This work considers the category distribution heterogeneity in federated learning. This issue
is due to biased labeling preferences at multiple clients and is a typical setting of data …

Linear scalarization, ie, combining all loss functions by a weighted sum, has been the
default choice in the literature of multi-task learning (MTL) since its inception. In recent years …

Recent multi-task learning research argues against unitary scalarization, where training
simply minimizes the sum of the task losses. Several ad-hoc multi-task optimization …

Vision-language models (VLMs) can effectively transfer to various vision tasks via prompt
learning. Real-world scenarios often require adapting a model to multiple similar yet distinct …

In the fashion domain, there exists a variety of vision-and-language (V+ L) tasks, including
cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image …

Understanding the structure of multiple related tasks allows for multi-task learning to improve
the generalisation ability of one or all of them. However, it usually requires training each …

Diffusion-based generative models have achieved remarkable success in various domains.
It trains a shared model on denoising tasks that encompass different noise levels …

Abstract Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by
leveraging the knowledge obtained from related tasks. Occasionally, learning multiple tasks …

Multi-objective optimization (MOO) has become an influential framework in many machine
learning problems with multiple objectives such as learning with multiple criteria and multi …

This paper presents LibMTL, an open-source Python library built on PyTorch, which
provides a unified, comprehensive, reproducible, and extensible implementation framework …