Temporal Inductive Logic Reasoning over Hypergraphs

TL;DR

This paper introduces TILR, a novel inductive logic reasoning method designed for temporal hypergraphs, extending reasoning capabilities beyond traditional knowledge graphs to more complex, real-world data structures.

Contribution

The paper proposes TILR, a new ILP approach for reasoning over temporal hypergraphs, including a novel hypergraph traversal method and new benchmark datasets.

Findings

TILR outperforms existing methods on new benchmarks.

The multi-start random B-walk effectively enables hypergraph reasoning.

Created and released two new temporal hypergraph datasets.

Abstract

Inductive logic reasoning is a fundamental task in graph analysis, which aims to generalize patterns from data. This task has been extensively studied for traditional graph representations, such as knowledge graphs (KGs), using techniques like inductive logic programming (ILP). Existing ILP methods assume learning from KGs with static facts and binary relations. Beyond KGs, graph structures are widely present in other applications such as procedural instructions, scene graphs, and program executions. While ILP is beneficial for these applications, applying it to those graphs is nontrivial: they are more complex than KGs, which usually involve timestamps and n-ary relations, effectively a type of hypergraph with temporal events. In this work, we propose temporal inductive logic reasoning (TILR), an ILP method that reasons on temporal hypergraphs. To enable hypergraph reasoning, we introduce the multi-start random B-walk, a novel graph traversal method for hypergraphs. By combining it with a path-consistency algorithm, TILR learns logic rules by generalizing from both temporal and relational data. To address the lack of hypergraph benchmarks, we create and release two temporal hypergraph datasets: YouCook2-HG and nuScenes-HG. Experiments on these benchmarks demonstrate that TILR achieves superior reasoning capability over various strong baselines.