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

TL;DR

This paper introduces Node-MoE, a novel GNN framework that adaptively selects node-specific filters using a mixture of experts, improving performance on graphs with mixed homophilic and heterophilic patterns.

Contribution

The paper proposes a mixture of experts approach for GNNs, enabling adaptive filter selection per node to handle diverse graph structures.

Findings

Node-MoE outperforms traditional GNNs on mixed-pattern graphs.

Theoretical analysis shows global filters can harm performance on certain nodes.

Experimental results confirm the effectiveness of adaptive filtering.

Abstract

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.