xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links

Abstract

Modeling time-evolving knowledge graphs (KGs) has recently gained increasing interest. Here, graph representation learning has become the dominant paradigm for link prediction on temporal KGs. However, the embedding-based approaches largely operate in a black-box fashion, lacking the ability to interpret their predictions. This paper provides a link forecasting framework that reasons over query-relevant subgraphs of temporal KGs and jointly models the structural dependencies and the temporal dynamics. Especially, we propose a temporal relational attention mechanism and a novel reverse representation update scheme to guide the extraction of an enclosing subgraph around the query. The subgraph is expanded by an iterative sampling of temporal neighbors and by attention propagation. Our approach provides human-understandable evidence explaining the forecast. We evaluate our model on four benchmark temporal knowledge graphs for the link forecasting task. While being more explainable, our model obtains a relative improvement of up to 20% on Hits@1 compared to the previous best KG forecasting method. We also conduct a survey with 53 respondents, and the results show that the evidence extracted by the model for link forecasting is aligned with human understanding.

24 pages, 8 figures, accepted to ICLR 2021

References in corpus (7)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Tensor Decompositions for temporal knowledge base completion
• Inductive Relation Prediction by Subgraph Reasoning
• Dynamically Fused Graph Network for Multi-hop Reasoning
• Reasoning on Knowledge Graphs with Debate Dynamics
• DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion