Related papers: Factored Classifier-Free Guidance
The reliance of text classifiers on spurious correlations can lead to poor generalization at deployment, raising concerns about their use in safety-critical domains such as healthcare. In this work, we propose to use counterfactual data…
Counterfactual explanations (CFE) for deep image classifiers aim to reveal how minimal input changes lead to different model decisions, providing critical insights for model interpretation and improvement. However, existing CFE methods…
Counterfactual explanations aim to enhance model transparency by showing how inputs can be minimally altered to change predictions. For multivariate time series, existing methods often generate counterfactuals that are invalid, implausible,…
Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However,…
Adding additional control to pretrained diffusion models has become an increasingly popular research area, with extensive applications in computer vision, reinforcement learning, and AI for science. Recently, several studies have proposed…
We study counterfactual identifiability in causal models with bijective generation mechanisms (BGM), a class that generalizes several widely-used causal models in the literature. We establish their counterfactual identifiability for three…
Fairness in machine learning research has largely focused on outcome-oriented fairness criteria such as Equalized Odds, while comparatively less attention has been given to procedural-oriented fairness, which addresses how a model arrives…
Negative guidance -- explicitly suppressing unwanted attributes -- remains a fundamental challenge in diffusion models, particularly in few-step sampling regimes. While Classifier-Free Guidance (CFG) works well in standard settings, it…
Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion process by gradients…
We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals…
Generative diffusion models show promise for data augmentation. However, applying them to fine-grained tasks presents a significant challenge: ensuring synthetic images accurately capture the subtle, category-defining features critical for…
We introduce Policy Gradient Guidance (PGG), a simple extension of classifier-free guidance from diffusion models to classical policy gradient methods. PGG augments the policy gradient with an unconditional branch and interpolates…
Counterfactual explanations (CFs) offer human-centric insights into machine learning predictions by highlighting minimal changes required to alter an outcome. Therefore, CFs can be used as (i) interventions for abnormality prevention and…
Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…
Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions. For CEs to be useful, it is important that they are easy for users to interpret. Existing methods for…
Counterfactual medical image generation enables clinicians to explore clinical hypotheses, such as predicting disease progression, facilitating their decision-making. While existing methods can generate visually plausible images from…
Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences,…
Foundation models, despite their robust zero-shot capabilities, remain vulnerable to spurious correlations and 'Clever Hans' strategies. Existing mitigation methods often rely on unavailable group labels or computationally expensive…
The use of machine learning models in high-stake applications (e.g., healthcare, lending, college admission) has raised growing concerns due to potential biases against protected social groups. Various fairness notions and methods have been…
Machine learning models are increasingly used in critical areas such as loan approvals and hiring, yet they often function as black boxes, obscuring their decision-making processes. Transparency is crucial, as individuals need explanations…