TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion

by   Jiapeng Wu, et al.

Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challenging when the TKG is updated frequently. The model has to adapt to changes in the TKG for efficient training and inference while preserving its performance on historical knowledge. Recent work approaches TKG completion (TKGC) by augmenting the encoder-decoder framework with a time-aware encoding function. However, naively fine-tuning the model at every time step using these methods does not address the problems of 1) catastrophic forgetting, 2) the model's inability to identify the change of facts (e.g., the change of the political affiliation and end of a marriage), and 3) the lack of training efficiency. To address these challenges, we present the Time-aware Incremental Embedding (TIE) framework, which combines TKG representation learning, experience replay, and temporal regularization. We introduce a set of metrics that characterizes the intransigence of the model and propose a constraint that associates the deleted facts with negative labels. Experimental results on Wikidata12k and YAGO11k datasets demonstrate that the proposed TIE framework reduces training time by about ten times and improves on the proposed metrics compared to vanilla full-batch training. It comes without a significant loss in performance for any traditional measures. Extensive ablation studies reveal performance trade-offs among different evaluation metrics, which is essential for decision-making around real-world TKG applications.


page 1

page 2

page 3

page 4


History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completion

Temporal knowledge graph (TKG) completion models typically rely on havin...

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting

Temporal knowledge graph (TKG) reasoning is a crucial task that has gain...

A Temporal Knowledge Graph Completion Method Based on Balanced Timestamp Distribution

Completion through the embedding representation of the knowledge graph (...

A Pre-training Framework for Knowledge Graph Completion

Knowledge graph completion (KGC) is one of the effective methods to iden...

Wasserstein Adversarial Learning based Temporal Knowledge Graph Embedding

Research on knowledge graph embedding (KGE) has emerged as an active fie...

SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement

Knowledge graph (KG) refinement mainly aims at KG completion and correct...

Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning

A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to d...

Please sign up or login with your details

Forgot password? Click here to reset