Scholarlink

As artificial intelligence technology rapidly evolves, data security and privacy protection have become paramount concerns. Federated Learning, a privacy-preserving distributed machine learning approach, facilitates model training without the need for data to leave local devices, significantly reducing the risk of data breaches. However, the variability in network conditions and the heterogeneity of data across devices can lead to performance disparities, introducing biases in the model transmission process and potentially compromising the effectiveness of privacy preservation. To mitigate this issue, we propose CAFL, a novel method for node feature extraction that combines node clustering based on Contrastive Learning with Self-Attention. CAFL is designed to optimize task allocation and model aggregation by carefully assessing node characteristics. We select nodes with high performance and stability (termed “strong node”) to build a robust Federated Learning system. Experimental results demonstrate that CAFL outperforms its stochastic static counterparts in terms of network communication efficiency.hin

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

CAFL: Contrastive Learning and Self-attention in Federated Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Riqing Xu,
  • Gang Lei,
  • Wenbin Qiu

摘要

As artificial intelligence technology rapidly evolves, data security and privacy protection have become paramount concerns. Federated Learning, a privacy-preserving distributed machine learning approach, facilitates model training without the need for data to leave local devices, significantly reducing the risk of data breaches. However, the variability in network conditions and the heterogeneity of data across devices can lead to performance disparities, introducing biases in the model transmission process and potentially compromising the effectiveness of privacy preservation. To mitigate this issue, we propose CAFL, a novel method for node feature extraction that combines node clustering based on Contrastive Learning with Self-Attention. CAFL is designed to optimize task allocation and model aggregation by carefully assessing node characteristics. We select nodes with high performance and stability (termed “strong node”) to build a robust Federated Learning system. Experimental results demonstrate that CAFL outperforms its stochastic static counterparts in terms of network communication efficiency.hin