ETT-CKGE: Efficient Task-driven Tokens for Continual Knowledge Graph Embedding

TL;DR

ETT-CKGE introduces a task-driven token mechanism for continual knowledge graph embedding, significantly improving efficiency and scalability while maintaining competitive predictive performance across multiple datasets.

Contribution

The paper proposes a novel token-based approach that replaces manual importance scoring and graph traversal, enabling efficient knowledge transfer in CKGE.

Findings

Achieves superior or competitive predictive performance on six benchmark datasets.

Reduces training time and memory usage compared to existing methods.

Demonstrates improved scalability and efficiency in continual knowledge graph embedding.

Abstract

Continual Knowledge Graph Embedding (CKGE) seeks to integrate new knowledge while preserving past information. However, existing methods struggle with efficiency and scalability due to two key limitations: (1) suboptimal knowledge preservation between snapshots caused by manually designed node/relation importance scores that ignore graph dependencies relevant to the downstream task, and (2) computationally expensive graph traversal for node/relation importance calculation, leading to slow training and high memory overhead. To address these limitations, we introduce ETT-CKGE (Efficient, Task-driven, Tokens for Continual Knowledge Graph Embedding), a novel task-guided CKGE method that leverages efficient task-driven tokens for efficient and effective knowledge transfer between snapshots. Our method introduces a set of learnable tokens that directly capture task-relevant signals, eliminating the need for explicit node scoring or traversal. These tokens serve as consistent and reusable guidance across snapshots, enabling efficient token-masked embedding alignment between snapshots. Importantly, knowledge transfer is achieved through simple matrix operations, significantly reducing training time and memory usage. Extensive experiments across six benchmark datasets demonstrate that ETT-CKGE consistently achieves superior or competitive predictive performance, while substantially improving training efficiency and scalability compared to state-of-the-art CKGE methods. The code is available at: https://github.com/lijingzhu1/ETT-CKGE/tree/main