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

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

doi:10.24963/ijcai.2026/280

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

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

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 2519-2527.

https://doi.org/10.24963/ijcai.2026/280

Keywords

Data Mining: Mining graphs
Machine Learning: Self-supervised Learning
Data Mining: Mining heterogenous data
Machine Learning: Representation learning

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.

Minda Chen, Yujie Mo, Junkai Huang, Guoqiu Wen, and Xiaofeng Zhu. 2026. Bridging Feature-structural Homophily and Long-range Heterogeneity for Self-supervised Heterogeneous Graph Learning. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 2519–2527. https://doi.org/10.24963/ijcai.2026/280

@inproceedings{ijcai2026p280,
  title     = {Bridging Feature-structural Homophily and Long-range Heterogeneity for Self-supervised Heterogeneous Graph Learning},
  author    = {Chen, Minda and Mo, Yujie and Huang, Junkai and Wen, Guoqiu and Zhu, Xiaofeng},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {2519--2527},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/280},
  url       = {https://doi.org/10.24963/ijcai.2026/280},
}

TY  - CPAPER
TI  - Bridging Feature-structural Homophily and Long-range Heterogeneity for Self-supervised Heterogeneous Graph Learning
AU  - Chen, Minda
AU  - Mo, Yujie
AU  - Huang, Junkai
AU  - Wen, Guoqiu
AU  - Zhu, Xiaofeng
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 2519
EP  - 2527
DO  - 10.24963/ijcai.2026/280
UR  - https://doi.org/10.24963/ijcai.2026/280
ER  -