Interpretable Graph Learning Over Sets of Temporally-Sparse Data
This addresses the challenge of handling fragmented temporal data in high-stakes domains like healthcare and fake news detection, offering an interpretable model for improved decision-making.
The paper tackles the problem of learning from irregular and asynchronous temporal data across multiple signals, such as medical measurements or social network events, by proposing Graph Mixing Additive Networks (GMAN), which achieves state-of-the-art performance with a 4-point increase in AUROC for in-hospital mortality prediction.
Real-world medical data often includes measurements from multiple signals that are collected at irregular and asynchronous time intervals. For example, different types of blood tests can be measured at different times and frequencies, resulting in fragmented and unevenly scattered temporal data. Similar issues of irregular sampling of different attributes occur in other domains, such as monitoring of large systems using event log files or the spread of fake news on social networks. Effectively learning from such data requires models that can handle sets of temporally sparse and heterogeneous signals. In this paper, we propose Graph Mixing Additive Networks (GMAN), a novel and interpretable-by-design model for learning over irregular sets of temporal signals. Our method achieves state-of-the-art performance in real-world medical tasks, including a 4-point increase in the AUROC score of in-hospital mortality prediction, compared to existing methods. We further showcase GMAN's flexibility by applying it to a fake news detection task. We demonstrate how its interpretability capabilities, including node-level, graph-level, and subset-level importance, allow for transition phases detection and gaining medical insights with real-world high-stakes implications. Finally, we provide theoretical insights on GMAN expressive power.