TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion

Abstract

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.

arXiv comment17 pages, 9 figures. EMNLP 2020 Long Paper

References in corpus (13)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Dynamic Graph Convolutional Networks
• Relational Graph Attention Networks
• Tensor Decompositions for temporal knowledge base completion
• GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction
• TEQUILA: Temporal Question Answering over Knowledge Bases
• Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition
• Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
• Learning Dynamic Embeddings from Temporal Interactions
• Learning Sequence Encoders for Temporal Knowledge Graph Completion
• Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution

Cited by in corpus (5)

• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• Temporal Knowledge Graph Completion: A Survey
• HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
• Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation