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

Think Locally, Act Globally: Federated Learning with Local and Global Representations

About

Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges for large models. To this end, we propose a new federated learning algorithm that jointly learns compact local representations on each device and a global model across all devices. As a result, the global model can be smaller since it only operates on local representations, reducing the number of communicated parameters. Theoretically, we provide a generalization analysis which shows that a combination of local and global models reduces both variance in the data as well as variance across device distributions. Empirically, we demonstrate that local models enable communication-efficient training while retaining performance. We also evaluate on the task of personalized mood prediction from real-world mobile data where privacy is key. Finally, local models handle heterogeneous data from new devices, and learn fair representations that obfuscate protected attributes such as race, age, and gender.

Paul Pu Liang, Terrance Liu, Liu Ziyin, Nicholas B. Allen, Randy P. Auerbach, David Brent, Ruslan Salakhutdinov, Louis-Philippe Morency• 2020

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 (test)
Accuracy74.08
3518
Image ClassificationCIFAR-10 (test)
Accuracy87.9
3381
Image ClassificationCIFAR-10
Accuracy77.65
507
Image ClassificationTinyImageNet (test)
Accuracy32.26
366
Image ClassificationPACS (test)
Average Accuracy76.72
254
Image ClassificationDomainNet (test)
Average Accuracy71.13
209
Image ClassificationMiniImagenet
Accuracy36.68
206
Image ClassificationCINIC-10 (test)
Accuracy59.9
177
Image ClassificationEMNIST (test)
Accuracy76.12
174
Image ClassificationOfficeHome
Average Accuracy78.75
131
Showing 10 of 80 rows
...

Other info

Follow for update