TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
This work addresses the challenge of temporal knowledge graph completion for AI applications requiring temporal reasoning, representing an incremental advance over prior methods.
The paper tackles the problem of inferring missing facts in temporal knowledge graphs by proposing the TeMP framework, which combines graph neural networks, temporal dynamics models, data imputation, and frequency-based gating to leverage multi-hop structural information and address temporal sparsity, resulting in a 10.7% average relative improvement in Hits@10 across three benchmarks.
Inferring missing facts in temporal knowledge graphs (TKGs) is a fundamental and challenging task. Previous works have approached this problem by augmenting methods for static knowledge graphs to leverage time-dependent representations. However, these methods do not explicitly leverage multi-hop structural information and temporal facts from recent time steps to enhance their predictions. Additionally, prior work does not explicitly address the temporal sparsity and variability of entity distributions in TKGs. We propose the Temporal Message Passing (TeMP) framework to address these challenges by combining graph neural networks, temporal dynamics models, data imputation and frequency-based gating techniques. Experiments on standard TKG tasks show that our approach provides substantial gains compared to the previous state of the art, achieving a 10.7% average relative improvement in Hits@10 across three standard benchmarks. Our analysis also reveals important sources of variability both within and across TKG datasets, and we introduce several simple but strong baselines that outperform the prior state of the art in certain settings.