always Beneficial For Every Feature?
Yilun Zheng, Xiang Li, Sitao Luan +2
Graph Neural Networks (GNNs) have demonstrated strong capabilities in processing structured data. While traditional GNNs typically treat each feature dimension equally during graph…
EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamics
Chenqing Hua, Yong Liu, Dinghuai Zhang +6
Enzyme design is a critical area in biotechnology, with applications ranging from drug development to synthetic biology. Traditional methods for enzyme function prediction or prote…
ReactZyme: A Benchmark for Enzyme-Reaction Prediction
Chenqing Hua, Bozitao Zhong, Sitao Luan +4
Enzymes, with their specific catalyzed reactions, are necessary for all aspects of life, enabling diverse biological processes and adaptations. Predicting enzyme functions is essen…
Flexible Diffusion Scopes with Parameterized Laplacian for Heterophilic Graph Learning
Qincheng Lu, Jiaqi Zhu, Sitao Luan +1
The ability of Graph Neural Networks (GNNs) to capture long-range and global topology information is limited by the scope of conventional graph Laplacian, leading to unsatisfactory…
Revealing the Pitfalls and Re-Evaluating the Advancement of Heterophilic Graph Learning
Sitao Luan, Qincheng Lu, Chenqing Hua +3
Over the past decade, Graph Neural Networks (GNNs) have achieved great success on machine learning tasks with relational data. However, recent studies have found that heterophily c…
The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges
Sitao Luan, Chenqing Hua, Qincheng Lu +11
Homophily principle, \ie{} nodes with the same labels or similar attributes are more likely to be connected, has been commonly believed to be the main reason for the superiority of…
What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networks
Yilun Zheng, Sitao Luan, Lihui Chen
Graph homophily refers to the phenomenon that connected nodes tend to share similar characteristics. Understanding this concept and its related metrics is crucial for designing eff…
GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection
Qincheng Lu, Sitao Luan, Xiao-Wen Chang
Massive MIMO (multiple-input multiple-output) detection is an important topic in wireless communication and various machine learning based methods have been developed recently for…
Representation Learning on Heterophilic Graph with Directional Neighborhood Attention
Qincheng Lu, Jiaqi Zhu, Sitao Luan +1
Graph Attention Network (GAT) is one of the most popular Graph Neural Network (GNN) architecture, which employs the attention mechanism to learn edge weights and has demonstrated p…
On Addressing the Limitations of Graph Neural Networks
Sitao Luan
This report gives a summary of two problems about graph convolutional networks (GCNs): over-smoothing and heterophily challenges, and outlines future directions to explore.
MUDiff: Unified Diffusion for Complete Molecule Generation
Chenqing Hua, Sitao Luan, Minkai Xu +4
Molecule generation is a very important practical problem, with uses in drug discovery and material design, and AI methods promise to provide useful solutions. However, existing me…
When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability
Sitao Luan, Chenqing Hua, Minkai Xu +6
Homophily principle, i.e., nodes with the same labels are more likely to be connected, has been believed to be the main reason for the performance superiority of Graph Neural Netwo…
Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Neural Networks
Sitao Luan, Mingde Zhao, Chenqing Hua +2
The core operation of current Graph Neural Networks (GNNs) is the aggregation enabled by the graph Laplacian or message passing, which filters the neighborhood information of nodes…
Revisiting Heterophily For Graph Neural Networks
Sitao Luan, Chenqing Hua, Qincheng Lu +5
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption). While GNNs have been common…
When Do We Need Graph Neural Networks for Node Classification?
Sitao Luan, Chenqing Hua, Qincheng Lu +3
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by additionally making use of graph structure based on the relational inductive bias (edge bias), rather than treati…
Graph Neural Networks Intersect Probabilistic Graphical Models: A Survey
Chenqing Hua, Sitao Luan, Qian Zhang +1
Graphs are a powerful data structure to represent relational data and are widely used to describe complex real-world data structures. Probabilistic Graphical Models (PGMs) have bee…