Timezone: »

 
Poster
Federated Reconstruction: Partially Local Federated Learning
Karan Singhal · Hakim Sidahmed · Zachary Garrett · Shanshan Wu · John Rush · Sushant Prakash

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @
in Poster Session 6 »

Personalization methods in federated learning aim to balance the benefits of federated and local training for data availability, communication cost, and robustness to client heterogeneity. Approaches that require clients to communicate all model parameters can be undesirable due to privacy and communication constraints. Other approaches require always-available or stateful clients, impractical in large-scale cross-device settings. We introduce Federated Reconstruction, the first model-agnostic framework for partially local federated learning suitable for training and inference at scale. We motivate the framework via a connection to model-agnostic meta learning, empirically demonstrate its performance over existing approaches for collaborative filtering and next word prediction, and release an open-source library for evaluating approaches in this setting. We also describe the successful deployment of this approach at scale for federated collaborative filtering in a mobile keyboard application.

Keywords: Robustness · Meta Learning · Privacy · Federated Learning

Author Information

Karan Singhal (Google Research)
Hakim Sidahmed (Google)
Zachary Garrett (Google)
Shanshan Wu (University of Texas at Austin)

Here is my homepage: http://wushanshan.github.io/

John Rush (Google)

I come from a pure mathematics background, formerly a harmonic analyst and mathematical physicist. I transferred to machine learning on the software side after grad school, and joined Google in 2018, working on federated learning. I am a main author of TensorFlow Federated; ask me about it!

Sushant Prakash (Google)

More from the Same Authors