paper-with-me

Papers

Towards an Improved Metric for Evaluating Disentangled Representations

2024-10-04 · Sahib Julka, Yashu Wang, Michael Granitzer

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.

📄 PDF Abstract BibTeX arXiv:2410.03056

Code (1)

julka01/innvariant 공식 구현 pytorch

Tasks

DisentanglementRepresentation Learning

Similar Papers 제목 키워드 기반

Enriching Disentanglement: From Logical Definitions to Quantitative Metrics

2023-05-19 · Yivan Zhang, Masashi Sugiyama

Disentangling the explanatory factors in complex data is a promising approach for generalizable and data-efficient representation learning. While a variety of quantitative metrics for learning and evaluating disentangled…

DisentanglementRepresentation Learning

Geometry of Deep Generative Models for Disentangled Representations

2019-02-19 · Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand 외

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric prope…

Representation Learning

Explaining Word Embeddings via Disentangled Representation

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Keng-Te Liao, Cheng-Syuan Lee, Zhong-Yu Huang, Shou-De Lin

Disentangled representations have attracted increasing attention recently. However, how to transfer the desired properties of disentanglement to word representations is unclear. In this work, we propose to transform typi…

DisentanglementWord Embeddings

GM Score: Incorporating inter-class and intra-class generator diversity, discriminability of disentangled representation, and sample fidelity for evaluating GANs

2021-12-13 · Harshvardhan GM, Aanchal Sahu, Mahendra Kumar Gourisaria

While generative adversarial networks (GAN) are popular for their higher sample quality as opposed to other generative models like the variational autoencoders (VAE) and Boltzmann machines, they suffer from the same diff…

Diversity

Gauge theory and twins paradox of disentangled representations

2019-06-24 · X. Dong, L. Zhou

Achieving disentangled representations of information is one of the key goals of deep network based machine learning system. Recently there are more discussions on this issue. In this paper, by comparing the geometric st…

BIG-bench Machine Learning