Scholarlink

Despite the superior fast learning performance of online meta-learning, to learn a good meta-model for within-task fast adaptation, a single edge device alone still has to learn over many tasks, which inevitably encounters the cold-start problem.

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

Edge-Edge Collaboration via Decentralized Online Meta-Learning

  • 章节

  • 发表日期：

    2025年

查看全文
  • Hang Wang,
  • Sen Lin,
  • Junshan Zhang

摘要

Despite the superior fast learning performance of online meta-learning, to learn a good meta-model for within-task fast adaptation, a single edge device alone still has to learn over many tasks, which inevitably encounters the cold-start problem.