Learning Conditional Invariance through Cycle Consistency
- URL: http://arxiv.org/abs/2111.13185v1
- Date: Thu, 25 Nov 2021 17:33:12 GMT
- Title: Learning Conditional Invariance through Cycle Consistency
- Authors: Maxim Samarin, Vitali Nesterov, Mario Wieser, Aleksander Wieczorek,
Sonali Parbhoo, and Volker Roth
- Abstract summary: 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.
- Score: 60.85059977904014
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Identifying meaningful and independent factors of variation in a dataset is a
challenging learning task frequently addressed by means of deep latent variable
models. This task can be viewed as learning symmetry transformations preserving
the value of a chosen property along latent dimensions. However, existing
approaches exhibit severe drawbacks in enforcing the invariance property in the
latent space. We address these shortcomings with a novel approach to cycle
consistency. Our method involves two separate latent subspaces for the target
property and the remaining input information, respectively. In order to enforce
invariance as well as sparsity in the latent space, we incorporate semantic
knowledge by using cycle consistency constraints relying on property side
information. The proposed method is based on the deep information bottleneck
and, in contrast to other approaches, allows using continuous target properties
and provides inherent model selection capabilities. We demonstrate on synthetic
and molecular data that our approach identifies more meaningful factors which
lead to sparser and more interpretable models with improved invariance
properties.
Related papers
- Flow Factorized Representation Learning [109.51947536586677]
We introduce a generative model which specifies a distinct set of latent probability paths that define different input transformations.
We show that our model achieves higher likelihoods on standard representation learning benchmarks while simultaneously being closer to approximately equivariant models.
arXiv Detail & Related papers (2023-09-22T20:15:37Z) - Towards Fair Disentangled Online Learning for Changing Environments [28.207499975916324]
We argue that changing environments in online learning can be attributed to partial changes in learned parameters that are specific to environments.
We propose a novel algorithm under the assumption that data collected at each time can be disentangled with two representations.
A novel regret is proposed in which it takes a mixed form of dynamic and static regret metrics followed by a fairness-aware long-term constraint.
arXiv Detail & Related papers (2023-05-31T19:04:16Z) - DOT-VAE: Disentangling One Factor at a Time [1.6114012813668934]
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.
arXiv Detail & Related papers (2022-10-19T22:53:02Z) - Identifiable Latent Causal Content for Domain Adaptation under Latent Covariate Shift [82.14087963690561]
Multi-source domain adaptation (MSDA) addresses the challenge of learning a label prediction function for an unlabeled target domain.
We present an intricate causal generative model by introducing latent noises across domains, along with a latent content variable and a latent style variable.
The proposed approach showcases exceptional performance and efficacy on both simulated and real-world datasets.
arXiv Detail & Related papers (2022-08-30T11:25:15Z) - Weakly Supervised Representation Learning with Sparse Perturbations [82.39171485023276]
We show that if one has weak supervision from observations generated by sparse perturbations of the latent variables, identification is achievable under unknown continuous latent distributions.
We propose a natural estimation procedure based on this theory and illustrate it on low-dimensional synthetic and image-based experiments.
arXiv Detail & Related papers (2022-06-02T15:30:07Z) - Self-Supervised Learning with Data Augmentations Provably Isolates
Content from Style [32.20957709045773]
We formulate the augmentation process as a latent variable model.
We study the identifiability of the latent representation based on pairs of views of the observations.
We introduce Causal3DIdent, a dataset of high-dimensional, visually complex images with rich causal dependencies.
arXiv Detail & Related papers (2021-06-08T18:18:09Z) - Learning Disentangled Representations with Latent Variation
Predictability [102.4163768995288]
This paper defines the variation predictability of latent disentangled representations.
Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs.
We develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations.
arXiv Detail & Related papers (2020-07-25T08:54:26Z) - 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) - NestedVAE: Isolating Common Factors via Weak Supervision [45.366986365879505]
We identify the connection between the task of bias reduction and that of isolating factors common between domains.
To isolate the common factors we combine the theory of deep latent variable models with information bottleneck theory.
Two outer VAEs with shared weights attempt to reconstruct the input and infer a latent space, whilst a nested VAE attempts to reconstruct the latent representation of one image, from the latent representation of its paired image.
arXiv Detail & Related papers (2020-02-26T15:49:57Z)
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.