FedVideoMAE combines VideoMAE pretraining, LoRA adaptation, client DP-SGD and secure aggregation to cut federated communication 28x while reaching 65-66% accuracy under strong privacy on RWF-2000 with 40 clients.
Fedmae: Federated self-supervised learning with one-block masked auto-encoder
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Abstract-only report: theoretical comparison finds MIM more robust than CL to non-IID data in D-SSL and robustness scales with connectivity; MAR loss proposed as practical application.
citing papers explorer
-
FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation
FedVideoMAE combines VideoMAE pretraining, LoRA adaptation, client DP-SGD and secure aggregation to cut federated communication 28x while reaching 65-66% accuracy under strong privacy on RWF-2000 with 40 clients.