APPTeK: Agent-Based Predicate Prediction in Temporal Knowledge Graphs

TL;DR

This paper introduces APPTeK, a reinforcement learning agent that predicts predicates in temporal knowledge graphs by exploring local subgraphs, achieving competitive results and providing insights into relevant structural patterns.

Contribution

The paper presents a novel agent-based approach using reinforcement learning for predicate prediction in temporal knowledge graphs, incorporating graph exploration and fingerprint encoding.

Findings

Achieves competitive performance with state-of-the-art embedding methods.

Provides interpretable insights into relevant graph structures.

Demonstrates effective sequential relation exploration.

Abstract

In temporal Knowledge Graphs (tKGs), the temporal dimension is attached to facts in a knowledge base resulting in quadruples between entities such as (Nintendo, released, Super Mario, Sep-13-1985), where the predicate holds within a time interval or at a timestamp. We propose a reinforcement learning agent gathering temporal relevant information about the query entities' neighborhoods, simultaneously. We refer to the encodings of the explored graph structures as fingerprints which are used as input to a Q-network. Our agent decides sequentially which relation type needs to be explored next to expand the local subgraphs of the query entities. Our evaluation shows that the proposed method yields competitive results compared to state-of-the-art embedding algorithms for tKGs, and we additionally gain information about the relevant structures between subjects and objects.