DOT-VAE: Disentangling One Factor at a Time
- URL: http://arxiv.org/abs/2210.10920v2
- Date: Fri, 21 Oct 2022 03:30:52 GMT
- Title: DOT-VAE: Disentangling One Factor at a Time
- Authors: Vaishnavi Patil, Matthew Evanusa, Joseph JaJa
- Abstract summary: We propose a novel framework which augments the latent space of a Variational Autoencoders with a disentangled space and is trained using a Wake-Sleep-inspired two-step algorithm for unsupervised disentanglement.
Our network learns to disentangle interpretable, independent factors from the data one at a time", and encode it in different dimensions of the disentangled latent space, while making no prior assumptions about the number of factors or their joint distribution.
- Score: 1.6114012813668934
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: As we enter the era of machine learning characterized by an overabundance of
data, discovery, organization, and interpretation of the data in an
unsupervised manner becomes a critical need. One promising approach to this
endeavour is the problem of Disentanglement, which aims at learning the
underlying generative latent factors, called the factors of variation, of the
data and encoding them in disjoint latent representations. Recent advances have
made efforts to solve this problem for synthetic datasets generated by a fixed
set of independent factors of variation. Here, we propose to extend this to
real-world datasets with a countable number of factors of variations. We
propose a novel framework which augments the latent space of a Variational
Autoencoders with a disentangled space and is trained using a
Wake-Sleep-inspired two-step algorithm for unsupervised disentanglement. Our
network learns to disentangle interpretable, independent factors from the data
``one at a time", and encode it in different dimensions of the disentangled
latent space, while making no prior assumptions about the number of factors or
their joint distribution. We demonstrate its quantitative and qualitative
effectiveness by evaluating the latent representations learned on two synthetic
benchmark datasets; DSprites and 3DShapes and on a real datasets CelebA.
Related papers
- Predictive variational autoencoder for learning robust representations
of time-series data [0.0]
We propose a VAE architecture that predicts the next point in time and show that it mitigates the learning of spurious features.
We show that together these two constraints on VAEs to be smooth over time produce robust latent representations and faithfully recover latent factors on synthetic datasets.
arXiv Detail & Related papers (2023-12-12T02:06:50Z) - ProtoVAE: Prototypical Networks for Unsupervised Disentanglement [1.6114012813668934]
We introduce a novel deep generative VAE-based model, ProtoVAE, that leverages a deep metric learning Prototypical network trained using self-supervision.
Our model is completely unsupervised and requires no priori knowledge of the dataset, including the number of factors.
We evaluate our proposed model on the benchmark dSprites, 3DShapes, and MPI3D disentanglement datasets.
arXiv Detail & Related papers (2023-05-16T01:29:26Z) - Towards Causal Representation Learning and Deconfounding from Indefinite
Data [17.793702165499298]
Non-statistical data (e.g., images, text, etc.) encounters significant conflicts in terms of properties and methods with traditional causal data.
We redefine causal data from two novel perspectives and then propose three data paradigms.
We implement the above designs as a dynamic variational inference model, tailored to learn causal representation from indefinite data.
arXiv Detail & Related papers (2023-05-04T08:20:37Z) - Leveraging sparse and shared feature activations for disentangled
representation learning [112.22699167017471]
We propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation.
We validate our approach on six real world distribution shift benchmarks, and different data modalities.
arXiv Detail & Related papers (2023-04-17T01:33:24Z) - Exploring the Trade-off between Plausibility, Change Intensity and
Adversarial Power in Counterfactual Explanations using Multi-objective
Optimization [73.89239820192894]
We argue that automated counterfactual generation should regard several aspects of the produced adversarial instances.
We present a novel framework for the generation of counterfactual examples.
arXiv Detail & Related papers (2022-05-20T15:02:53Z) - Leveraging Relational Information for Learning Weakly Disentangled
Representations [11.460692362624533]
Disentanglement is a difficult property to enforce in neural representations.
We present an alternative view over learning (weakly) disentangled representations.
arXiv Detail & Related papers (2022-05-20T09:58:51Z) - Equivariance Allows Handling Multiple Nuisance Variables When Analyzing
Pooled Neuroimaging Datasets [53.34152466646884]
In this paper, we show how bringing recent results on equivariant representation learning instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution.
We demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples.
arXiv Detail & Related papers (2022-03-29T04:54:06Z) - 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) - Evidential Sparsification of Multimodal Latent Spaces in Conditional
Variational Autoencoders [63.46738617561255]
We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder.
We use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not.
Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique.
arXiv Detail & Related papers (2020-10-19T01:27:21Z) - Learning to Manipulate Individual Objects in an Image [71.55005356240761]
We describe a method to train a generative model with latent factors that are independent and localized.
This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to objects.
Unlike other unsupervised generative models, ours enables object-centric manipulation, without requiring object-level annotations.
arXiv Detail & Related papers (2020-04-11T21:50:20Z)
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.