paper-with-me

Papers

Peer-to-Peer Deep Learning for Beyond-5G IoT

2023-10-29 · Srinivasa Pranav, José M. F. Moura

We present P2PL, a practical multi-device peer-to-peer deep learning algorithm that, unlike the federated learning paradigm, does not require coordination from edge servers or the cloud. This makes P2PL well-suited for the sheer scale of beyond-5G computing environments like smart cities that otherwise create range, latency, bandwidth, and single point of failure issues for federated approaches. P2PL introduces max norm synchronization to catalyze training, retains on-device deep model training to preserve privacy, and leverages local inter-device communication to implement distributed consensus. Each device iteratively alternates between two phases: 1) on-device learning and 2) peer-to-peer cooperation where they combine model parameters with nearby devices. We empirically show that all participating devices achieve the same test performance attained by federated and centralized training -- even with 100 devices and relaxed singly stochastic consensus weights. We extend these experimental results to settings with diverse network topologies, sparse and intermittent communication, and non-IID data distributions.

📄 PDF Abstract BibTeX arXiv:2310.18861

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningFederated Learning

Similar Papers 제목 키워드 기반

Identification of a Rank-dependent Peer Effect Model

2024-10-18 · Eyo I. Herstad, Myungkou Shin

We develop a model that captures peer effect heterogeneity by modeling the endogenous spillover to be linear in ordered peer outcomes. Unlike the canonical linear-in-means model, our approach accounts for the distributio…

model

PeerRank: Autonomous LLM Evaluation Through Web-Grounded, Bias-Controlled Peer Review

2026-02-01 · Yanki Margalit, Erni Avram, Ran Taig, Oded Margalit 외 arxiv

Evaluating large language models typically relies on human-authored benchmarks, reference answers, and human or single-model judgments, approaches that scale poorly, become quickly outdated, and mismatch open-world deplo…

NLPeer: A Unified Resource for the Computational Study of Peer Review

2022-11-12 · Nils Dycke, Ilia Kuznetsov, Iryna Gurevych

Peer review constitutes a core component of scholarly publishing; yet it demands substantial expertise and training, and is susceptible to errors and biases. Various applications of NLP for peer reviewing assistance aim …

Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations

2023-12-15 · Cedric Derstroff, Mattia Cerrato, Jannis Brugger, Jan Peters 외

Peer learning is a novel high-level reinforcement learning framework for agents learning in groups. While standard reinforcement learning trains an individual agent in trial-and-error fashion, all on its own, peer learni…

OpenAI Gymreinforcement-learningReinforcement Learning

Peer-to-Peer Learning Dynamics of Wide Neural Networks

2024-09-23 · Shreyas Chaudhari, Srinivasa Pranav, Emile Anand, José M. F. Moura

Peer-to-peer learning is an increasingly popular framework that enables beyond-5G distributed edge devices to collaboratively train deep neural networks in a privacy-preserving manner without the aid of a central server.…

Distributed OptimizationPrivacy Preserving