{"ID":2864364,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23923","arxiv_id":"2509.23923","title":"Graph Mixing Additive Networks","abstract":"We introduce GMAN, a flexible, interpretable, and expressive framework that extends Graph Neural Additive Networks (GNANs) to learn from sets of sparse time-series data. GMAN represents each time-dependent trajectory as a directed graph and applies an enriched, more expressive GNAN to each graph. It allows users to control the interpretability-expressivity trade-off by grouping features and graphs to encode priors, and it provides feature, node, and graph-level interpretability. On real-world datasets, including mortality prediction from blood tests and fake-news detection, GMAN outperforms strong non-interpretable black-box baselines while delivering actionable, domain-aligned explanations.","short_abstract":"We introduce GMAN, a flexible, interpretable, and expressive framework that extends Graph Neural Additive Networks (GNANs) to learn from sets of sparse time-series data. GMAN represents each time-dependent trajectory as a directed graph and applies an enriched, more expressive GNAN to each graph. It allows users to con...","url_abs":"https://arxiv.org/abs/2509.23923","url_pdf":"https://arxiv.org/pdf/2509.23923v2","authors":"[\"Maya Bechler-Speicher\",\"Andrea Zerio\",\"Maor Huri\",\"Marie Vibeke Vestergaard\",\"Ran Gilad-Bachrach\",\"Tine Jess\",\"Samir Bhatt\",\"Aleksejs Sazonovs\"]","published":"2025-09-28T14:58:58Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}