Papers of the day   All papers

Advances and Open Problems in Federated Learning

Comments

Jeff Dean: Nice comprehensive look at the state of federated learning research, including an overview of advances in the last three years (since https://arxiv.org/abs/1610.05492 in 2016), as well as a nice overview of open problems in the area. 105 pages, 485 references!

2 replies, 309 likes


Blaise Aguera: Advances and Open Problems in Federated Learning: https://arxiv.org/pdf/1912.04977.pdf from 22 Googlers and 36 academics at 24 institutions! (a) improving efficiency, (b) preserving privacy, (c) defending against attacks, (c) addressing fairness. Here’s to years of future progress on these :)

3 replies, 244 likes


Peter Kairouz: More than 1000 papers on Federated Learning were published in the first 6 months of 2020, compared to just 180 in all 2018! If you want to learn more about recent advances and open challenges in the field, please check our recent manuscript: https://arxiv.org/pdf/1912.04977.pdf!! 🙌

1 replies, 45 likes


Prateek Mittal: New paper on "Advances and Open Problems in Federated Learning", together with 58 co-authors from 25 institutions: https://arxiv.org/pdf/1912.04977.pdf

2 replies, 31 likes


Gautam Kamath ✈️ #NeurIPS2019: Very cool -- a thorough manifesto on the current state of federated learning! (https://arxiv.org/abs/1912.04977) Led by @KairouzPeter and Brendan McMahan. Just in time for today's workshop on federated learning! https://nips.cc/Conferences/2019/Schedule?showEvent=13202 #NeurIPS2019

0 replies, 20 likes


Mathieu Galtier: This is an impressive milestones in federated learning. A 100p papier by most influencers in the field! Thanks for paving the way for @Substra_org and @OWKINscience https://arxiv.org/pdf/1912.04977.pdf

0 replies, 12 likes


Karl Higley: This (excellent) 110 page survey paper on advances and open problems in federated learning never mentions the notoriously difficult distributed garbage collection problem. 😧🥺 https://arxiv.org/pdf/1912.04977.pdf

1 replies, 6 likes


Rasmus Pagh: "Advances and Open Problems in Federated Learning", incl. discussion of efficiency, privacy, fairness. Available as https://arxiv.org/pdf/1912.04977.pdf thanks to great editorial work by Brendan McMahan and @KairouzPeter. It was fun to contribute a small part to this 58-author paper!

0 replies, 3 likes


MehdiBen: Interested in recent advances and open problems of federated learning; Check this out: https://arxiv.org/pdf/1912.04977

0 replies, 2 likes


Underfox: In this paper is presented a very comprehensive survey on the many open challenges in the federated learning area, discussing recent advances and presenting an extensive collection of open problems and challenges. #MachineLearning https://arxiv.org/pdf/1912.04977.pdf https://t.co/AwmUDPXV1i

1 replies, 0 likes


Content

Found on Dec 17 2019 at https://arxiv.org/pdf/1912.04977.pdf

PDF content of a computer science paper: Advances and Open Problems in Federated Learning