Deep VIB is a neural-network parameterization of the information bottleneck objective trained via variational inference and the reparameterization trick, yielding improved generalization and adversarial robustness.
The variational fair autoencoder
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. Our model is based on a variational autoencoding architecture with priors that encourage independence between sensitive and latent factors of variation. Any subsequent processing, such as classification, can then be performed on this purged latent representation. To remove any remaining dependencies we incorporate an additional penalty term based on the "Maximum Mean Discrepancy" (MMD) measure. We discuss how these architectures can be efficiently trained on data and show in experiments that this method is more effective than previous work in removing unwanted sources of variation while maintaining informative latent representations.
verdicts
UNVERDICTED 4representative citing papers
Benchmark shows that combining data rebalancing with feature disentanglement mitigates shortcut learning more effectively than rebalancing alone in medical imaging models.
Dataset distillation introduces fairness gaps from subgroup pattern mismatches rather than just imbalance; distilling to a group-agnostic barycenter of predictive information reduces these gaps.
GPP trains local variational encoders in federated settings to release representations that keep utility within 1% of an autoencoder baseline while driving adversary AUC on sensitive attributes to near-random levels on MNIST, CelebA, and HAPT data.
citing papers explorer
-
Deep Variational Information Bottleneck
Deep VIB is a neural-network parameterization of the information bottleneck objective trained via variational inference and the reparameterization trick, yielding improved generalization and adversarial robustness.
-
Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
Benchmark shows that combining data rebalancing with feature disentanglement mitigates shortcut learning more effectively than rebalancing alone in medical imaging models.
-
Fair Dataset Distillation via Cross-Group Barycenter Alignment
Dataset distillation introduces fairness gaps from subgroup pattern mismatches rather than just imbalance; distilling to a group-agnostic barycenter of predictive information reduces these gaps.
-
Distributed Deep Variational Approach for Privacy-preserving Data Release
GPP trains local variational encoders in federated settings to release representations that keep utility within 1% of an autoencoder baseline while driving adversary AUC on sensitive attributes to near-random levels on MNIST, CelebA, and HAPT data.