Federated learning framework optimizes energy-harvesting devices for global and personalized models

This research paper introduces a novel framework for federated learning (FL) designed for energy-harvesting mobile devices. The proposed system addresses challenges posed by heterogeneous data distributions and limited energy availability by leveraging cluster information. It supports two learning objectives: enhancing a global model's representativeness by reducing data bias, and personalizing cluster-specific models by exploiting this bias. Numerical results indicate improved fairness or personalization with reduced communication overhead. AI

IMPACT Enhances efficiency and personalization in distributed learning systems with limited energy resources.

RANK_REASON The cluster contains a single academic paper from arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• federated learning
• Mobile Devices
• Model personalization

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →