Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs

Abstract

The availability of large scale event data with time stamps has given rise to dynamically evolving knowledge graphs that contain temporal information for each edge. Reasoning over time in such dynamic knowledge graphs is not yet well understood. To this end, we present Know-Evolve, a novel deep evolutionary knowledge network that learns non-linearly evolving entity representations over time. The occurrence of a fact (edge) is modeled as a multivariate point process whose intensity function is modulated by the score for that fact computed based on the learned entity embeddings. We demonstrate significantly improved performance over various relational learning approaches on two large scale real-world datasets. Further, our method effectively predicts occurrence or recurrence time of a fact which is novel compared to prior reasoning approaches in multi-relational setting.

References in corpus (6)

• A Review of Relational Machine Learning for Knowledge Graphs
• Probabilistic Reasoning via Deep Learning: Neural Association Models
• Deep Coevolutionary Network: Embedding User and Item Features for Recommendation
• Bayesian Poisson Tucker Decomposition for Learning the Structure of International Relations
• Predicting the Co-Evolution of Event and Knowledge Graphs
• A Stochastic Differential Equation Framework for Guiding Online User Activities in Closed Loop

Cited by in corpus (15)

• Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
• Adversarial Attack on Graph Structured Data
• Temporal Knowledge Graph Completion: A Survey
• Representation Learning over Dynamic Graphs
• HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
• FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents
• A Survey on Dynamic Network Embedding
• Streaming Graph Neural Networks
• Learning Dynamic Embeddings from Temporal Interactions
• Learning Sequence Encoders for Temporal Knowledge Graph Completion
• TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation
• RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion
• Dynamic Network Embedding via Incremental Skip-gram with Negative Sampling
• Timestamping Documents and Beliefs
• A Probit Tensor Factorization Model For Relational Learning