NashAE: Disentangling Representations through Adversarial Covariance
Minimization
- URL: http://arxiv.org/abs/2209.10677v1
- Date: Wed, 21 Sep 2022 22:02:26 GMT
- Title: NashAE: Disentangling Representations through Adversarial Covariance
Minimization
- Authors: Eric Yeats, Frank Liu, David Womble, Hai Li
- Abstract summary: We present a self-supervised method to disentangle factors of variation in high-dimensional data that does not rely on prior knowledge of the underlying variation profile.
We show that NashAE has increased reliability and increased capacity to capture salient data characteristics in the learned latent representation.
- Score: 8.22507807169023
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present a self-supervised method to disentangle factors of variation in
high-dimensional data that does not rely on prior knowledge of the underlying
variation profile (e.g., no assumptions on the number or distribution of the
individual latent variables to be extracted). In this method which we call
NashAE, high-dimensional feature disentanglement is accomplished in the
low-dimensional latent space of a standard autoencoder (AE) by promoting the
discrepancy between each encoding element and information of the element
recovered from all other encoding elements. Disentanglement is promoted
efficiently by framing this as a minmax game between the AE and an ensemble of
regression networks which each provide an estimate of an element conditioned on
an observation of all other elements. We quantitatively compare our approach
with leading disentanglement methods using existing disentanglement metrics.
Furthermore, we show that NashAE has increased reliability and increased
capacity to capture salient data characteristics in the learned latent
representation.
Related papers
- A Unifying Information-theoretic Perspective on Evaluating Generative Models [5.524685807042777]
Several recent approaches utilize "precision" and "recall," borrowed from the classification domain, to individually quantify the output fidelity (realism) and output diversity (representation of the real data variation)
We unify a class of kth-nearest-neighbors (kNN)-based metrics under an information-theoretic lens using approaches from kNN density estimation.
We propose a tri-dimensional metric composed of Precision Cross-Entropy (PCE), Recall Cross-Entropy (RCE), and Recall Entropy (RE)
arXiv Detail & Related papers (2024-12-18T21:17:02Z) - Unpicking Data at the Seams: Understanding Disentanglement in VAEs [5.05828899601167]
Disentanglement, or identifying statistically independent factors of the data, is relevant to much of machine learning.
Disentanglement arises in several generative paradigms including Variational Autoencoders (VAEs), Generative Adversarial Networks and diffusion models.
arXiv Detail & Related papers (2024-10-29T21:54:18Z) - Disentanglement with Factor Quantized Variational Autoencoders [11.086500036180222]
We propose a discrete variational autoencoder (VAE) based model where the ground truth information about the generative factors are not provided to the model.
We demonstrate the advantages of learning discrete representations over learning continuous representations in facilitating disentanglement.
Our method called FactorQVAE combines optimization based disentanglement approaches with discrete representation learning.
arXiv Detail & Related papers (2024-09-23T09:33:53Z) - Hodge-Aware Contrastive Learning [101.56637264703058]
Simplicial complexes prove effective in modeling data with multiway dependencies.
We develop a contrastive self-supervised learning approach for processing simplicial data.
arXiv Detail & Related papers (2023-09-14T00:40:07Z) - Disentanglement via Latent Quantization [60.37109712033694]
In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space.
We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
arXiv Detail & Related papers (2023-05-28T06:30:29Z) - Learning Conditional Invariance through Cycle Consistency [60.85059977904014]
We propose a novel approach to identify meaningful and independent factors of variation in a dataset.
Our method involves two separate latent subspaces for the target property and the remaining input information.
We demonstrate on synthetic and molecular data that our approach identifies more meaningful factors which lead to sparser and more interpretable models.
arXiv Detail & Related papers (2021-11-25T17:33:12Z) - Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic
Uncertainty [58.144520501201995]
Bi-Lipschitz regularization of neural network layers preserve relative distances between data instances in the feature spaces of each layer.
With the use of an attentive set encoder, we propose to meta learn either diagonal or diagonal plus low-rank factors to efficiently construct task specific covariance matrices.
We also propose an inference procedure which utilizes scaled energy to achieve a final predictive distribution.
arXiv Detail & Related papers (2021-10-12T22:04:19Z) - Identifiable Energy-based Representations: An Application to Estimating
Heterogeneous Causal Effects [83.66276516095665]
Conditional average treatment effects (CATEs) allow us to understand the effect heterogeneity across a large population of individuals.
Typical CATE learners assume all confounding variables are measured in order for the CATE to be identifiable.
We propose an energy-based model (EBM) that learns a low-dimensional representation of the variables by employing a noise contrastive loss function.
arXiv Detail & Related papers (2021-08-06T10:39:49Z) - Closed-Form Factorization of Latent Semantics in GANs [65.42778970898534]
A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images.
In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner.
We propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
arXiv Detail & Related papers (2020-07-13T18:05:36Z) - Learning Flat Latent Manifolds with VAEs [16.725880610265378]
We propose an extension to the framework of variational auto-encoders, where the Euclidean metric is a proxy for the similarity between data points.
We replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one.
We evaluate our method on a range of data-sets, including a video-tracking benchmark.
arXiv Detail & Related papers (2020-02-12T09:54:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.