提出新度量标准EDI，更稳定地评估表征解耦效果。
Towards an Improved Metric for Evaluating Disentangled Representations
- 基于因子-代码关系的独占性设计新度量方法
- 在模块化、紧凑性等维度上表现更稳定
- 适合需要可靠评估解耦表示的研究者
解耦表示学习对提升表征的可控性、可解释性和可迁移性至关重要。然而，如何获得可靠且一致的定量解耦度量仍是重大挑战，源于不同度量衡量不同性质以及设计带来的潜在偏差。本文全面分析了现有主流解耦评估指标，从模块化、紧凑性、显式性、因子-代码关系检测及解耦程度描述等方面进行比较。提出一种新框架与度量方法（简称EDI），基于‘独占性’概念改进因子-代码关系建模，减少人为判断。深入分析表明，EDI能有效衡量核心属性，且相比现有方法更具稳定性，建议作为标准化评估手段推广使用。
原文摘要 · Abstract (English)
Disentangled representation learning plays a pivotal role in making representations controllable, interpretable and transferable. Despite its significance in the domain, the quest for reliable and consistent quantitative disentanglement metric remains a major challenge. This stems from the utilisation of diverse metrics measuring different properties and the potential bias introduced by their design. Our work undertakes a comprehensive examination of existing popular disentanglement evaluation metrics, comparing them in terms of measuring aspects of disentanglement (viz. Modularity, Compactness, and Explicitness), detecting the factor-code relationship, and describing the degree of disentanglement. We propose a new framework for quantifying disentanglement, introducing a metric entitled \emph{EDI}, that leverages the intuitive concept of \emph{exclusivity} and improved factor-code relationship to minimize ad-hoc decisions. An in-depth analysis reveals that EDI measures essential properties while offering more stability than existing metrics, advocating for its adoption as a standardised approach.
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。