RECORD
Papaya: Federated Learning, but Fully Decentralized
Machine Learning · Submitted 10 Mar 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We instead implement a peer to peer learning system in which nodes train on their own data and periodically perform a weighted average of their parameters with that of their peers according to a learned trust matrix.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Federated Learning systems use a centralized server to aggregate model updates. This is a bandwidth and resource-heavy constraint and exposes the system to privacy concerns. We instead implement a peer to peer learning system in which nodes train on their own data and periodically perform a weighted average of their parameters with that of their peers according to a learned trust matrix. So far, we have created a model client framework and have been using this to run experiments on the proposed system using multiple virtual nodes which in reality exist on the same computer. We used this strategy as stated in Iteration 1 of our proposal to prove the concept of peer to peer learning with shared parameters. We now hope to run more experiments and build a more deployable real world system for the same.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Federated Learning systems use a centralized server to aggregate model updates. | background 1.00 | 0.05 | 0.03 | asserted 1.00 |
| s1 | This is a bandwidth and resource-heavy constraint and exposes the system to privacy concerns. | background 0.96 | 0.07 | 0.04 | asserted 1.00 |
| s2 | We instead implement a peer to peer learning system in which nodes train on their own data and periodically perform a weighted average of their parameters with that of their peers according to a learned trust matrix. | method 0.76 | 0.89 | 0.35 | asserted 1.00 |
| s3 | So far, we have created a model client framework and have been using this to run experiments on the proposed system using multiple virtual nodes which in reality exist on the same computer. | limitation 0.62 | 0.95 | 0.04 | asserted 1.00 |
| s4 | We used this strategy as stated in Iteration 1 of our proposal to prove the concept of peer to peer learning with shared parameters. | method 0.49 | 0.83 | 0.05 | asserted 1.00 |
| s5 | We now hope to run more experiments and build a more deployable real world system for the same. | future work 1.00 | 0.12 | 0.06 | hedged possibility 0.58 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Federated Learning systems use a centralized server to aggregate model updates. This is a bandwidth and resource-heavy constraint and exposes the system to privacy concerns. We instead implement a peer to peer learning system in which nodes train on their own data and periodically perform a weighted average of their parameters with that of their peers according to a learned trust matrix. So far, we have created a model client framework and have been using this to run experiments on the proposed system using multiple virtual nodes which in reality exist on the same computer. We used this strategy as stated in Iteration 1 of our proposal to prove the concept of peer to peer learning with shared parameters. We now hope to run more experiments and build a more deployable real world system for the same.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 1 sentence without a confident label
Cites as background 2 papers
-
Lalitha et al. [ref] propose a method for Peer to Peer Federated Learning in their 2019 paper.
Peer-to-peer Federated Learning on Graphs · Peer to Peer Federated Learning · 0.89
-
Another development in the context of peer to peer sharing of model training information is explained in the GossipGrad paper by Daily et al. [ref] Their paper proposes a method of training models on multiple GPU nodes within the same computing cluster through the propagation of gradients through the network via the gossip protocol.
GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent · Peer to Peer Federated Learning · 0.89
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.