Manocha, Bedi receive Amazon Research Award for 'federated learning'

Manocha, Bedi receive Amazon Research Award for 'federated learning'

Manocha, Bedi receive Amazon Research Award for 'federated learning'

ISR-affiliated Distinguished University Professor Dinesh Manocha (ECE/CS/UMIACS) and Visiting Assistant Research Scientist Amrit Bedi (ISR) are receiving $50K in funding from Amazon Research Awards (ARA) for their AI/machine learning project, “Ensuring Fairness via Federated Learning Beyond Consensus.” The two entered their proposal through the ARA Spring/Summer 2022 call for proposals. Bedi works primarily on the ArtIAMAS research project with Manocha and Professor Derek Paley (AE/ISR).

What is federated learning?

Federated learning is a decentralized way to unlock information that feeds new AI applications and trains existing AI models without individual users’ data being seen or collected. The actual data never leave an individual mobile phone, laptop, or private server.

Federated learning is fast becoming the standard that complies with new regulations for handling and storing private data. It also offers a way to tap raw data streaming from sensors on satellites, bridges, machines, and a growing number of smart devices.

The new technique enables mobile phones to collaboratively learn a shared prediction model while keeping the training data on the device, decoupling the ability to do machine learning from the need to store data in the cloud. Federated learning goes beyond the use of local models that make predictions on mobile devices by bringing model training to the device as well.

A device downloads the current model, improves it by learning from data on the phone, then summarizes the changes as a small focused update. Only this update is sent to the cloud, using encrypted communication. It is then averaged with other user updates to improve the shared model. Training data remains on the device itself; no individual updates are stored in the cloud.

Federated learning produces smarter models, lower latency, and less power consumption, all while ensuring privacy. In addition to providing an update to the shared model, the improved model can also be used immediately on the device for a more personalized experience.

Related Articles:
UMD’s SeaDroneSim can generate simulated images and videos to help UAV systems recognize ‘objects of interest’ in the water
Cornelia Fermüller is PI for 'NeuroPacNet,' a $1.75M NSF funding award
Lampropoulos and Miers Receive NSF Funding for Privacy-Preserving Computing
New Research Helps Robots Grasp Situational Context
ISR Alum Quoted in CNN, WSJ on AI Risks
Autonomy Summit Explores Potential and Challenges of AI
CEEE Study Explores How AI Can Reduce HVAC Energy Consumption
Goulias Tapped to Develop Renewable Construction Materials
LEGOLAS participates at U.S. Senate Robotics Showcase on Capitol Hill
Two ECE Graduate Students Win 2023 UMD Three Minute Thesis Competition

December 19, 2022


Prev   Next

Current Headlines

Lampropoulos and Miers Receive NSF Funding for Privacy-Preserving Computing

Logan Selph Awarded NSF Graduate Research Fellowship

Announcing the 2025 Master’s Fellows in Fire Protection Engineering

Passing the Torch: Maryland Robotics Center’s Next Chapter

New Quantum Hardware Lab Made Possible by Donation from ECE Alum Paul Gaske ‘76

UMD Team Advances Mission Concept for 2029 Asteroid Flyby

Alumni Spotlight: Christine Pongratz ’13, M.S. ’14

Pamela Abshire Named ECE Chair of Stony Brook University

News Resources

Return to Newsroom

Search News

Archived News

Events Resources

Events Calendar