Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions

TL;DR

The paper introduces HGPM, a hypergraph learning model that captures higher-order interaction patterns through tokenization and an inclusion-aware Transformer, improving accuracy in complex relational data tasks.

Contribution

HGPM shifts from message passing to pattern learning, enabling better modeling of compositional hyperedge structures and outperforming existing methods on benchmarks.

Findings

HGPM matches or exceeds state-of-the-art on ten benchmarks.

In adverse-event prediction, HGPM correctly identifies inhibitory drug interactions.

The code and data are publicly available at the provided GitHub URL.

Abstract

Hypergraphs model higher-order relations that drive real-world decisions, from drug prescriptions to recommendations. A central structural signal in such data, beyond what pairwise relations can express, is interaction compositionality: whether a higher-order relation is compositional, emergent, or inhibitory with respect to its observed or unobserved sets. In polypharmacy, the regime decides whether a drug should be dropped, kept, or excluded: a compositional drug triple can be safely simplified, an emergent triple requires all drugs jointly, and an inhibitory triple flags a drug that disrupts an existing interaction. However, existing hypergraph learning methods, which merely propagate messages over observed hyperedges, leave this compositional signal unmodeled, allowing dangerous drug combinations to slip through and be misclassified. To this end, we propose the Hypergraph Pattern Machine (HGPM), shifting the paradigm from message passing to learning the compositional pattern of subsets. It tokenizes compositional subsets, organizes them in an inclusion DAG, and trains an inclusion-aware Transformer under masked reconstruction. On ten hypergraph benchmarks, HGPM matches or exceeds state-of-the-art methods. Notably, in a real adverse-event prediction case, HGPM correctly identifies the drug addition that inhibits the side effect among feature-identical candidates, a discrimination existing methods cannot make. The code and data are in https://github.com/KryieZhao/HGPM.git.