A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning
By: Zhiyu Zhang , Wei Chen , Youfang Lin and more
Potential Business Impact:
Helps computers remember old facts without forgetting new ones.
Recent Continual Learning (CL)-based Temporal Knowledge Graph Reasoning (TKGR) methods focus on significantly reducing computational cost and mitigating catastrophic forgetting caused by fine-tuning models with new data. However, existing CL-based TKGR methods still face two key limitations: (1) They usually one-sidedly reorganize individual historical facts, while overlooking the historical context essential for accurately understanding the historical semantics of these facts; (2) They preserve historical knowledge by simply replaying historical facts, while ignoring the potential conflicts between historical and emerging facts. In this paper, we propose a Deep Generative Adaptive Replay (DGAR) method, which can generate and adaptively replay historical entity distribution representations from the whole historical context. To address the first challenge, historical context prompts as sampling units are built to preserve the whole historical context information. To overcome the second challenge, a pre-trained diffusion model is adopted to generate the historical distribution. During the generation process, the common features between the historical and current distributions are enhanced under the guidance of the TKGR model. In addition, a layer-by-layer adaptive replay mechanism is designed to effectively integrate historical and current distributions. Experimental results demonstrate that DGAR significantly outperforms baselines in reasoning and mitigating forgetting.
Similar Papers
DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization
Machine Learning (CS)
Predicts future events and fills in missing history.
Research on Graph-Retrieval Augmented Generation Based on Historical Text Knowledge Graphs
Computation and Language
Helps computers understand old writings better.
Task-Aware Retrieval Augmentation for Dynamic Recommendation
Information Retrieval
Improves online suggestions by learning changing tastes.