Disentangling Latent Factors of Variational Auto-encoder with Whitening

Hahn, Sangchul; Choi, Heeyoul

doi:10.1007/978-3-030-30508-6_47

Cited by 6 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, it would be interesting to investigate fine-grained control of solution redundancy across containers, to reduce or dynamically tune their number. In a future paper, we will describe how another post-processing operation commonly used in Machine Learning known as "whitening" [23,27] could be used to further decorrelate the FD space and reduce the number of redundancies.…”

Section: Discussionmentioning

confidence: 99%

Ensemble Feature Extraction for Multi-Container Quality-Diversity Algorithms

Cazenille

2021

Preprint

View full text Add to dashboard Cite

Quality-Diversity algorithms search for large collections of diverse and high-performing solutions, rather than just for a single solution like typical optimisation methods. They are specially adapted for multi-modal problems that can be solved in many different ways, such as complex reinforcement learning or robotics tasks. However, these approaches are highly dependent on the choice of feature descriptors (FDs) quantifying the similarity in behaviour of the solutions. While FDs usually needs to be hand-designed, recent studies have proposed ways to define them automatically by using feature extraction techniques, such as PCA or Auto-Encoders, to learn a representation of the problem from previously explored solutions.Here, we extend these approaches to more complex problems which cannot be efficiently explored by relying only on a single representation but require instead a set of diverse and complementary representations. We describe MC-AURORA, a Quality-Diversity approach that optimises simultaneously several collections of solutions, each with a different set of FDs, which are, in turn, defined automatically by an ensemble of modular auto-encoders. We show that this approach produces solutions that are more diverse than those produced by single-representation approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

Ensemble Feature Extraction for Multi-Container Quality-Diversity Algorithms

Cazenille

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Other examples of disentanglement algorithms include information-theoretic methods in GANs [12], latent whitening [23], covariance penalization [35], and Bayesian hyperpriors [2]. A number of techniques also utilize known groupings or discrete labels of the data [28,8,55,22].…”

Section: Latent Disentanglement In Generative Modelsmentioning

confidence: 99%

Geometric Disentanglement for Generative Latent Shape Models

Aumentado-Armstrong

Tsogkas

Jepson

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent representations of generative models. However, it remains an open problem to learn a generative model of shape that is interpretable and easily manipulated, particularly in the absence of supervised labels. In this paper, we propose an unsupervised approach to partitioning the latent space of a variational autoencoder for 3D point clouds in a natural way, using only geometric information. Our method makes use of tools from spectral differential geometry to separate intrinsic and extrinsic shape information, and then considers several hierarchical disentanglement penalties for dividing the latent space in this manner, including a novel one that penalizes the Jacobian of the latent representation of the decoded output with respect to the latent encoding. We show that the resulting representation exhibits intuitive and interpretable behavior, enabling tasks such as pose transfer and poseaware shape retrieval that cannot easily be performed by models with an entangled representation.

show abstract

“…Second, the latent sentence should not be any arbitrary sentence, but it should be a realistic sentence in that language domain. Note that in the conventional VAE models, the latent space is modeled to have an isotropic Gaussian distribution without any other regularizations on the space, even though there are several works that regularize the space to disentangle the dimensions (Higgins et al, 2017;Kim and Mnih, 2018;Hahn and Choi, 2019). If we do not address this issue, the inference model can be trained to mistranslate the monolingual input sentence focusing on easy reconstruction by the reconstruction model.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Training of Both Translation Models in the Back-Translation Framework

Heo¹,

Choi²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Semi-supervised learning algorithms in neural machine translation (NMT) have significantly improved translation quality compared to the supervised learning algorithms by using additional monolingual corpora. Among them, back-translation is a theoretically wellstructured and cutting-edge method. Given two pre-trained NMT models between source and target languages, one translates a monolingual sentence as a latent sentence, and the other reconstructs the monolingual input sentence given the latent sentence. Therefore, previous works tried to apply the variational auto-encoder's (VAE) training framework to the back-translation framework. However, the discrete property of the latent sentence made it impossible to use backpropagation in the framework. This paper proposes a categorical reparameterization trick that generates a differentiable sentence, with which we practically implement the VAE's training framework for the back-translation and train it by end-to-end backpropagation. In addition, we propose several regularization techniques that are especially advantageous to this framework. In our experiments, we demonstrate that our method makes backpropagation available through the latent sentences and improves the BLEU scores on the datasets of the WMT18 translation task.

show abstract

Disentangling Latent Factors of Variational Auto-encoder with Whitening

Cited by 6 publications

References 7 publications

Ensemble Feature Extraction for Multi-Container Quality-Diversity Algorithms

Ensemble Feature Extraction for Multi-Container Quality-Diversity Algorithms

Geometric Disentanglement for Generative Latent Shape Models

End-to-End Training of Both Translation Models in the Back-Translation Framework

Contact Info

Product

Resources

About