Federated Residual Learning

By Alekh Agarwal, J. Langford, Chen-Yu Wei. 2020

39 citations recorded by the source corpus.

We study a new form of federated learning where the clients train personalized local models and make predictions jointly with the server-side shared model. Using this new federated learning framework, the complexity of the central shared model can be minimized while still gaining all the performance benefits that joint training provides. Our framework is robust to data heterogeneity, addressing the slow convergence problem traditional federated learning methods face when the data is non-i.i.d. across clients. We test the theory empirically and find substantial performance gains over baselines.

Subfields: Artificial Intelligence, Computer Science Applications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sham M. Kakade
2. Zaïd Harchaoui
3. Krishna Pillutla
4. Francis R. Bach
5. Zeyuan Allen-Zhu
6. Martin Jaggi
7. Anima Anandkumar
8. Sergey Levine

In Computer Science Applications

1. Sham M. Kakade
2. Krishna Pillutla
3. Zaïd Harchaoui

Citations in the corpus

• Robust Aggregation for Federated Learning (2019, positive): “We train the shared and personalized parameters on each other’s residuals, following the residual learning scheme of [3].”