EWC有效缓解知识图谱持续学习中的遗忘问题。
Elastic Weight Consolidation for Knowledge Graph Continual Learning: An Empirical Evaluation
- 用EWC正则化方法减少神经模型在连续学习时的灾难性遗忘
- 遗忘率从12.62%降至6.85%，降幅达45.7%
- 提醒评估设计需关注任务划分方式，否则结果易偏差
知识图谱需持续更新以融入新信息，但神经嵌入模型在顺序学习新任务时易出现灾难性遗忘。本文在FB15k-237数据集上，使用TransE嵌入对弹性权重巩固（EWC）这一正则化持续学习方法进行评估。基于五组随机种子的多轮实验表明，与直接顺序训练相比，EWC将遗忘率从12.62%降低至6.85%，降幅达45.7%。研究发现任务划分策略显著影响遗忘程度：按关系类型分组的任务导致遗忘率高达12.62%，而随机划分仅2.81%，差值达9.8个百分点，说明任务构造方式会扭曲评估结果。尽管仅针对单一嵌入模型与数据集，本研究证实EWC在知识图谱持续学习中可有效抑制遗忘，并强调评估协议设计的重要性。
原文摘要 · Abstract (English)
Knowledge graphs (KGs) require continual updates as new information emerges, but neural embedding models suffer from catastrophic forgetting when learning new tasks sequentially. We evaluate Elastic Weight Consolidation (EWC), a regularization-based continual learning method, on KG link prediction using TransE embeddings on FB15k-237. Across multiple experiments with five random seeds, we find that EWC reduces catastrophic forgetting from 12.62% to 6.85%, a 45.7% reduction compared to naive sequential training. We observe that the task partitioning strategy affects the magnitude of forgetting: relation-based partitioning (grouping triples by relation type) exhibits 9.8 percentage points higher forgetting than randomly partitioned tasks (12.62% vs 2.81%), suggesting that task construction influences evaluation outcomes. While focused on a single embedding model and dataset, our results demonstrate that EWC effectively mitigates catastrophic forgetting in KG continual learning and highlight the importance of evaluation protocol design.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。