Scholarlink

<p>We provide our perspective on <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\({\mathbb{X}}\)</EquationSource> <EquationSource Format="MATHML"><math> <mi mathvariant="double-struck">X</mi> </math></EquationSource> </InlineEquation>-Learning (<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\({\mathbb{X}}\)</EquationSource> <EquationSource Format="MATHML"><math> <mi mathvariant="double-struck">X</mi> </math></EquationSource> </InlineEquation>L), a novel distributed learning architecture that generalizes and extends the concept of <i>decentralization</i>. Our goal is to present a vision for <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\({\mathbb{X}}\)</EquationSource> <EquationSource Format="MATHML"><math> <mi mathvariant="double-struck">X</mi> </math></EquationSource> </InlineEquation>L, introducing its unexplored design considerations and degrees of freedom. To this end, we shed light on the intuitive yet non-trivial connections between <InlineEquation ID="IEq5"> <EquationSource Format="TEX">\({\mathbb{X}}\)</EquationSource> <EquationSource Format="MATHML"><math> <mi mathvariant="double-struck">X</mi> </math></EquationSource> </InlineEquation>L, graph theory, and Markov chains. We also present a series of open research directions to stimulate further research.</p>

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

From federated learning to \({\mathbb{X}}\)-Learning: breaking the barriers of decentrality through random walks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月4日

查看全文
  • Allan Salihovic,
  • Payam Abdisarabshali,
  • Michael Langberg,
  • Seyyedali Hosseinalipour

摘要

We provide our perspective on \({\mathbb{X}}\) X -Learning ( \({\mathbb{X}}\) X L), a novel distributed learning architecture that generalizes and extends the concept of decentralization. Our goal is to present a vision for \({\mathbb{X}}\) X L, introducing its unexplored design considerations and degrees of freedom. To this end, we shed light on the intuitive yet non-trivial connections between \({\mathbb{X}}\) X L, graph theory, and Markov chains. We also present a series of open research directions to stimulate further research.