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.
Thirty-Sixth
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
GCD-FGL mitigates neighborhood absorption and global semantic inconsistency in federated generalized category discovery, delivering +4.86 average HRScore gain over baselines on five graph datasets.
FedEPD decouples topological purification from semantic recalibration using energy-guided pruning and prototype injection to improve minority performance in federated long-tailed graph learning.
Empirical comparison shows APPLE, FedGC, and FedProto outperform other PFL algorithms on MNIST, SignMNIST, and Digit5 using accuracy, precision, recall, and F1 score.
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.
-
Generalized Category Discovery in Federated Graph Learning
GCD-FGL mitigates neighborhood absorption and global semantic inconsistency in federated generalized category discovery, delivering +4.86 average HRScore gain over baselines on five graph datasets.
-
Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach
FedEPD decouples topological purification from semantic recalibration using energy-guided pruning and prototype injection to improve minority performance in federated long-tailed graph learning.
-
Pattern Recognition Tasks with Personalized Federated Learning
Empirical comparison shows APPLE, FedGC, and FedProto outperform other PFL algorithms on MNIST, SignMNIST, and Digit5 using accuracy, precision, recall, and F1 score.