Graph Mixing Additive Networks

2025/09/28 by Bechler-Speicher, Maya, Zerio, Andrea, Huri, Maor +5
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2509.23923

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.

Citations

• The Interpretable and Effective Graph Neural Additive Networks
• SAITS: Self-attention-based imputation for time series
• Graph-Guided Network for Irregularly Sampled Multivariate Time Series
• CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
• How Attentive are Graph Attention Networks?
• Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series
• Multi-Time Attention Networks for Irregularly Sampled Time Series
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Set Functions for Time Series
• Interpolation-Prediction Networks for Irregularly Sampled Time Series
• Fake News Detection on Social Media using Geometric Deep Learning
• Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
• BRITS: Bidirectional Recurrent Imputation for Time Series
• Attention Is All You Need
• Inductive Representation Learning on Large Graphs
• Recurrent Neural Networks for Multivariate Time Series with Missing Values

Related

• SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data
• The Interpretable and Effective Graph Neural Additive Networks
• Generative Causal Explanations for Graph Neural Networks
• GDBN: a Graph Neural Network Approach to Dynamic Bayesian Network
• Towards Causal Classification: A Comprehensive Study on Graph Neural Networks