{"ID":2873863,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.06219","arxiv_id":"2509.06219","title":"MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning","abstract":"Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like catastrophic forgetting, distribution bias, memory limits, and weak generalization. We propose MCIGLE, a novel framework that addresses these issues by extracting and aligning multimodal graph features and applying Concatenated Recursive Least Squares for effective knowledge retention. Through multi-channel processing, MCIGLE balances accuracy and memory preservation. Experiments on public datasets validate its effectiveness and generalizability.","short_abstract":"Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like catastrophic forgetting, distribution bias, memory limits, and weak generalization...","url_abs":"https://arxiv.org/abs/2509.06219","url_pdf":"https://arxiv.org/pdf/2509.06219v1","authors":"[\"Haochen You\",\"Baojing Liu\"]","published":"2025-09-07T21:49:43Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.MM\"]","methods":"[]","has_code":false}