Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Federated Optimization in Heterogeneous Networks

About

Federated Learning is a distributed learning paradigm with two key challenges that differentiate it from traditional distributed optimization: (1) significant variability in terms of the systems characteristics on each device in the network (systems heterogeneity), and (2) non-identically distributed data across the network (statistical heterogeneity). In this work, we introduce a framework, FedProx, to tackle heterogeneity in federated networks. FedProx can be viewed as a generalization and re-parametrization of FedAvg, the current state-of-the-art method for federated learning. While this re-parameterization makes only minor modifications to the method itself, these modifications have important ramifications both in theory and in practice. Theoretically, we provide convergence guarantees for our framework when learning over data from non-identical distributions (statistical heterogeneity), and while adhering to device-level systems constraints by allowing each participating device to perform a variable amount of work (systems heterogeneity). Practically, we demonstrate that FedProx allows for more robust convergence than FedAvg across a suite of realistic federated datasets. In particular, in highly heterogeneous settings, FedProx demonstrates significantly more stable and accurate convergence behavior relative to FedAvg---improving absolute test accuracy by 22% on average.

Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith• 2018

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 (test)
Accuracy71.93
3518
Image ClassificationCIFAR-10 (test)
Accuracy86.28
3381
Image ClassificationCIFAR-10 (test)--
906
Image ClassificationMNIST (test)
Accuracy96.05
882
Image ClassificationCIFAR-100
Top-1 Accuracy56.45
622
Image ClassificationCIFAR10 (test)
Accuracy59.4
585
Image ClassificationClothing1M (test)
Accuracy71.35
546
Image ClassificationCIFAR-10
Accuracy81.9
507
Depth EstimationNYU v2 (test)--
423
Image ClassificationMNIST--
395
Showing 10 of 346 rows
...

Other info

Follow for update