IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
MLSP-45.4

PARTIAL VARIABLE TRAINING FOR EFFICIENT ON-DEVICE FEDERATED LEARNING

Tien-Ju Yang, Dhruv Guliani, Françoise Beaufays, Giovanni Motta, Google LLC, United States of America

Session:
Distributed and Federated Learning II

Track:
Machine Learning for Signal Processing

Location:
Gather Area H

Presentation Time:
Thu, 12 May, 21:00 - 21:45 China Time (UTC +8)
Thu, 12 May, 13:00 - 13:45 UTC

Session Chair:
Rainer Martin, Ruhr-Uni­ver­si­tät Bo­chum
Presentation
Discussion
Resources
Session MLSP-45
MLSP-45.1: FedClean: A Defense Mechanism Against Parameter Poisoning Attacks in Federated Learning
Abhishek Kumar, University of Oulu & University of Helsinki, Finland; Vivek Khimani, Drexel University, United States of America; Dimitris Chatzopoulos, University College Dublin, Ireland; Pan Hui, Hong Kong University of Science and Technology & University of Helsinki, Hong Kong
MLSP-45.2: A METHOD TO REVEAL SPEAKER IDENTITY IN DISTRIBUTED ASR TRAINING, AND HOW TO COUNTER IT
Trung Dang, Peter Chin, Boston University, United States of America; Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Françoise Beaufays, Google LLC, United States of America
MLSP-45.3: ON THE CONVERGENCE OF ADAM-TYPE ALGORITHMS FOR SOLVING STRUCTURED SINGLE NODE AND DECENTRALIZED MIN-MAX SADDLE POINT GAMES
Babak Barazandeh, Kristal Curtis, Chandrima Sarkar, Splunk, United States of America; Ram Sriharsha, Pinecone, United States of America; George Michailidis, University of Florida, United States of America
MLSP-45.4: PARTIAL VARIABLE TRAINING FOR EFFICIENT ON-DEVICE FEDERATED LEARNING
Tien-Ju Yang, Dhruv Guliani, Françoise Beaufays, Giovanni Motta, Google LLC, United States of America
MLSP-45.5: GRADIENT STALENESS IN ASYNCHRONOUS OPTIMIZATION UNDER RANDOM COMMUNICATION DELAYS
Haider Al-Lawati, Stark Draper, University of Toronto, Canada
MLSP-45.6: TEMPO: IMPROVING TRAINING PERFORMANCE IN CROSS-SILO FEDERATED LEARNING
Chen Ying, Baochun Li, University of Toronto, Canada; Bo Li, Hong Kong University of Science and Technology, Hong Kong