Skip to content
conftrace_
2025 ICML ICML 2025

Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Zhongtian Ma, Qiaosheng Zhang, Bocheng Zhou, Yexin Zhang, Shuyue Hu, Zhen Wang

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Learning Theory Deep Learning > Architectures > Graph Neural Networks

Keywords

signal-to-noise ratio feature noise graph attention mechanism contextual stochastic block model over smoothing structure noise
Download PDF