The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs

TL;DR

This paper introduces the Heterophily Snowflake Hypothesis, a novel approach allowing GNNs to adaptively aggregate neighbors in heterophilic graphs, improving performance and interpretability across various architectures and datasets.

Contribution

It proposes a new hypothesis and framework enabling GNNs to dynamically determine neighbor aggregation, addressing heterophily challenges and enhancing GNN versatility.

Findings

Effective across 10 diverse graphs with varying heterophily ratios

Scalable to deep GNN architectures with up to 32 layers

Outperforms traditional methods and improves explainability

Abstract

Graph Neural Networks (GNNs) have become pivotal tools for a range of graph-based learning tasks. Notably, most current GNN architectures operate under the assumption of homophily, whether explicitly or implicitly. While this underlying assumption is frequently adopted, it is not universally applicable, which can result in potential shortcomings in learning effectiveness. In this paper, \textbf{for the first time}, we transfer the prevailing concept of ``one node one receptive field" to the heterophilic graph. By constructing a proxy label predictor, we enable each node to possess a latent prediction distribution, which assists connected nodes in determining whether they should aggregate their associated neighbors. Ultimately, every node can have its own unique aggregation hop and pattern, much like each snowflake is unique and possesses its own characteristics. Based on observations, we innovatively introduce the Heterophily Snowflake Hypothesis and provide an effective solution to guide and facilitate research on heterophilic graphs and beyond. We conduct comprehensive experiments including (1) main results on 10 graphs with varying heterophily ratios across 10 backbones; (2) scalability on various deep GNN backbones (SGC, JKNet, etc.) across various large number of layers (2,4,6,8,16,32 layers); (3) comparison with conventional snowflake hypothesis; (4) efficiency comparison with existing graph pruning algorithms. Our observations show that our framework acts as a versatile operator for diverse tasks. It can be integrated into various GNN frameworks, boosting performance in-depth and offering an explainable approach to choosing the optimal network depth. The source code is available at \url{https://github.com/bingreeky/HeteroSnoH}.