27 citations · 67 across the 23 of their papers we have counts for
10 papers · 1 filter
Unveiling Mode Connectivity in Graph Neural Networks
Bingheng Li, Zhikai Chen, Haoyu Han +3
A fundamental challenge in understanding graph neural networks (GNNs) lies in characterizing their optimization dynamics and loss landscape geometry, critical for improving interpr…
Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
Yongjia Lei, Haoyu Han, Ryan A. Rossi +5
Text-rich Graph Knowledge Bases (TG-KBs) have become increasingly crucial for answering queries by providing textual and structural knowledge. However, current retrieval methods of…
Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
Haoyu Han, Juanhui Li, Wei Huang +5
Graph Neural Networks (GNNs) have proven to be highly effective for node classification tasks across diverse graph structural patterns. Traditionally, GNNs employ a uniform global…
Mixture of Link Predictors on Graphs
Li Ma, Haoyu Han, Juanhui Li +4
Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning. Heuristic methods, leveraging a range of different pairwise m…
Spectral-Aware Augmentation for Enhanced Graph Representation Learning
Kaiqi Yang, Haoyu Han, Wei Jin +1
Graph Contrastive Learning (GCL) has demonstrated remarkable effectiveness in learning representations on graphs in recent years. To generate ideal augmentation views, the augmenta…
Label-free Node Classification on Graphs with Large Language Models (LLMS)
Zhikai Chen, Haitao Mao, Hongzhi Wen +5
In recent years, there have been remarkable advancements in node classification achieved by Graph Neural Networks (GNNs). However, they necessitate abundant high-quality labels to…
Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
Haitao Mao, Zhikai Chen, Wei Jin +5
Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and…
Towards Label Position Bias in Graph Neural Networks
Haoyu Han, Xiaorui Liu, Feng Shi +3
Graph Neural Networks (GNNs) have emerged as a powerful tool for semi-supervised node classification tasks. However, recent studies have revealed various biases in GNNs stemming fr…
LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation
Rui Xue, Haoyu Han, MohamadAli Torkamani +2
Recent works have demonstrated the benefits of capturing long-distance dependency in graphs by deeper graph neural networks (GNNs). But deeper GNNs suffer from the long-lasting sca…
Alternately Optimized Graph Neural Networks
Haoyu Han, Xiaorui Liu, Haitao Mao +4
Graph Neural Networks (GNNs) have greatly advanced the semi-supervised node classification task on graphs. The majority of existing GNNs are trained in an end-to-end manner that ca…