Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach

Fuente: arXiv
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:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909217656406016
author Han, Haoyu
Li, Juanhui
Huang, Wei
Tang, Xianfeng
Lu, Hanqing
Luo, Chen
Liu, Hui
Tang, Jiliang
author_facet Han, Haoyu
Li, Juanhui
Huang, Wei
Tang, Xianfeng
Lu, Hanqing
Luo, Chen
Liu, Hui
Tang, Jiliang
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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03464
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
Han, Haoyu
Li, Juanhui
Huang, Wei
Tang, Xianfeng
Lu, Hanqing
Luo, Chen
Liu, Hui
Tang, Jiliang
Machine Learning
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.
title Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
topic Machine Learning
url https://arxiv.org/abs/2406.03464