Research map / Graph learning / Graph algorithms and clustering
Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Revisits the 1-peer exponential graph for decentralized learning, extending its finite-time convergence beyond node counts that are powers of two.
Problem
The 1-peer exponential graph gives finite-time convergence and maximal expected spectral gap for decentralized learning only when the number of nodes n is a power of two; its efficiency for arbitrary n is unclear.
Approach
Revisits the 1-peer exponential graph for arbitrary node counts to improve the expected spectral gap of dynamic communication graphs, reducing deviation from global averaging. Details beyond the abstract are not available.
Experimental setup
Builds on: 1-peer exponential graph
Closest papers by meaning
- Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence (NeurIPS 2023 · similarity 0.91)
- Bottleneck Communication Delay Minimization for Communication-Efficient Decentralized Learning (ICML 2026 · similarity 0.89)
- Exponential Graph is Provably Efficient for Decentralized Deep Training (NeurIPS 2021 · similarity 0.89)
- Revisiting Differentially Private Algorithms for Decentralized Online Learning (ICML 2025 · similarity 0.84)
- Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks (ICML 2025 · similarity 0.83)
- B-ary Tree Push-Pull Method is Provably Efficient for Distributed Learning on Heterogeneous Data (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.