Neural Predicting Higher-order Patterns in Temporal Networks
This work addresses the challenge of modeling complex interactions in dynamic systems for researchers in network science and machine learning, representing an incremental advancement with a novel method for a known bottleneck.
The authors tackled the problem of predicting higher-order interaction patterns in temporal networks by proposing HIT, the first model for full-spectrum higher-order pattern prediction in temporal hypergraphs, achieving an averaged 20% AUC gain for interaction type identification and more accurate time estimation compared to baselines.
Dynamic systems that consist of a set of interacting elements can be abstracted as temporal networks. Recently, higher-order patterns that involve multiple interacting nodes have been found crucial to indicate domain-specific laws of different temporal networks. This posts us the challenge of designing more sophisticated hypergraph models for these higher-order patterns and the associated new learning algorithms. Here, we propose the first model, named HIT, for full-spectrum higher-order pattern prediction in temporal hypergraphs. Particularly, we focus on predicting three types of common but important interaction patterns involving three interacting elements in temporal networks, which could be extended to even higher-order patterns. HIT extracts the structural representation of a node triplet of interest on the temporal hypergraph and uses it to tell what type of, when, and why the interaction expansion could happen in this triplet. HIT could achieve significant improvement (averaged 20% AUC gain to identify the interaction type, uniformly more accurate time estimation) compared to both heuristic and other neural-network-based baselines on 5 real-world large temporal hypergraphs. Moreover, HIT provides a certain degree of interpretability by identifying the most discriminatory structural features on the temporal hypergraphs for predicting different higher-order patterns.