Related papers: Fair Class-Incremental Learning using Sample Weigh…
Machine learning algorithms have been increasingly deployed in critical automated decision-making systems that directly affect human lives. When these algorithms are only trained to minimize the training/test error, they could suffer from…
Understanding and removing bias from the decisions made by machine learning models is essential to avoid discrimination against unprivileged groups. Despite recent progress in algorithmic fairness, there is still no clear answer as to which…
Deep learning models frequently exploit spurious features in training data to achieve low training error, often resulting in poor generalization when faced with shifted testing distributions. To address this issue, various methods from…
In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…
Learning to Rank (LTR) is one of the most widely used machine learning applications. It is a key component in platforms with profound societal impacts, including job search, healthcare information retrieval, and social media content feeds.…
Federated Learning (FL) has emerged as a vital paradigm in modern machine learning that enables collaborative training across decentralized data sources without exchanging raw data. This approach not only addresses privacy concerns but also…
Fairness in machine learning has received considerable attention. However, most studies on fair learning focus on either supervised learning or unsupervised learning. Very few consider semi-supervised settings. Yet, in reality, most machine…
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to…
Recently, the pretrain-finetune paradigm has become a cornerstone in various deep learning areas. While in general the pre-trained model would promote both effectiveness and efficiency of downstream tasks fine-tuning, studies have shown…
Boosting algorithms enjoy strong theoretical guarantees: when weak learners maintain positive edge, AdaBoost achieves geometric decrease of exponential loss. We study how to incorporate group fairness constraints into boosting while…
Representation learning is increasingly applied to generate representations that generalize well across multiple downstream tasks. Ensuring fairness guarantees in representation learning is crucial to prevent unfairness toward specific…
Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent trends favor algorithmic methods that embed fairness into the training process. These methods steer models towards fair…
Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data…
Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and…
Group distributionally robust optimization, which aims to improve robust accuracies -- worst-group and unbiased accuracies -- is a prominent algorithm used to mitigate spurious correlations and address dataset bias. Although existing…
We introduce an innovative approach to enhancing the empirical risk minimization (ERM) process in model training through a refined reweighting scheme of the training data to enhance fairness. This scheme aims to uphold the sufficiency rule…
Training fair machine learning models, aiming for their interpretability and solving the problem of domain shift has gained a lot of interest in the last years. There is a vast amount of work addressing these topics, mostly in separation.…
Privacy concerns associated with machine learning models have driven research into machine unlearning, which aims to erase the memory of specific target training data from already trained models. This issue also arises in federated…
In the federated learning setting, multiple clients jointly train a model under the coordination of the central server, while the training data is kept on the client to ensure privacy. Normally, inconsistent distribution of data across…
In machine learning, training data often capture the behaviour of multiple subgroups of some underlying human population. When the amounts of training data for the subgroups are not controlled carefully, under-representation bias arises. We…