Graph Mixing Additive Networks
This work addresses the need for interpretable models in domains like healthcare and misinformation detection, though it appears incremental as it builds upon existing Graph Neural Additive Networks.
The authors tackled the problem of learning from sparse time-series data by introducing GMAN, a framework that extends Graph Neural Additive Networks to represent time-dependent trajectories as directed graphs, and it outperformed non-interpretable baselines on real-world datasets like mortality prediction and fake-news detection.
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.