Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs

Abstract

Knowledge graph reasoning is a critical task in natural language processing. The task becomes more challenging on temporal knowledge graphs, where each fact is associated with a timestamp. Most existing methods focus on reasoning at past timestamps and they are not able to predict facts happening in the future. This paper proposes Recurrent Event Network (RE-NET), a novel autoregressive architecture for predicting future interactions. The occurrence of a fact (event) is modeled as a probability distribution conditioned on temporal sequences of past knowledge graphs. Specifically, our RE-NET employs a recurrent event encoder to encode past facts and uses a neighborhood aggregator to model the connection of facts at the same timestamp. Future facts can then be inferred in a sequential manner based on the two modules. We evaluate our proposed method via link prediction at future times on five public datasets. Through extensive experiments, we demonstrate the strength of RENET, especially on multi-step inference over future timestamps, and achieve state-of-the-art performance on all five datasets. Code and data can be found at https://github.com/INK-USC/RE-Net.

arXiv comment15 pages, 8 figures, accepted at as full paper in EMNLP 2020

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Inductive Representation Learning on Large Graphs
• Complex Embeddings for Simple Link Prediction
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Dynamic Memory Networks for Visual and Textual Question Answering
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• Learning Deep Generative Models of Graphs
• A note on the evaluation of generative models
• DynGEM: Deep Embedding Method for Dynamic Graphs
• Graph networks as learnable physics engines for inference and control
• Scalable Link Prediction in Dynamic Networks via Non-Negative Matrix Factorization
• Node Embedding over Temporal Graphs
• Tensor Decompositions for temporal knowledge base completion
• Using Social Media to Predict the Future: A Systematic Literature Review
• Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
• Learning Sequence Encoders for Temporal Knowledge Graph Completion

Cited by in corpus (15)

• 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
• Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
• Temporal Knowledge Graph Forecasting with Neural ODE
• xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links
• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
• On the Ambiguity of Rank-Based Evaluation of Entity Alignment or Link Prediction Methods
• DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
• Temporal Knowledge Graph Reasoning Triggered by Memories
• Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
• Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism
• RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion
• Bayesian Inference of a Social Graph with Trace Feasibility Guarantees