Protect Before Generate: Error Correcting Codes within Discrete Deep Generative Models
- URL: http://arxiv.org/abs/2410.07840v1
- Date: Thu, 10 Oct 2024 11:59:58 GMT
- Title: Protect Before Generate: Error Correcting Codes within Discrete Deep Generative Models
- Authors: María Martínez-García, Grace Villacrés, David Mitchell, Pablo M. Olmos,
- Abstract summary: We introduce a novel method that enhances variational inference in discrete latent variable models.
We leverage Error Correcting Codes (ECCs) to introduce redundancy in the latent representations.
This redundancy is then exploited by the variational posterior to yield more accurate estimates.
- Score: 3.053842954605396
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite significant advancements in deep probabilistic models, learning low-dimensional discrete latent representations remains a challenging task. In this paper, we introduce a novel method that enhances variational inference in discrete latent variable models by leveraging Error Correcting Codes (ECCs) to introduce redundancy in the latent representations. This redundancy is then exploited by the variational posterior to yield more accurate estimates, thereby narrowing the variational gap. Inspired by ECCs commonly used in digital communications and data storage, we demonstrate proof-of-concept using a Discrete Variational Autoencoder (DVAE) with binary latent variables and block repetition codes. We further extend this idea to a hierarchical structure based on polar codes, where certain latent bits are more robustly protected. Our method improves generation quality, data reconstruction, and uncertainty calibration compared to the uncoded DVAE, even when trained with tighter bounds such as the Importance Weighted Autoencoder (IWAE) objective. In particular, we demonstrate superior performance on MNIST, FMNIST, CIFAR10, and Tiny ImageNet datasets. The general approach of integrating ECCs into variational inference is compatible with existing techniques to boost variational inference, such as importance sampling or Hamiltonian Monte Carlo. We also outline the key properties ECCs must have to effectively enhance discrete variational inference.
Related papers
- Variational Encoder-Decoders for Learning Latent Representations of Physical Systems [0.0]
We present a framework for learning data-driven low-dimensional representations of a physical system.
We successfully model the hydraulic pressure response at observation wells of a groundwater flow model.
arXiv Detail & Related papers (2024-12-06T16:46:48Z) - Uncertainty in latent representations of variational autoencoders optimized for visual tasks [3.9504737666460037]
We investigate the properties of inference in Variational Autoencoders (VAEs)
We draw inspiration from classical computer vision to introduce an inductive bias into the VAE.
We find that restored inference capabilities are delivered by developing a motif in the inference network.
arXiv Detail & Related papers (2024-04-23T16:26:29Z) - 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) - Enhancing Multiple Reliability Measures via Nuisance-extended
Information Bottleneck [77.37409441129995]
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition.
We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training.
We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
arXiv Detail & Related papers (2023-03-24T16:03:21Z) - Regularizing Variational Autoencoder with Diversity and Uncertainty
Awareness [61.827054365139645]
Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference.
We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
arXiv Detail & Related papers (2021-10-24T07:58:13Z) - Unsupervised Controllable Generation with Self-Training [90.04287577605723]
controllable generation with GANs remains a challenging research problem.
We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training.
Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
arXiv Detail & Related papers (2020-07-17T21:50:35Z) - Unlabelled Data Improves Bayesian Uncertainty Calibration under
Covariate Shift [100.52588638477862]
We develop an approximate Bayesian inference scheme based on posterior regularisation.
We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
arXiv Detail & Related papers (2020-06-26T13:50:19Z) - Improve Variational Autoencoder for Text Generationwith Discrete Latent
Bottleneck [52.08901549360262]
Variational autoencoders (VAEs) are essential tools in end-to-end representation learning.
VAEs tend to ignore latent variables with a strong auto-regressive decoder.
We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
arXiv Detail & Related papers (2020-04-22T14:41:37Z) - Deterministic Decoding for Discrete Data in Variational Autoencoders [5.254093731341154]
We study a VAE model with a deterministic decoder (DD-VAE) for sequential data that selects the highest-scoring tokens instead of sampling.
We demonstrate the performance of DD-VAE on multiple datasets, including molecular generation and optimization problems.
arXiv Detail & Related papers (2020-03-04T16:36:52Z)
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.