FedMKGC：面向隐私保护的联邦多语言知识图谱补全
FedMKGC: Privacy-Preserving Federated Multilingual Knowledge Graph Completion
AI总结：
针对多语言知识图谱补全中原始数据传输引发的隐私问题，提出无需数据交换与实体对齐的联邦学习框架FedMKGC，通过聚合多客户端语言模型权重实现知识融合，性能媲美当前最优对齐类模型且保护隐私。
摘要：
知识图谱补全（KGC）旨在预测知识图谱（KGs）中的缺失事实，鉴于现代知识图谱仍普遍存在不完整问题，该任务至关重要。虽然在多个对齐的知识图谱上训练KGC模型可提升性能，但以往依赖知识图谱间传输原始数据的方法会引发隐私担忧。为应对这一挑战，我们提出一种全新的联邦学习框架，可在无需原始数据交换与实体对齐的前提下，隐式聚合来自多个知识图谱的知识。我们将每个知识图谱视为一个客户端，通过基于文本的知识表示学习训练本地语言模型，再由中央服务器聚合各客户端的模型权重。由于自然语言提供了通用表示形式，同一知识在不同知识图谱中具有相似的语义表示，因此聚合后的语言模型能够利用多语言知识图谱中的互补知识，且无需共享原始用户数据。在某基准数据集上开展的大量实验表明，我们的方法显著提升了多语言知识图谱的KGC效果，在无需任何标注对齐数据或原始用户数据共享的情况下，性能与当前最优的基于对齐的模型相当。我们的代码将公开发布。
英文摘要：
Knowledge graph completion (KGC) aims to predict missing facts in knowledge graphs (KGs), which is crucial as modern KGs remain largely incomplete. While training KGC models on multiple aligned KGs can improve performance, previous methods that rely on transferring raw data among KGs raise privacy concerns. To address this challenge, we propose a new federated learning framework that implicitly aggregates knowledge from multiple KGs without demanding raw data exchange and entity alignment. We treat each KG as a client that trains a local language model through textbased knowledge representation learning. A central server then aggregates the model weights from clients. As natural language provides a universal representation, the same knowledge thus has similar semantic representations across KGs. As such, the aggregated language model can leverage complementary knowledge from multilingual KGs without demanding raw user data sharing. Extensive experiments on a benchmark dataset demonstrate that our method substantially improves KGC on multilingual KGs, achieving comparable performance to state-of-the-art alignment-based models without requiring any labeled alignments or raw user data sharing. Our codes will be publicly available.
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。
