Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Kyrie, Wang, Zehong, Ma, Tianyi, Wu, Fang, Tang, Xiangru, Lio, Pietro, Wang, Sheng, Ye, Yanfang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909049012879360
author Zhao, Kyrie
Wang, Zehong
Ma, Tianyi
Wu, Fang
Tang, Xiangru
Lio, Pietro
Wang, Sheng
Ye, Yanfang
author_facet Zhao, Kyrie
Wang, Zehong
Ma, Tianyi
Wu, Fang
Tang, Xiangru
Lio, Pietro
Wang, Sheng
Ye, Yanfang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16527
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions
Zhao, Kyrie
Wang, Zehong
Ma, Tianyi
Wu, Fang
Tang, Xiangru
Lio, Pietro
Wang, Sheng
Ye, Yanfang
Machine Learning
Artificial Intelligence
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.
title Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.16527