APPTeK: Agent-Based Predicate Prediction in Temporal Knowledge Graphs
This work addresses predicate prediction for researchers and practitioners in knowledge graph completion, though it is incremental as it builds on existing embedding algorithms.
The paper tackles the problem of predicting predicates in temporal knowledge graphs by proposing a reinforcement learning agent that explores entity neighborhoods to gather temporal information, achieving competitive results compared to state-of-the-art embedding methods.
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.