从相似性矩阵中挖掘可解释的表示维度，提升神经与行为数据的分析能力
Similarity-based representation factorization for revealing interpretable dimensions in representational data
- 基于相似性矩阵，通过非负分解提取低维可解释表示
- 在稀疏数据下仍能恢复有意义的维度，且预测行为特征
- 适合神经科学、心理学等领域的可解释性分析
表示研究广泛存在于神经科学、心理学和人工智能等领域。尽管通常通过刺激间的相似性来研究和比较表示，但现有方法对塑造表示的维度揭示有限，且可解释性不足。为此，本文提出一种通用计算方法——相似性基础表示因子分解（SRF），从测量数据导出的相似性矩阵中恢复低维、非负、可解释的嵌入表示。在多种仿真及神经、行为和计算数据集上，SRF能从不同形式的表示数据中恢复可解释维度，即使在数据稀疏、不完整的情况下依然有效。所获维度与任务特定模型结果一致，能预测独立的行为属性，提升探索性分析效果，并在验证假设测试中提供更强统计效力，优于直接比较相似性矩阵。这些结果确立了SRF作为通用方法，在揭示、理解与利用表示底层维度方面具有广泛应用前景。
原文摘要 · Abstract (English)
The study of representations is widespread across fields, including neuroscience, psychology, and artificial intelligence. While representations are often studied and compared through similarities between stimuli, current methods provide only limited access to the dimensions that shape these representations and are often limited in interpretability. To overcome these challenges, here we introduce Similarity-Based Representation Factorization (SRF), a general computational method for recovering low-dimensional, non-negative, interpretable embeddings from similarity matrices derived from measured data. Across simulations and many neural, behavioral, and computational datasets, SRF recovers interpretable dimensions from diverse forms of representational data, even for very sparsely sampled, incomplete data. The dimensions derived from these datasets match those obtained by task-specific models, predict independent behavioral properties, improve exploratory analysis, and offer higher power for confirmatory hypothesis testing than comparing similarity matrices. Together, these results establish SRF as a general-purpose method with broad applications for uncovering, understanding, and using the dimensions underlying representations.
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。