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.
@article{arxiv.2509.23923,
title = {Graph Mixing Additive Networks},
author = {Maya Bechler-Speicher and Andrea Zerio and Maor Huri and Marie Vibeke Vestergaard and Ran Gilad-Bachrach and Tine Jess and Samir Bhatt and Aleksejs Sazonovs},
journal= {arXiv preprint arXiv:2509.23923},
year = {2025}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2505.19193