RealFM: A Realistic Mechanism to Incentivize Federated Participation and Contribution

1 code implementation • 20 Oct 2023 • Marco Bornstein, Amrit Singh Bedi, Anit Kumar Sahu, Furqan Khan, Furong Huang

On real-world data, RealFM improves device and server utility, as well as data contribution, by over 3 and 4 magnitudes respectively compared to baselines.

Large-Scale Distributed Learning via Private On-Device Locality-Sensitive Hashing

no code implementations • 5 Jun 2023 • Tahseen Rabbani, Marco Bornstein, Furong Huang

This allows devices to avoid maintaining (i) the fully-sized model and (ii) large amounts of hash tables in local memory for LSH analysis.

SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication

1 code implementation • 25 Oct 2022 • Marco Bornstein, Tahseen Rabbani, Evan Wang, Amrit Singh Bedi, Furong Huang

Furthermore, we provide theoretical results for IID and non-IID settings without any bounded-delay assumption for slow clients which is required by other asynchronous decentralized FL algorithms.

Federated Learning Image Classification

Comfetch: Federated Learning of Large Networks on Constrained Clients via Sketching

no code implementations • 17 Sep 2021 • Tahseen Rabbani, Brandon Feng, Marco Bornstein, Kyle Rui Sang, Yifan Yang, Arjun Rajkumar, Amitabh Varshney, Furong Huang

Federated learning (FL) is a popular paradigm for private and collaborative model training on the edge.

Federated Learning