REVIEW 4 cited by
Decentralized Federated Learning: A Segmented Gossip Approach
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The emerging concern about data privacy and security has motivated the proposal of federated learning, which allows nodes to only synchronize the locally-trained models instead their own original data. Conventional federated learning architecture, inherited from the parameter server design, relies on highly centralized topologies and the assumption of large nodes-to-server bandwidths. However, in real-world federated learning scenarios the network capacities between nodes are highly uniformly distributed and smaller than that in a datacenter. It is of great challenges for conventional federated learning approaches to efficiently utilize network capacities between nodes. In this paper, we propose a model segment level decentralized federated learning to tackle this problem. In particular, we propose a segmented gossip approach, which not only makes full utilization of node-to-node bandwidth, but also has good training convergence. The experimental results show that even the training time can be highly reduced as compared to centralized federated learning.
Forward citations
Cited by 4 Pith papers
-
Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities
DFL under local averaging is lazy random-walk diffusion on temporal networks; real structural and temporal heterogeneities slow mixing by one to two orders of magnitude relative to standard synthetic benchmarks.
-
Reputation-driven Cooperation in Lattice-based Decentralized Federated Learning through Evolutionary Game Theory
In a lattice-based simulation of decentralized federated learning, a reputation mechanism that rewards cooperators and penalizes defectors raises average accuracy from 70% to 82% and drives cooperation to near 100%.
-
FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning
FIRMA introduces Fibonacci ring aggregation protocols for server-free federated learning that maintain private heads and achieve higher accuracy than FedAvg under label skew across multiple benchmarks and heterogeneit...
-
DFCA: Decentralized Federated Clustering Algorithm
DFCA decentralizes IFCA-style clustered federated learning: clients keep one model per cluster, train their assigned model locally, and exchange only that model with neighbors via a running average, matching centraliz...
Discussion (0). Sign in to comment.