PROVABLY EFFICIENT FEDERATED ACTIVE MULTI-TASK REPRESENTATION LEARNING
Lists
Only you see this
Abstract
Multi-task representation learning is an emerging machine learning paradigm that integrates data from multiple sources, harnessing task similarities to enhance overall model performance. The application of multi-task learning to real-world settings is hindered due to data scarcity, along with challenges related to scalability and computational resources. To address these challenges, we develop a fast and sample-efficient approach for multi-task active learning with linear representation when the amount of data from source tasks and target tasks is limited. By leveraging the techniques from active learning, we propose an adaptive sampling-based alternating projected gradient descent (GD) and minimization algorithm that iteratively estimates the relevance of each source task to the target task and samples from each source task based on the estimated relevance. We present the convergence guarantees and the sample and time complexities of our algorithm. We evaluated the effectiveness of our algorithm using numerical experiments and compared it against four benchmark algorithms using synthetic and real MNIST-C datasets.
BibTeX
@misc{lin2025provably,
author = {Jiabin Lin and Shana Moothedath and Tuan Anh Le},
title = {{PROVABLY EFFICIENT FEDERATED ACTIVE MULTI-TASK REPRESENTATION LEARNING}},
year = {2025},
url = {https://openreview.net/forum?id=jYJq2gQb7J},
howpublished = {OpenReview},
note = {Submitted to ICLR 2025},
}