paper-with-me

홈 › Papers

Re-thinking Federated Active Learning based on Inter-class Diversity

2023-03-22 · CVPR 2023 1 · Sangmook Kim, Sangmin Bae, Hwanjun Song, Se-Young Yun

Although federated learning has made awe-inspiring advances, most studies have assumed that the client's data are fully labeled. However, in a real-world scenario, every client may have a significant amount of unlabeled instances. Among the various approaches to utilizing unlabeled data, a federated active learning framework has emerged as a promising solution. In the decentralized setting, there are two types of available query selector models, namely 'global' and 'local-only' models, but little literature discusses their performance dominance and its causes. In this work, we first demonstrate that the superiority of two selector models depends on the global and local inter-class diversity. Furthermore, we observe that the global and local-only models are the keys to resolving the imbalance of each side. Based on our findings, we propose LoGo, a FAL sampling strategy robust to varying local heterogeneity levels and global imbalance ratio, that integrates both models by two steps of active selection scheme. LoGo consistently outperforms six active learning strategies in the total number of 38 experimental settings.

📄 PDF Abstract BibTeX arXiv:2303.12317

Code (1)

raymin0223/logo 공식 구현 pytorch

Tasks

Active LearningDiversityFederated Learning

Similar Papers 제목 키워드 기반

V-Thinker: Interactive Thinking with Images

2025-11-06 · Runqi Qiao, Qiuna Tan, Minghan Yang, Guanting Dong 외 arxiv

Empowering Large Multimodal Models (LMMs) to deeply integrate image interaction with long-horizon reasoning capabilities remains a long-standing challenge in this field. Recent advances in vision-centric reasoning explor…

Reinforcement LearningMultimodal Reasoning

Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts

2023-12-05 · CVPR 2024 1 · Jiayi Chen, Benteng Ma, Hengfei Cui, Yong Xia

Federated learning facilitates the collaborative learning of a global model across multiple distributed medical institutions without centralizing data. Nevertheless, the expensive cost of annotation on local clients rema…

Active LearningDiversityFederated LearningInformativeness+1

Language of Thought Shapes Output Diversity in Large Language Models

2026-01-16 · Shaoyang Xu, Wenxuan Zhang arxiv

Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the language used during model thinking-the language of thought-provides a novel an…

Federated Active Learning Under Extreme Non-IID and Global Class Imbalance

2026-03-11 · Chen-Chen Zong, Sheng-Jun Huang arxiv

Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints, yet its effectiveness degrades in realistic settings with severe global class imbalance and highly heterogeneous clients. We cond…

Active Learning

InFL-UX: A Toolkit for Web-Based Interactive Federated Learning

2025-03-06 · Tim Maurer, Abdulrahman Mohamed Selim, Hasan Md Tusfiqur Alam, Matthias Eiletz 외

This paper presents InFL-UX, an interactive, proof-of-concept browser-based Federated Learning (FL) toolkit designed to integrate user contributions seamlessly into the machine learning (ML) workflow. InFL-UX enables use…

Federated Learning