知识图谱持续学习中的弹性权重固化：一项实证评估
Elastic Weight Consolidation for Knowledge Graph Continual Learning: An Empirical Evaluation
AI总结：
本文通过实验证明，EWC在知识图谱持续学习中有效缓解灾难性遗忘，且任务划分策略影响遗忘程度。
摘要：
知识图谱（KGs）需要持续更新以适应新信息的出现，但神经嵌入模型在连续学习新任务时会遭受灾难性遗忘。我们评估了弹性权重固化（EWC），一种基于正则化的持续学习方法，在使用TransE嵌入的FB15k-237知识图谱链接预测任务上的表现。在多个实验中使用五个随机种子，我们发现EWC将灾难性遗忘率从12.62%降低到6.85%，比朴素的顺序训练减少了45.7%。我们观察到任务划分策略影响遗忘的程度：基于关系的划分（按关系类型分组）比随机划分的任务表现出9.8个百分点更高的遗忘（12.62% vs 2.81%），这表明任务构建影响评估结果。虽然我们专注于单一嵌入模型和数据集，但我们的结果表明EWC在知识图谱持续学习中有效缓解了灾难性遗忘，并突显了评估协议设计的重要性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
