Federated Learning with Matched Averaging — mentioned by amarcheschi

Sat, 12 Apr 2025 21:13:40 GMT

I did my undergrad internship on federated learning. I was tasked with implementing in a simulator different federated algorithms, so to have a way to compare them in a meaningful way. The last that had to be implemented was FedMA. We didn't manage to do it. That algorithm is absolutely devilish. Every issue that I solved made other two issue arise, and neither my supervisors could help. The sheer idea of matching neurons in different networks might (and does) make sense, but the way the approximate costs are calculated require other 2/3 math papers that I could follow for only the first…

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

Federated Learning with Matched Averaging · HackerPapers discussions

Federated Learning with Matched Averaging — mentioned by amarcheschi