LFHE: Local-First Heuristic Evolution for Bounded Local Topology Search in Decentralized Learning with Non-IID Data

Key points

• Adaptive peer-selection methods can exploit local model information, but broader peer discovery may require increasingly large control state, whereas direct spectral optimization typically relies on graph-wide information.1
• We study the intermediate setting of bounded local topology search and propose Local-First Heuristic Evolution (LFHE), a representation-driven rewiring framework whose candidate discovery and scoring use only ego-neighborhood and friend-of-a-friend (FoF) information.1
• Matched-protocol controls identify the structural term as the principal empirical topology-selection signal, while comparison with broader peer discovery exposes a trade-off between predictive performance and discovery-state locality.1
• Together, these results motivate state-aware bounded local topology search between pairwise peer selection and globally informed topology optimization.1

Sources (1)

• [1]LFHE: Local-First Heuristic Evolution for Bounded Local Topology Search in Decentralized Learning with Non-IID Data
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 11:29 AM

  Decentralized learning is highly sensitive to communication topology under non-IID data.

  Adaptive peer-selection methods can exploit local model information, but broader peer discovery may require increasingly large control state, whereas direct spectral optimization typically relies on graph-wide information.

Extractive summary: sentences quoted from the sources.