MMiC combines one-layer parameter substitution, Banzhaf-inspired client selection, and Markowitz-inspired global aggregation to report top global and personalized results on multiple multimodal federated learning benchmarks with missing modalities.
Fleet, Jamie Ryan Kiros, and Sanja Fidler
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MMiC: Mitigating Modality Incompleteness in Clustered Federated Learning
MMiC combines one-layer parameter substitution, Banzhaf-inspired client selection, and Markowitz-inspired global aggregation to report top global and personalized results on multiple multimodal federated learning benchmarks with missing modalities.