L@bISEN, LSL Team, Yncrea Ouest, 29200 Brest, France.
Generix Group, 75012 Paris, France.
Sensors (Basel). 2023 Feb 20;23(4):2362. doi: 10.3390/s23042362.
In recent years, the rapid development of deep learning approaches has paved the way to explore the underlying factors that explain the data. In particular, several methods have been proposed to learn to identify and disentangle these underlying explanatory factors in order to improve the learning process and model generalization. However, extracting this representation with little or no supervision remains a key challenge in machine learning. In this paper, we provide a theoretical outlook on recent advances in the field of unsupervised representation learning with a focus on auto-encoding-based approaches and on the most well-known supervised disentanglement metrics. We cover the current state-of-the-art methods for learning disentangled representation in an unsupervised manner while pointing out the connection between each method and its added value on disentanglement. Further, we discuss how to quantify disentanglement and present an in-depth analysis of associated metrics. We conclude by carrying out a comparative evaluation of these metrics according to three criteria, (i) modularity, (ii) compactness and (iii) informativeness. Finally, we show that only the Mutual Information Gap score (MIG) meets all three criteria.
近年来，深度学习方法的快速发展为探索解释数据的潜在因素铺平了道路。特别是，已经提出了几种方法来学习识别和分解这些潜在的解释因素，以提高学习过程和模型的泛化能力。然而，在没有监督的情况下提取这种表示仍然是机器学习中的一个关键挑战。在本文中，我们提供了一个关于无监督表示学习领域的最新进展的理论观点，重点是基于自动编码的方法和最著名的监督解缠度量标准。我们涵盖了当前最先进的无监督学习方法，同时指出了每种方法及其在解缠方面的附加值之间的联系。此外，我们还讨论了如何量化解缠，并对相关度量标准进行了深入分析。最后，我们根据三个标准（i）模块性、（ii）紧凑性和（iii）信息量对这些度量标准进行了比较评估。最后，我们表明只有互信息差距得分（MIG）满足所有三个标准。
