提出新方法揭示嵌入空间中的语义结构，提升可解释性与效率。
One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces
- 构建语义场子空间SFS，保留几何结构并捕捉局部语义关系。
- SAFARI算法通过语义迁移度量发现层次化语义结构，速度提升15~30倍。
- 适用于文本、图像多模态数据，适合关注可解释性的研究者。
嵌入空间是现代AI的核心，将原始数据转化为高维向量以编码丰富语义关系。然而其内部结构仍不透明，现有方法常在语义一致性与结构规整性之间妥协，或因计算开销过高而难以应用。为此，本文提出语义场子空间（SFS），一种保持几何特性且上下文感知的表示方式，用于捕捉嵌入空间中的局部语义邻域。同时，提出SAFARI（SemAntic Field subspAce deteRmInation）算法，一种无监督、跨模态的层级语义结构发现方法，利用新提出的语义迁移度量来量化随着SFS演化时语义的变化。为保障可扩展性，设计了高效的语义迁移近似方法，替代昂贵的SVD计算，在平均误差低于0.01的前提下实现15~30倍加速。在六个真实世界文本与图像数据集上的广泛评估表明，SFS在分类任务及政治偏见检测等细微任务中均优于标准分类器，SAFARI始终能揭示可解释且泛化的语义层级。本工作构建了一个统一框架，用于结构化、分析和扩展嵌入空间中的语义理解。
原文摘要 · Abstract (English)
Embedding spaces are fundamental to modern AI, translating raw data into high-dimensional vectors that encode rich semantic relationships. Yet, their internal structures remain opaque, with existing approaches often sacrificing semantic coherence for structural regularity or incurring high computational overhead to improve interpretability. To address these challenges, we introduce the Semantic Field Subspace (SFS), a geometry-preserving, context-aware representation that captures local semantic neighborhoods within the embedding space. We also propose SAFARI (SemAntic Field subspAce deteRmInation), an unsupervised, modality-agnostic algorithm that uncovers hierarchical semantic structures using a novel metric called Semantic Shift, which quantifies how semantics evolve as SFSes evolve. To ensure scalability, we develop an efficient approximation of Semantic Shift that replaces costly SVD computations, achieving a 15~30x speedup with average errors below 0.01. Extensive evaluations across six real-world text and image datasets show that SFSes outperform standard classifiers not only in classification but also in nuanced tasks such as political bias detection, while SAFARI consistently reveals interpretable and generalizable semantic hierarchies. This work presents a unified framework for structuring, analyzing, and scaling semantic understanding in embedding spaces.
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。