Few-Round Learning for Federated Learning
Dec 6, 2021
Speakers
Younghyun Park
Speaker · 0 followers
Dong-Jun Han
Speaker · 0 followers
Do-Yeon Kim
Speaker · 0 followers
Jaekyun Moon
Speaker · 0 followers
About
In federated learning (FL), a number of distributed clients targeting the same task collaborate to train a single global model without sharing their data. The learning process typically starts from a randomly initialized or some pretrained model. In this paper, we aim at designing an initial model based on which an arbitrary group of clients can obtain a global model for its own purpose, within only a few rounds of FL. The key challenge here is that the task of the group conducting FL are generally unknown when the initial model is prepared. Our idea is to take a meta-learning approach to construct the initial model so that any group with a possibly unseen task can obtain a high-accuracy global model within only R rounds of FL. Our meta-learning itself could be done via federated learning among willing participants and is based on an episodic arrangement to mimic the R rounds of FL followed by inference in each episode. Extensive experimental results show that our method generalizes well for arbitrary groups of clients and provides large performance improvements given the same overall communication/computation resources, compared to other baselines relying on known pretraining methods (e.g., federated meta-learning ideas targeting personalization).In federated learning (FL), a number of distributed clients targeting the same task collaborate to train a single global model without sharing their data. The learning process typically starts from a randomly initialized or some pretrained model. In this paper, we aim at designing an initial model based on which an arbitrary group of clients can obtain a global model for its own purpose, within only a few rounds of FL. The key challenge here is that the task of the group conducting FL are genera…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Towards Instance-Optimal Offline Reinforcement Learning with Pessimism
Watch later
Ming Yin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
De-randomizing MCMC dynamics with the diffusion Stein operator
Watch later
Zheyang Shen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Detection of Topological Changes via Geometric Alignment
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Localization with Sampling-Argmax
Watch later
Jiefeng Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Adaptive Fine-tuning for Vision and Language Pre-trained Models
Watch later
Shentong Mo, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Speaker Introduction (Andreas)
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%