首个面向生物医学知识图谱持续学习的真实时序评估基准。
PrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs
- 基于9个权威数据库构建真实演化图谱，含10类实体、30种关系。
- 发现模型性能受解码器与持续学习策略强烈交互影响，单一方案难通用。
- 多模态特征提升任务效果最高达60%，现有框架难以处理超大规模演化数据。
生物医学知识图谱支撑药物重定位和临床决策，但其上游本体在不同周期更新，每次释放新增超580万条边，废弃近90万条。现有持续图学习研究多基于静态合成数据，无法模拟真实生物医学图谱的异步结构演化。为此，我们提出PrimeKG-CL，一个基于九个权威生物医学数据库构建的持续图学习基准（129K+节点，810万+边，10类节点，30种关系），包含两个真实时间快照（2021年6月与2023年7月），新增583万条边，移除88.9万条，保留721万条。设计了10个按实体类型分组的任务，融合多模态节点特征，并采用持久/新增/删除三类测试划分。在三项任务中评估六种持续学习策略、四种KGE解码器，以及LKGE（LLM-RAG代理）和CMKL。结果表明：解码器与学习策略间存在强交互作用，无统一最优组合；仅DistMult能清晰区分持久与过时知识，标准指标混淆知识保留与遗忘失败；多模态特征使实体级任务性能提升最高达60%；近期框架IncDE在567万三元组任务上五次尝试均失败，最大消耗达350GB内存。数据、流程、基线及分层划分已开源。
原文摘要 · Abstract (English)
Biomedical knowledge graphs underwrite drug repurposing and clinical decision support, yet the upstream ontologies they depend on update on independent cycles that add millions of edges and deprecate hundreds of thousands more between releases. Yet existing continual graph learning has been studied almost exclusively on synthetic random splits of static, generic KGs, a regime that cannot reproduce the asynchronous, structured evolution real biomedical KGs undergo. To this end, we introduce PrimeKG-CL, a CGL benchmark built from nine authoritative biomedical databases (129K+ nodes, 8.1M+ edges, 10 node types, 30 relation types) with two genuine temporal snapshots (June 2021, July 2023; 5.83M edges added, 889K removed, 7.21M persistent), 10 entity-type-grouped tasks, multimodal node features, and a per-task persistent/added/removed test stratification. On three tasks (biomedical relationship prediction, entity classification, KGQA), we evaluate six CL strategies across four KGE decoders, plus LKGE, an LLM-RAG agent, and CMKL. We find that decoder choice and continual learning strategy interact strongly: no single strategy performs best across all decoders, and mismatched combinations can significantly degrade performance. Moreover, only DistMult exhibits a clear separation between persistent and deprecated knowledge, indicating that standard metrics conflate retention of still-valid facts with failure to forget outdated ones; this effect is absent under RotatE. In addition, multimodal features improve entity-level tasks by up to 60%, and a recent CKGE framework (IncDE) failed to scale to our 5.67M-triple base task across five attempts up to 350GB RAM. Data, pipeline, baselines, and the stratified split are released openly. Dataset:huggingface.co/datasets/yradwan147/PrimeKGCL|Code:github.com/yradwan147/primekg-cl-neurips2026
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。