The reviewed record of science sign in
Pith

arxiv: 2412.07243 · v1 · pith:LJ5ILQ45 · submitted 2024-12-10 · cs.LG · cs.AI

A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Neural Networks

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:LJ5ILQ45record.jsonopen to challenge →

classification cs.LG cs.AI
keywords oversmoothingdynamicaldynamo-gatgnnsstabilitysystemsanalysisapproach
0
0 comments X
read the original abstract

Oversmoothing in Graph Neural Networks (GNNs) poses a significant challenge as network depth increases, leading to homogenized node representations and a loss of expressiveness. In this work, we approach the oversmoothing problem from a dynamical systems perspective, providing a deeper understanding of the stability and convergence behavior of GNNs. Leveraging insights from dynamical systems theory, we identify the root causes of oversmoothing and propose \textbf{\textit{DYNAMO-GAT}}. This approach utilizes noise-driven covariance analysis and Anti-Hebbian principles to selectively prune redundant attention weights, dynamically adjusting the network's behavior to maintain node feature diversity and stability. Our theoretical analysis reveals how DYNAMO-GAT disrupts the convergence to oversmoothed states, while experimental results on benchmark datasets demonstrate its superior performance and efficiency compared to traditional and state-of-the-art methods. DYNAMO-GAT not only advances the theoretical understanding of oversmoothing through the lens of dynamical systems but also provides a practical and effective solution for improving the stability and expressiveness of deep GNNs.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.