Advances and Open Problems in Federated Learning · HackerPapers discussions

Advances and Open Problems in Federated Learning — mentioned by techwizrd

Thu, 17 Aug 2023 04:37:12 GMT

I really like seeing articles or papers that describe the current advances and open challenges in a sub-field (such as [0]). They're underappreciated, but good practice or reading for folks wanting to get in the field. They're also worthwhile and humbling to look back at every few years: did we get the challenges right? How well did we understand the problem at the time? 0: https://arxiv.org/abs/1912.04977

Paper and discussion history. A mention is not an endorsement.

Advances and Open Problems in Federated Learning — mentioned by techwizrd

Tue, 21 Mar 2023 00:05:11 GMT

I'm not entirely how the approach they're using works [0], but I study federated learning and one of the highly-cited survey papers has several chapters (5 and 6 in particular) addressing potential attacks, failure modes, and bias [1]. 0: https://github.com/learning-at-home/hivemind 1: https://arxiv.org/abs/1912.04977

Paper and discussion history. A mention is not an endorsement.

Advances and Open Problems in Federated Learning — mentioned by techwizrd

Tue, 22 Dec 2020 20:21:20 GMT

For those interested or confused around federated learning, I suggest skimming the 2019 paper "Advances and Open Problems in Federated Learning" [0]. The introduction is quite good and the table of contents gives a good overview of the current challenges in the field. From the paper, "Federated learning is a machine learning setting where multiple entities (clients) collaborate in solving a machine learning problem, under the coordination of a central server or service provider. Each client’s raw data is stored locally and not exchanged or transferred; instead, focused updates intended for…

Paper and discussion history. A mention is not an endorsement.