Related papers: Enforcing Conditional Independence for Fair Repres…

Recent advancements in image synthesis have enabled high-quality image generation and manipulation. Most works focus on: 1) conditional manipulation, where an image is modified conditioned on a given attribute, or 2) disentangled…

The deployment of generative AI (GenAI) models raises significant fairness concerns, addressed in this paper through novel characterization and enforcement techniques specific to GenAI. Unlike standard AI performing specific tasks, GenAI's…

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on…

We consider constraint-based methods for causal structure learning, such as the PC-, FCI-, RFCI- and CCD- algorithms (Spirtes et al. (2000, 1993), Richardson (1996), Colombo et al. (2012), Claassen et al. (2013)). The first step of all…

Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a…

Testing for conditional independence is a core aspect of constraint-based causal discovery. Although commonly used tests are perfect in theory, they often fail to reject independence in practice, especially when conditioning on multiple…

Contrastive Learning has shown impressive results on natural and medical images, without requiring annotated data. However, a particularity of medical images is the availability of meta-data (such as age or sex) that can be exploited for…

Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms…

Conditional selective inference (SI) has been actively studied as a new statistical inference framework for data-driven hypotheses. The basic idea of conditional SI is to make inferences conditional on the selection event characterized by a…

Most existing works on disentangled representation learning are solely built upon an marginal independence assumption: all factors in disentangled representations should be statistically independent. This assumption is necessary but…

The problem of measuring conditional dependence between two random phenomena arises when a third one (a confounder) has a potential influence on the amount of information between them. A typical issue in this challenging problem is the…

Conditional image generation is effective for diverse tasks including training data synthesis for learning-based computer vision. However, despite the recent advances in generative adversarial networks (GANs), it is still a challenging task…

We study a class of determinantal ideals that are related to conditional independence (CI) statements with hidden variables. Such CI statements correspond to determinantal conditions on a matrix whose entries are probabilities of events…

We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often…

We study the problem of performing classification in a manner that is fair for sensitive groups, such as race and gender. This problem is tackled through the lens of disentangled and locally fair representations. We learn a locally fair…

Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness into an opportunity: one can take advantage of distribution…

A decision can be defined as fair if equal individuals are treated equally and unequals unequally. Adopting this definition, the task of designing machine learning (ML) models that mitigate unfairness in automated decision-making systems…

Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g., women and men) remains an open challenge. We propose an approach that extends the use of the Wasserstein…

Fairness in machine learning has become a critical concern. Existing approaches often focus on achieving full fairness across all score ranges generated by predictive models, ensuring fairness in both high- and low-percentile populations.…

We study the data-driven selection of causal graphical models using constraint-based algorithms, which determine the existence or non-existence of edges (causal connections) in a graph based on testing a series of conditional independence…