用深度变分自编码器融合结构与文本，提升知识图谱补全效果。
Deep Sparse Latent Feature Models for Knowledge Graph Completion
- 基于稀疏潜在特征模型，结合图结构与文本信息
- 在四个数据集上显著优于现有方法，提升链接预测性能
- 适合关注可解释性与多模态知识补全的研究者
近年来，知识图谱补全（KGC）研究侧重于基于文本的方法以应对大规模知识图谱的复杂性。尽管取得了显著进展，这些方法往往难以充分捕捉图的全局结构特性。随机块模型（SBMs），尤其是潜在特征关系模型（LFRM），提供了强大的概率框架，用于识别潜在社区结构并改进链接预测。本文提出一种新的概率KGC框架，采用通过深度变分自编码器（VAE）优化的稀疏潜在特征模型。该方法动态融合全局聚类信息与局部文本特征，有效完成缺失三元组，同时增强对底层潜在结构的可解释性。在四个不同规模的基准数据集上的大量实验表明，该方法实现了显著的性能提升。
原文摘要 · Abstract (English)
Recent advances in knowledge graph completion (KGC) have emphasized text-based approaches to navigate the inherent complexities of large-scale knowledge graphs (KGs). While these methods have achieved notable progress, they frequently struggle to fully incorporate the global structural properties of the graph. Stochastic blockmodels (SBMs), especially the latent feature relational model (LFRM), offer robust probabilistic frameworks for identifying latent community structures and improving link prediction. This paper presents a novel probabilistic KGC framework utilizing sparse latent feature models, optimized via a deep variational autoencoder (VAE). Our proposed method dynamically integrates global clustering information with local textual features to effectively complete missing triples, while also providing enhanced interpretability of the underlying latent structures. Extensive experiments on four benchmark datasets with varying scales demonstrate the significant performance gains achieved by our method.
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。