---
title: "Bridging Feature-structural Homophily and Long-range Heterogeneity for Self-supervised Heterogeneous Graph Learning"
authors:
  - "Minda Chen"
  - "Yujie Mo"
  - "Junkai Huang"
  - "Guoqiu Wen"
  - "Xiaofeng Zhu"
doi: "10.24963/ijcai.2026/280"
url: "https://ijcai.org/proceedings/2026/280"
pdf: "https://ijcai.org/proceedings/2026/0280.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2519-2527"
track: "Main Track"
keywords:
  - "Data Mining: Mining graphs"
  - "Machine Learning: Self-supervised Learning"
  - "Data Mining: Mining heterogenous data"
  - "Machine Learning: Representation learning"
---

# Bridging Feature-structural Homophily and Long-range Heterogeneity for Self-supervised Heterogeneous Graph Learning

Minda Chen, Yujie Mo, Junkai Huang, Guoqiu Wen, Xiaofeng Zhu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2519-2527. DOI: [10.24963/ijcai.2026/280](https://doi.org/10.24963/ijcai.2026/280)

## Abstract

Self-supervised heterogeneous graph learning has achieved promising results in diverse applications but still faces two issues: (i) existing methods focus on either feature similarity or meta-path to capture homophily, neglecting their inherent complementarity; (ii) existing methods rely on meta-paths to capture interactions among same-type nodes, which may introduce noise and inherently exclude long-range cross-type interactions. To address these issues, we first propose a self-expressive solver that captures the complementary homophily between meta-paths and node features to obtain homophilous representations. Meanwhile, we design separate path encoders to model diverse interactions, thus explicitly including cross-type interactions while mitigating noise via adaptive fusion. Theoretical analysis verifies that homophilous representations exhibit a high-order grouping effect to capture complementary homophily, while path encoders possess adaptive smoothness capabilities to filter noise. Extensive experiments on diverse datasets, including a large-scale dataset, demonstrate the superiority of the proposed method.