Interpreting Equivariant Representations
- URL: http://arxiv.org/abs/2401.12588v1
- Date: Tue, 23 Jan 2024 09:43:30 GMT
- Title: Interpreting Equivariant Representations
- Authors: Andreas Abildtrup Hansen, Anna Calissano, Aasa Feragen
- Abstract summary: In this paper, we demonstrate that the inductive bias imposed on the by an equivariant model must also be taken into account when using latent representations.
We show how not accounting for the inductive biases leads to decreased performance on downstream tasks, and vice versa.
- Score: 5.325297567945828
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Latent representations are used extensively for downstream tasks, such as
visualization, interpolation or feature extraction of deep learning models.
Invariant and equivariant neural networks are powerful and well-established
models for enforcing inductive biases. In this paper, we demonstrate that the
inductive bias imposed on the by an equivariant model must also be taken into
account when using latent representations. We show how not accounting for the
inductive biases leads to decreased performance on downstream tasks, and vice
versa, how accounting for inductive biases can be done effectively by using an
invariant projection of the latent representations. We propose principles for
how to choose such a projection, and show the impact of using these principles
in two common examples: First, we study a permutation equivariant variational
auto-encoder trained for molecule graph generation; here we show that invariant
projections can be designed that incur no loss of information in the resulting
invariant representation. Next, we study a rotation-equivariant representation
used for image classification. Here, we illustrate how random invariant
projections can be used to obtain an invariant representation with a high
degree of retained information. In both cases, the analysis of invariant latent
representations proves superior to their equivariant counterparts. Finally, we
illustrate that the phenomena documented here for equivariant neural networks
have counterparts in standard neural networks where invariance is encouraged
via augmentation. Thus, while these ambiguities may be known by experienced
developers of equivariant models, we make both the knowledge as well as
effective tools to handle the ambiguities available to the broader community.
Related papers
- Unsupervised Representation Learning from Sparse Transformation Analysis [79.94858534887801]
We propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components.
Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model.
arXiv Detail & Related papers (2024-10-07T23:53:25Z) - Learning Disentangled Discrete Representations [22.5004558029479]
We show the relationship between discrete latent spaces and disentangled representations by replacing the standard Gaussian variational autoencoder with a tailored categorical variational autoencoder.
We provide both analytical and empirical findings that demonstrate the advantages of discrete VAEs for learning disentangled representations.
arXiv Detail & Related papers (2023-07-26T12:29:58Z) - Domain Generalization In Robust Invariant Representation [10.132611239890345]
In this paper, we investigate the generalization of invariant representations on out-of-distribution data.
We show that the invariant model learns unstructured latent representations that are robust to distribution shifts.
arXiv Detail & Related papers (2023-04-07T00:58:30Z) - Self-Supervised Learning for Group Equivariant Neural Networks [75.62232699377877]
Group equivariant neural networks are the models whose structure is restricted to commute with the transformations on the input.
We propose two concepts for self-supervised tasks: equivariant pretext labels and invariant contrastive loss.
Experiments on standard image recognition benchmarks demonstrate that the equivariant neural networks exploit the proposed self-supervised tasks.
arXiv Detail & Related papers (2023-03-08T08:11:26Z) - Posterior Collapse and Latent Variable Non-identifiability [54.842098835445]
We propose a class of latent-identifiable variational autoencoders, deep generative models which enforce identifiability without sacrificing flexibility.
Across synthetic and real datasets, latent-identifiable variational autoencoders outperform existing methods in mitigating posterior collapse and providing meaningful representations of the data.
arXiv Detail & Related papers (2023-01-02T06:16:56Z) - PAC Generalization via Invariant Representations [41.02828564338047]
We consider the notion of $epsilon$-approximate invariance in a finite sample setting.
Inspired by PAC learning, we obtain finite-sample out-of-distribution generalization guarantees.
Our results show bounds that do not scale in ambient dimension when intervention sites are restricted to lie in a constant size subset of in-degree bounded nodes.
arXiv Detail & Related papers (2022-05-30T15:50:14Z) - Equivariance Discovery by Learned Parameter-Sharing [153.41877129746223]
We study how to discover interpretable equivariances from data.
Specifically, we formulate this discovery process as an optimization problem over a model's parameter-sharing schemes.
Also, we theoretically analyze the method for Gaussian data and provide a bound on the mean squared gap between the studied discovery scheme and the oracle scheme.
arXiv Detail & Related papers (2022-04-07T17:59:19Z) - Topographic VAEs learn Equivariant Capsules [84.33745072274942]
We introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables.
We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST.
We demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.
arXiv Detail & Related papers (2021-09-03T09:25:57Z) - 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)
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.