Related papers: Inference-Time Selective Debiasing to Enhance Fair…

As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with…

Image classifiers often rely overly on peripheral attributes that have a strong correlation with the target class (i.e., dataset bias) when making predictions. Due to the dataset bias, the model correctly classifies data samples including…

Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance gains. However, recent studies have demonstrated the existence…

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

Traditional approaches to learning fair machine learning models often require rebuilding models from scratch, typically without considering potentially existing models. In a context where models need to be retrained frequently, this can…

Image generative models, particularly diffusion-based models, have surged in popularity due to their remarkable ability to synthesize highly realistic images. However, since these models are data-driven, they inherit biases from the…

Semi-supervised learning (SSL) provides an effective means of leveraging unlabelled data to improve a model performance. Even though the domain has received a considerable amount of attention in the past years, most methods present the…

In this article, we review selective inference, a set of techniques for inference when the statistical question asked is a function of the data. This setting often arises in contemporary scientific workflows, where hypotheses and parameters…

We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models. Our hypothesis is: Biased Models have Biased Explanations. To establish that, we first translate existing…

Model selection aims to identify a sufficiently well performing model that is possibly simpler than the most complex model among a pool of candidates. However, the decision-making process itself can inadvertently introduce non-negligible…

Despite significant progress, recent studies indicate that current large language models (LLMs) may still capture dataset biases and utilize them during inference, leading to the poor generalizability of LLMs. However, due to the diversity…

Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are available at training time. Similarly to inductive learning…

Text-to-image (T2I) diffusion models have achieved widespread success due to their ability to generate high-resolution, photorealistic images. These models are trained on large-scale datasets, like LAION-5B, often scraped from the internet.…

Feature selection is an important but challenging task in causal inference for obtaining unbiased estimates of causal quantities. Properly selected features in causal inference not only significantly reduce the time required to implement a…

Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech. This leads to a single estimate for each input without any guarantees or measures of…

Feature attribution methods, proposed recently, help users interpret the predictions of complex models. Our approach integrates feature attributions into the objective function to allow machine learning practitioners to incorporate priors…

Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several debiasing methods exist, they require access to the LLMs'…

We propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label. By implicitly assuming the existence of a generative model for which a…

Due to their similarity-based learning objectives, pretrained sentence encoders often internalize stereotypical assumptions that reflect the social biases that exist within their training corpora. In this paper, we describe several kinds of…

We propose a regression-based approach to removing implicit biases in representations. On tasks where the protected attribute is observed, the method is statistically more efficient than known approaches. Further, we show that this approach…