arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.01759cs.AI
收藏

从潜隐到明晰:利用 KGEPrisma 将知识图谱嵌入转化为可解释结构

From Latent to Lucid: Transforming Knowledge Graph Embeddings into Interpretable Structures with KGEPrisma

Sony AI Barcelona(索尼巴塞罗那人工智能实验室);Cognitive Systems Group, University of Bamberg(巴姆伯格大学认知系统组)

Christoph Wehner, Chrysa Iliopoulou, Ute Schmid, Tarek R. Besold

AI总结:

本文提出 KGEPrisma,一种针对知识图谱嵌入模型的事后局部可解释方法,通过直接解码潜隐表示并利用嵌入平滑性提取符号规则与事实,无需重训练即可生成忠实解释,提升模型透明度。

摘要:

在本文中,我们提出了一种针对知识图谱嵌入(KGE)模型的事后、局部可解释人工智能方法。这些模型对知识图谱补全至关重要,但因其不透明的黑箱特性而受到批评。尽管它们通过高维潜隐表示在捕捉知识图谱语义方面取得了显著成功,但其固有的复杂性给可解释性带来了巨大挑战。现有方法(如 Kelpie)使用资源密集型的扰动来解释 KGE 模型,而我们的方法直接解码 KGE 模型编码的潜隐表示,利用嵌入的平滑性,这一平滑性遵循如下原则:相似的嵌入反映知识图谱中相似的行为,即节点之所以被相似地嵌入,是因为它们的图邻域看起来相似。这一原则通常被称为平滑性。通过在相似嵌入实体的子图邻域内识别以三元组形式存在的符号结构,我们的方法识别出模型所依赖的统计规律,并将这些洞见转化为人类可理解的符号规则和事实。这弥合了 KGE 模型的抽象表示与其预测输出之间的差距,提供了清晰、可解释的洞见。主要贡献包括:一种新颖的针对 KGE 模型的事后、局部可解释人工智能方法,无需重新训练即可提供即时、忠实的解释,有助于在大规模知识图谱上进行实时应用。该方法的灵活性使得能够生成基于规则、基于实例和基于类比的解释,满足多样化的用户需求。大量评估表明,我们的方法在提供忠实且局部化良好的解释方面具有有效性,增强了 KGE 模型的透明度和可信度。

英文摘要:

In this paper, we introduce a post-hoc and local explainable AI method tailored for Knowledge Graph Embedding (KGE) models. These models are essential to Knowledge Graph Completion yet criticized for their opaque, black-box nature. Despite their significant success in capturing the semantics of knowledge graphs through high-dimensional latent representations, their inherent complexity poses substantial challenges to explainability. While existing methods like Kelpie use resource-intensive perturbation to explain KGE models, our approach directly decodes the latent representations encoded by KGE models, leveraging the smoothness of the embeddings, which follows the principle that similar embeddings reflect similar behaviours within the Knowledge Graph, meaning that nodes are similarly embedded because their graph neighbourhood looks similar. This principle is commonly referred to as smoothness. By identifying symbolic structures, in the form of triples, within the subgraph neighborhoods of similarly embedded entities, our method identifies the statistical regularities on which the models rely and translates these insights into human-understandable symbolic rules and facts. This bridges the gap between the abstract representations of KGE models and their predictive outputs, offering clear, interpretable insights. Key contributions include a novel post-hoc and local explainable AI method for KGE models that provides immediate, faithful explanations without retraining, facilitating real-time application on large-scale knowledge graphs. The method's flexibility enables the generation of rule-based, instance-based, and analogy-based explanations, meeting diverse user needs. Extensive evaluations show the effectiveness of our approach in delivering faithful and well-localized explanations, enhancing the transparency and trustworthiness of KGE models.

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。

↑