{"ID":5551910,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T01:45:22.703757252Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00377","arxiv_id":"2607.00377","title":"SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport","abstract":"Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce stability of individual node (or node-pair) embeddings. Due to optimizing nodes in isolation, these methods fail to maintain global relational structure, causing inter-node correspondences to progressively distort under continual learning. To this end, we propose a novel Structure-Aware Optimal Transport (SAOT) framework that explicitly captures and preserves relational structure within graph representations across sequential tasks. Specifically, SAOT leverages optimal transport theory to capture global inter-node correspondences, thereby facilitating and enhancing graph representation learning. Simultaneously, SAOT incorporates a cross-task knowledge distillation mechanism to preserve the previous structural knowledge. Extensive experiments on four CGL benchmark datasets demonstrate that SAOT outperforms existing self-supervised baselines. In particular, SAOT achieves significant performance gains, improving average accuracy by up to 5% on CoraFull-CL and over 15% on Products-CL compared with state-of-the-art methods in the Class-IL setting.","short_abstract":"Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce stability of individua...","url_abs":"https://arxiv.org/abs/2607.00377","url_pdf":"https://arxiv.org/pdf/2607.00377v1","authors":"[\"Yuting Zhang\",\"Yanbei Liu\",\"Zhitao Xiao\",\"Lei Geng\",\"Yanwei Pang\",\"Xiao Wang\"]","published":"2026-07-01T03:21:23Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.SI\"]","methods":"[]","has_code":false}