15 papers
Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs
Huizhe Zhang, Yuchang Zhu, Huazhen Zhong +2
Dynamic graph learning aims to capture evolving structural and semantic patterns in real-world systems, such as fraud detection and recommender systems. Due to the scarcity of labe…
Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics
Yuchang Zhu, Zezhong Xie, Huizhe Zhang +4
Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such…
SGNNBench: A Holistic Evaluation of Spiking Graph Neural Network on Large-scale Graph
Huizhe Zhang, Jintang Li, Yuchang Zhu +2
Graph Neural Networks (GNNs) are exemplary deep models designed for graph data. Message passing mechanism enables GNNs to effectively capture graph topology and push the performanc…
What Matters in LLM-generated Data: Diversity and Its Effect on Model Fine-Tuning
Yuchang Zhu, Huazhen Zhong, Qunshu Lin +6
With the remarkable generative capabilities of large language models (LLMs), using LLM-generated data to train downstream models has emerged as a promising approach to mitigate dat…
SaGIF: Improving Individual Fairness in Graph Neural Networks via Similarity Encoding
Yuchang Zhu, Jintang Li, Huizhe Zhang +2
Individual fairness (IF) in graph neural networks (GNNs), which emphasizes the need for similar individuals should receive similar outcomes from GNNs, has been a critical issue. De…
GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization
Huizhe Zhang, Jintang Li, Yuchang Zhu +2
Graph Transformers (GTs), which integrate message passing and self-attention mechanisms simultaneously, have achieved promising empirical results in graph prediction tasks. However…
Are Large Language Models In-Context Graph Learners?
Jintang Li, Ruofan Wu, Yuchang Zhu +3
Large language models (LLMs) have demonstrated remarkable in-context reasoning capabilities across a wide range of tasks, particularly with unstructured inputs such as language or…
Measuring Diversity in Synthetic Datasets
Yuchang Zhu, Huizhe Zhang, Bingzhe Wu +5
Large language models (LLMs) are widely adopted to generate synthetic datasets for various natural language processing (NLP) tasks, such as text classification and summarization. H…
Revisiting Graph Autoencoders as Implicit Contrastive Learners
Jintang Li, Ruofan Wu, Yuchang Zhu +3
Graph autoencoders (GAEs) and graph contrastive learning (GCL) are two major paradigms for self-supervised representation learning on graphs, yet they are often studied in isolatio…
One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes
Yuchang Zhu, Jintang Li, Yatao Bian +2
Recent studies have highlighted fairness issues in Graph Neural Networks (GNNs), where they produce discriminatory predictions against specific protected groups categorized by sens…
Fair Graph Representation Learning via Sensitive Attribute Disentanglement
Yuchang Zhu, Jintang Li, Zibin Zheng +1
Group fairness for Graph Neural Networks (GNNs), which emphasizes algorithmic decisions neither favoring nor harming certain groups defined by sensitive attributes (e.g., race and…
LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning
Jintang Li, Jiawang Dan, Ruofan Wu +9
Over the past few years, graph neural networks (GNNs) have become powerful and practical tools for learning on (static) graph-structure data. However, many real-world applications,…
The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation
Yuchang Zhu, Jintang Li, Liang Chen +1
Graph neural networks (GNNs) are being increasingly used in many high-stakes tasks, and as a result, there is growing attention on their fairness recently. GNNs have been shown to…
HeteroNet: Heterophily-aware Representation Learning on Heterogenerous Graphs
Jintang Li, Zheng Wei, Jiawang Dan +9
Real-world graphs are typically complex, exhibiting heterogeneity in the global structure, as well as strong heterophily within local neighborhoods. While a growing body of literat…
Oversmoothing: A Nightmare for Graph Contrastive Learning?
Jintang Li, Wangbin Sun, Ruofan Wu +3
Oversmoothing is a common phenomenon observed in graph neural networks (GNNs), in which an increase in the network depth leads to a deterioration in their performance. Graph contra…