Scholarlink

To overcome one of the main limitations of federated learning, that is the non-negligible communication overhead between the clients and server, the present work proposes a novel federated scheme based on principles envisaged by semantic communications. The proposed semantic-based dimensionality reduction algorithm is employed to reduce the data exchanges by more than one order of magnitude and negligible performance loss. The effectiveness of the proposed approach is validated through a classification scenario leveraging transfer learning.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Semantic-Based Dimensionality Reduction in Federated Learning Approaches

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Danilo Menegatti,
  • Alessandro Giuseppi,
  • Antonio Pietrabissa

摘要

To overcome one of the main limitations of federated learning, that is the non-negligible communication overhead between the clients and server, the present work proposes a novel federated scheme based on principles envisaged by semantic communications. The proposed semantic-based dimensionality reduction algorithm is employed to reduce the data exchanges by more than one order of magnitude and negligible performance loss. The effectiveness of the proposed approach is validated through a classification scenario leveraging transfer learning.