English
Related papers

Related papers: How to Not Measure Disentanglement

200 papers

Measuring inconsistency is viewed as an important issue related to handling inconsistencies. Good measures are supposed to satisfy a set of rational properties. However, defining sound properties is sometimes problematic. In this paper, we…

Artificial Intelligence · Computer Science 2014-06-03 Said Jabbour , Yue Ma , Badran Raddaoui , Lakhdar Sais , Yakoub Salhi

Disentangled representation learning offers useful properties such as dimension reduction and interpretability, which are essential to modern deep learning approaches. Although deep learning techniques have been widely applied to…

Machine Learning · Computer Science 2022-04-11 Sichen Zhao , Wei Shao , Jeffrey Chan , Flora D. Salim

The growing need for trustworthy machine learning has led to the blossom of interpretability research. Numerous explanation methods have been developed to serve this purpose. However, these methods are deficiently and inappropriately…

Machine Learning · Computer Science 2022-03-29 Yipei Wang , Xiaoqian Wang

The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the…

In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation…

Machine Learning · Statistics 2019-12-10 Eduardo Hugo Sanchez , Mathieu Serrurier , Mathias Ortner

Entanglement does not describe all quantum correlations and several authors have shown the need to go beyond entanglement when dealing with mixed states. Various different measures have sprung up in the literature, for a variety of reasons,…

Quantum Physics · Physics 2023-01-23 Aharon Brodutch , Kavan Modi

The definition of Linear Symmetry-Based Disentanglement (LSBD) formalizes the notion of linearly disentangled representations, but there is currently no metric to quantify LSBD. Such a metric is crucial to evaluate LSBD methods and to…

Machine Learning · Computer Science 2022-06-29 Loek Tonnaer , Luis A. Pérez Rey , Vlado Menkovski , Mike Holenderski , Jacobus W. Portegies

Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…

Machine Learning · Computer Science 2016-02-09 William Whitney

In this paper, the defining properties of a valid measure of the dependence between two random variables are reviewed and complemented with two original ones, shown to be more fundamental than other usual postulates. While other popular…

Methodology · Statistics 2019-12-03 Gery Geenens , Pierre Lafaye de Micheaux

The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we…

Machine Learning · Computer Science 2019-06-19 Francesco Locatello , Stefan Bauer , Mario Lucic , Gunnar Rätsch , Sylvain Gelly , Bernhard Schölkopf , Olivier Bachem

Nestedness is a property of interaction networks widely observed in natural mutualistic communities. Despite a widespread interest on this pattern, no general consensus exists on how to measure it. Instead, several metrics aiming at…

Physics and Society · Physics 2020-02-04 Claudia Payrato-Borras , Laura Hernandez , Yamir Moreno

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…

Computation and Language · Computer Science 2022-10-10 Pierre Colombo , Guillaume Staerman , Nathan Noiry , Pablo Piantanida

Probabilistic generative models provide a flexible and systematic framework for learning the underlying geometry of data. However, model selection in this setting is challenging, particularly when selecting for ill-defined qualities such as…

Machine Learning · Computer Science 2022-10-05 Chester Holtz , Gal Mishne , Alexander Cloninger

Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disentangled representations were found to be useful for diverse…

Distinguishability and predictability are part of complementarity relations which apply to two different kinds of interference experiments, with and without a path-detector, respectively. In [Opt. Comm. 179, 337 (2000)], Englert and Bergou…

Quantum Physics · Physics 2021-12-07 Marcos L. W. Basso , Jonas Maziero

The detection of entanglement in a bipartite state is a crucial issue in quantum information science. Based on realignment of density matrices and the vectorization of the reduced density matrices, we introduce a new set of separability…

Quantum Physics · Physics 2024-12-09 Yu Lu , Zhong-Xi Shen , Shao-Ming Fei , Zhi-Xi Wang

Employing a recently proposed separability criterion we develop analytical lower bounds for the concurrence and for the entanglement of formation of bipartite quantum systems. The separability criterion is based on a nondecomposable…

Quantum Physics · Physics 2007-05-23 Heinz-Peter Breuer

In many scientific and data-driven applications, machine learning models are increasingly used as measurement instruments, rather than merely as predictors of predefined labels. When the measurement function is learned from data, the…

Machine Learning · Computer Science 2026-01-27 Indrė Žliobaitė

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this…

Machine Learning · Computer Science 2020-10-29 Francesco Locatello , Stefan Bauer , Mario Lucic , Gunnar Rätsch , Sylvain Gelly , Bernhard Schölkopf , Olivier Bachem