Robust Learning on Heterogeneous Graphs with Heterophily: A Graph Structure Learning Approach

TL;DR

This paper introduces HGUL, a unified framework for robust learning on heterogeneous graphs with heterophily, effectively handling structural noise and improving performance over existing methods.

Contribution

The paper proposes a novel framework that jointly addresses heterophily and noisy structures in heterogeneous graphs, enhancing robustness and accuracy.

Findings

HGUL outperforms existing methods on multiple datasets.

It maintains strong robustness under structural noise.

The framework effectively filters noisy edges and captures class relationships.

Abstract

Heterogeneous graphs with heterophily have emerged as a powerful abstraction for modeling complex real-world systems, where nodes of different types and labels interact in diverse and often non-homophilous ways. Despite recent advances, robust representation learning for such graphs remains largely unexplored, particularly in the presence of noisy or misleading connectivity. In this work, we investigate this problem and identify structural noise as a critical challenge that significantly degrades model performance. To address this issue, we propose a unified framework, Heterogeneous Graph Unified Learning (HGUL), which jointly handles heterophily and noisy graph structures. The framework consists of three complementary modules: a kNN-based graph construction module that recovers reliable local neighborhoods, a graph structure learning module that adaptively refines the adjacency by filtering noisy edges, and a heterogeneous affinity learning module that captures class-level relationships via an extended affinity matrix derived from a polynomial graph kernel. Extensive experiments on multiple datasets demonstrate that HGUL consistently outperforms existing methods on clean graphs and maintains strong robustness under varying levels of structural noise. The results further underscore the importance of jointly modeling heterophily and noise in heterogeneous graph learning.