cs.LGDec 30, 2025

SelfGRL: Self-Organized Graph Representation Learning Inspired by Helmholtz Free Energy Minimization

Authors: Rui Chen, Junjun Guo, Hongbin Wang, Yan Xiang, Yantuan Xian, Zhengtao Yu

Organizations: Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, Yunnan, China · Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming, 650500, Yunnan, China

Abstract

Graph Representation Learning (GRL) requires node embeddings to preserve local structural coherence while remaining globally discriminative. Existing graph self-supervised methods generally coordinate these competing objectives through method-specific designs, lacking a unified and adaptive mechanism that responds to the evolving representation state. To address this limitation, we propose SelfGRL, a self-organized graph representation learning framework that reformulates representation learning as Helmholtz free-energy minimization on the unit hypersphere. SelfGRL models local neighborhood attraction as a Structural Binding Energy through neighbor-mean alignment, while introducing a Sampling-Free Repulsive Entropy objective to preserve global dispersion and prevent representation collapse without pairwise negative sampling. To dynamically coordinate these competing effects, we develop an endogenous Bayesian Thermostat that adaptively regulates their relative strengths in response to the evolving representation state, allowing the system to approach a metastable semantic equilibrium without requiring manually tuned loss weights. Extensive experiments on node classification across both homophilic and heterophilic benchmark datasets, together with link prediction evaluations, demonstrate that SelfGRL consistently achieves strong performance across diverse graph structures.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions

    May 12, 2026Mohamed Mahmoud Amar, Nairouz Mrabah, Mohamed Bouguessa +1Graph Representation LearningGraph SSL

  2. Graph Topology Information Enhanced Heterogeneous Graph Representation Learning

    Apr 7, 2026He Zhao, Zhiwei Zeng, Yongwei Wang +1Graph Representation LearningGraph Structure Learning

  3. SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport

    Jul 1, 2026Yuting Zhang, Yanbei Liu, Zhitao Xiao +3Graph Representation LearningGraph SSL