Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
arXiv:2106.00327
Abstract
Temporal Knowledge Graphs (TKGs) have been developed and used in many different areas. Reasoning on TKGs that predicts potential facts (events) in the future brings great challenges to existing models. When facing a prediction task, human beings usually search useful historical information (i.e., clues) in their memories and then reason for future meticulously. Inspired by this mechanism, we propose CluSTeR to predict future facts in a two-stage manner, Clue Searching and Temporal Reasoning, accordingly. Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts. At the temporal reasoning stage, it adopts a graph convolution network based sequence method to deduce answers from clues. Experiments on four datasets demonstrate the substantial advantages of CluSTeR compared with the state-of-the-art methods. Moreover, the clues found by CluSTeR further provide interpretability for the results.
arXiv commentACL 2021 long paper (main conference)
References in corpus (20)
- Adam: A Method for Stochastic Optimization
- Twitter mood predicts the stock market
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
- An Actor-Critic Algorithm for Sequence Prediction
- Reinforcement Learning for Relation Classification from Noisy Data
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
- Efficiently Embedding Dynamic Knowledge Graphs
- From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
- Using Social Media to Predict the Future: A Systematic Literature Review
- Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
- Multi-Hop Knowledge Graph Reasoning with Reward Shaping
- Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
- Temporal Knowledge Graph Forecasting with Neural ODE
- Learning Sequence Encoders for Temporal Knowledge Graph Completion
- A Study of Reinforcement Learning for Neural Machine Translation
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning
- Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs
- T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion
- DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion