FedMGS formalizes modality-imbalanced MM-FGL as latent semantic synthesis and uses availability-aware encoding, prototype-guided synthesis, and reliability-calibrated fusion to recover missing modalities, reporting up to 17.41% gains on four tasks.
Proceedings of the AAAI Conference on Artificial Intelligence37, 8 (2023), 9953–9961
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approach
FedMGS formalizes modality-imbalanced MM-FGL as latent semantic synthesis and uses availability-aware encoding, prototype-guided synthesis, and reliability-calibrated fusion to recover missing modalities, reporting up to 17.41% gains on four tasks.