Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge Graphs

TL;DR

This paper introduces MT-Path, a reinforcement learning approach for reasoning over N-tuple temporal knowledge graphs, enhancing explainability and accuracy by leveraging mixture policies and semantic dependency modeling.

Contribution

The paper proposes a novel mixture policy-based reinforcement learning method, MT-Path, for explainable reasoning over N-tuple TKGs, integrating semantic dependencies with an auxiliary GCN.

Findings

MT-Path outperforms existing methods in predictive accuracy.

The approach provides improved explainability in reasoning paths.

Experimental results validate the effectiveness of mixture policies and GCN integration.

Abstract

Temporal Knowledge Graphs (TKGs), which utilize quadruples in the form of (subject, predicate, object, timestamp) to describe temporal facts, have attracted extensive attention. N-tuple TKGs (N-TKGs) further extend traditional TKGs by utilizing n-tuples to incorporate auxiliary elements alongside core elements (i.e., subject, predicate, and object) of facts, so as to represent them in a more fine-grained manner. Reasoning over N-TKGs aims to predict potential future facts based on historical ones. However, existing N-TKG reasoning methods often lack explainability due to their black-box nature. Therefore, we introduce a new Reinforcement Learning-based method, named MT-Path, which leverages the temporal information to traverse historical n-tuples and construct a temporal reasoning path. Specifically, in order to integrate the information encapsulated within n-tuples, i.e., the entity-irrelevant information within the predicate, the information about core elements, and the complete information about the entire n-tuples, MT-Path utilizes a mixture policy-driven action selector, which bases on three low-level policies, namely, the predicate-focused policy, the core-element-focused policy and the whole-fact-focused policy. Further, MT-Path utilizes an auxiliary element-aware GCN to capture the rich semantic dependencies among facts, thereby enabling the agent to gain a deep understanding of each n-tuple. Experimental results demonstrate the effectiveness and the explainability of MT-Path.