Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

Paper Title Number 4

Published in GitHub Journal of Bugs, 2024

This paper is about fixing template issue #693.

Recommended citation: Your Name, You. (2024). "Paper Title Number 3." GitHub Journal of Bugs. 1(3).
Download Paper

When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline

Published in AAAI, 2025

Existing HNNs primarily focus on scenarios characterized by homophily, that is, the assumption that connected nodes share similar attributes or labels. This assumption, while effective in many cases, limits the generalizability of HNNs to settings where heterophily is predominant. - We recognize the absence of robust metrics for quantifying homophily and heterophily in hypergraphs. - We observe a scarcity of high-quality datasets that represent non-homophilous applications. - To the best of our knowledge, few works have focused on designing HNNs specifcally tailored for heterophilic hypergraph learning (HHL).

Recommended citation: Li M, Gu Y, Wang Y^*, Fang Y, Bai L, Zhuang X, Pietro Lio. When hypergraph meets heterophily: New benchmark datasets and baseline[C]// Proceeding of AAAI Conference on Artificial Intelligence (AAAI). 2025, 39(17): 18377-18384.

ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection

Published in AAAI, 2025

This paper is the first to address graph OOD detection in multi-label classification by leveraging energy functions, demonstrating improved performance across diverse datasets.

Recommended citation: Cai, Tingyi and Jiang, Yunliang and Li, Ming and Huang, Changqin and Wang, Yi and Huang, Qionghao. ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution Detection. AAAI, 2025.

All roads lead to rome: Integrating out-of-distribution detection into heterophilic graph learning

Published in IJCAI, 2025

Heterophilic graph neural networks (GNNs) have gained prominence for their ability to learn effective representations in graphs with diverse, attribute-aware relationships. While existing methods leverage attribute inference during message passing to improve performance, they often struggle with challenging heterophilic graphs. This is due to edge distribution shifts introduced by diverse connection patterns, which blur attribute distinctions and undermine message-passing stability. This paper introduces H$_2$OGNN, a novel framework that reframes edge attribute inference as an out-of-distribution (OOD) detection problem. H$_2$OGNN introduces a simple yet effective symbolic energy regularization approach for OOD learning, ensuring robust classification boundaries between homophilic and heterophilic edge attributes. This design significantly improves the stability and reliability of GNNs across diverse connectivity patterns. Through theoretical analysis, we show that H$_2$OGNN addresses the graph denoising problem by going beyond feature smoothing, offering deeper insights into how precise edge attribute identification boosts model performance. Extensive experiments on nine benchmark datasets demonstrate that H$_2$OGNN not only achieves state-of-the-art performance but also consistently outperforms other heterophilic GNN frameworks, particularly on datasets with high heterophily.

Recommended citation: Wang Y, Huang C, Li M, Cai T, Zheng Z, Huang X. All roads lead to rome: Integrating out-of-distribution detection into heterophilic graph learning[C]// Proceeding of International Joint Conference on Artificial Intelligence (IJCAI). 2025.

talks

Paper Title Number 1

Published: October 01, 2009

under review

Recommended citation: Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1).

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015