Saved in:
Bibliographic Details
Main Authors: Han, Haoyu, Li, Juanhui, Huang, Wei, Tang, Xianfeng, Lu, Hanqing, Luo, Chen, Liu, Hui, Tang, Jiliang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.03464
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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 filter, typically a low-pass filter for homophilic graphs and a high-pass filter for heterophilic graphs. However, real-world graphs often exhibit a complex mix of homophilic and heterophilic patterns, rendering a single global filter approach suboptimal. In this work, we theoretically demonstrate that a global filter optimized for one pattern can adversely affect performance on nodes with differing patterns. To address this, we introduce a novel GNN framework Node-MoE that utilizes a mixture of experts to adaptively select the appropriate filters for different nodes. Extensive experiments demonstrate the effectiveness of Node-MoE on both homophilic and heterophilic graphs.