Portrait de Sitao Luan n'est pas disponible

Sitao Luan

luansito@mila.quebec
Doctorat - McGill University
Superviseur⋅e principal⋅e
Doina Precup
Site web
Github
Google Scholar

Publications

Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks
Sitao Luan
Mingde Zhao
Xiao-Wen Chang
Doina Precup
2024-02-20
Complex Networks & Their Applications XII (publié)
doi.org
arxiv.org
When Do We Need Graph Neural Networks for Node Classification?
Sitao Luan
Chenqing Hua
Qincheng Lu
Jiaqi Zhu
Xiao-Wen Chang
Doina Precup
2024-02-20
Complex Networks & Their Applications XII (publié)
doi.org
arxiv.org
MUDiff: Unified Diffusion for Complete Molecule Generation
Chenqing Hua
Sitao Luan
Minkai Xu
Rex Ying
Zhitao Ying
Jie Fu
Stefano Ermon
Doina Precup
2023-11-18
logconference.io/LOG/2023/Conference (poster)
doi.org
openreview.net
When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability
Sitao Luan
Chenqing Hua
Minkai Xu
Qincheng Lu
Jiaqi Zhu
Xiao-Wen Chang
Jie Fu
Jure Leskovec
Doina Precup
2023-04-25
ArXiv (prépublication)
arxiv.org
arxiv.org
When Do Graph Neural Networks Help with Node Classification: Investigating the Homophily Principle on Node Distinguishability
Sitao Luan
Chenqing Hua
Minkai Xu
Qincheng Lu
Jiaqi Zhu
Xiao-Wen Chang
Jie Fu
Jure Leskovec
Doina Precup
Homophily principle, i.e., nodes with the same labels are more likely to be connected, was believed to be the main reason for the performanc… (voir plus)e superiority of Graph Neural Networks (GNNs) over Neural Networks (NNs) on Node Classification (NC) tasks. Recently, people have developed theoretical results arguing that, even though the homophily principle is broken, the advantage of GNNs can still hold as long as nodes from the same class share similar neighborhood patterns [29], which questions the validity of homophily. However, this argument only considers intra-class Node Distinguishability (ND) and ignores inter-class ND, which is insufficient to study the effect of homophily. In this paper, we first demonstrate the aforementioned insufficiency with examples and argue that an ideal situation for ND is to have smaller intra-class ND than inter-class ND. To formulate this idea and have a better understanding of homophily, we propose Contextual Stochastic Block Model for Homophily (CSBM-H) and define two metrics, Probabilistic Bayes Error (PBE) and Expected Negative KL-divergence (ENKL), to quantify ND, through which we can also find how intra- and inter-class ND influence ND together. We visualize the results and give detailed analysis. Through experiments, we verified that the superiority of GNNs is
openreview.net