CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement

• URL: http://arxiv.org/abs/2503.07938v1
• Date: Tue, 11 Mar 2025 00:32:56 GMT
• Title: CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement
• Authors: Chenrui Ma, Rongchang Zhao, Xi Xiao, Hongyang Xie, Tianyang Wang, Xiao Wang, Hao Zhang, Yanning Shen,
• Abstract summary: Deep generative models may inherit or amplify biases and fairness issues by encoding sensitive attributes alongside predictive features.<n>We propose CAD-VAE (Correlation-Aware Disentangled VAE), which introduces a correlated latent code to capture the shared information between target and sensitive attributes.<n>Experiments on benchmark datasets demonstrate that CAD-VAE produces fairer representations, realistic counterfactuals, and improved fairness-aware image editing.
• Score: 24.818829983471765
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While deep generative models have significantly advanced representation learning, they may inherit or amplify biases and fairness issues by encoding sensitive attributes alongside predictive features. Enforcing strict independence in disentanglement is often unrealistic when target and sensitive factors are naturally correlated. To address this challenge, we propose CAD-VAE (Correlation-Aware Disentangled VAE), which introduces a correlated latent code to capture the shared information between target and sensitive attributes. Given this correlated latent, our method effectively separates overlapping factors without extra domain knowledge by directly minimizing the conditional mutual information between target and sensitive codes. A relevance-driven optimization strategy refines the correlated code by efficiently capturing essential correlated features and eliminating redundancy. Extensive experiments on benchmark datasets demonstrate that CAD-VAE produces fairer representations, realistic counterfactuals, and improved fairness-aware image editing.

Related papers

• Enhancing Graph Contrastive Learning with Reliable and Informative Augmentation for Recommendation [84.45144851024257]
  We propose a novel framework that aims to enhance graph contrastive learning by constructing contrastive views with stronger collaborative information via discrete codes. The core idea is to map users and items into discrete codes rich in collaborative information for reliable and informative contrastive view generation.
  arXiv  Detail & Related papers  (2024-09-09T14:04:17Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning [49.60634126342945]
  Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Recent research reveals that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information. We employ contrastive learning to promote global feature alignment in addition to learning counterfactual clues.
  arXiv  Detail & Related papers  (2024-06-09T07:29:55Z)
• A Sequentially Fair Mechanism for Multiple Sensitive Attributes [0.46040036610482665]
  In the standard use case of Algorithmic Fairness, the goal is to eliminate the relationship between a sensitive variable and a corresponding score. We propose a sequential framework, which allows to progressively achieve fairness across a set of sensitive features. Our approach seamlessly extends to approximate fairness, enveloping a framework accommodating the trade-off between risk and unfairness.
  arXiv  Detail & Related papers  (2023-09-12T22:31:57Z)
• A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition [10.821982414387525]
  We show that current methods can actually suffer in generalizing such fitted attributes interdependencies onto scenes or identities off the dataset distribution. To render models robust in realistic scenes, we propose the attributes-disentangled feature learning to ensure the recognition of an attribute not inferring on the existence of others.
  arXiv  Detail & Related papers  (2023-07-28T01:34:55Z)
• Conditional Mutual Information for Disentangled Representations in Reinforcement Learning [13.450394764597663]
  Reinforcement Learning environments can produce training data with spurious correlations between features. Disentangled representations can improve robustness, but existing disentanglement techniques that minimise mutual information between features require independent features. We propose an auxiliary task for RL algorithms that learns a disentangled representation of high-dimensional observations with correlated features.
  arXiv  Detail & Related papers  (2023-05-23T14:56:19Z)
• Contrastive Learning with Consistent Representations [8.364383223740097]
  This paper proposes Contrastive Learning with Consistent Representations CoCor. At the heart of CoCor is a novel consistency metric termed DA consistency. Experimental results demonstrate that CoCor notably enhances the generalizability and transferability of learned representations.
  arXiv  Detail & Related papers  (2023-02-03T04:34:00Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)
• Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning [64.78972193105443]
  This paper presents a novel AE detection framework, named trustworthy for predictions. performs the detection by distinguishing the AE's abnormal relation with its augmented versions. An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label.
  arXiv  Detail & Related papers  (2022-08-31T08:18:44Z)
• Fairness without the sensitive attribute via Causal Variational Autoencoder [17.675997789073907]
  Due to privacy purposes and var-ious regulations such as RGPD in EU, many personal sensitive attributes are frequently not collected. By leveraging recent developments for approximate inference, we propose an approach to fill this gap. Based on a causal graph, we rely on a new variational auto-encoding based framework named SRCVAE to infer a sensitive information proxy.
  arXiv  Detail & Related papers  (2021-09-10T17:12:52Z)
• InteL-VAEs: Adding Inductive Biases to Variational Auto-Encoders via Intermediary Latents [60.785317191131284]
  We introduce a simple and effective method for learning VAEs with controllable biases by using an intermediary set of latent variables. In particular, it allows us to impose desired properties like sparsity or clustering on learned representations. We show that this, in turn, allows InteL-VAEs to learn both better generative models and representations.
  arXiv  Detail & Related papers  (2021-06-25T16:34:05Z)
• Decomposed Adversarial Learned Inference [118.27187231452852]
  We propose a novel approach, Decomposed Adversarial Learned Inference (DALI) DALI explicitly matches prior and conditional distributions in both data and code spaces. We validate the effectiveness of DALI on the MNIST, CIFAR-10, and CelebA datasets.
  arXiv  Detail & Related papers  (2020-04-21T20:00:35Z)

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.