FedMPO recovers missing modalities via topology-aware generation, filters noisy recoveries with missing-aware routing, and uses reliability-aware aggregation to achieve up to 5.65% gains over baselines in high-missing and non-IID federated graph settings.
arXiv preprint arXiv:2402.05322 , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
SUPRA resolves the aggregation dilemma in MAGL by decoupling modality-specific MLP paths from a shared lightweight GNN, achieving SOTA performance with 3.5x lower memory and 4.4x faster training.
FDQ improves stability in multimodal graph unlearning by using feature-dimension aware quantile selection to protect sensitive high-dimensional layers while preserving utility and enabling effective forgetting.
citing papers explorer
-
Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
FedMPO recovers missing modalities via topology-aware generation, filters noisy recoveries with missing-aware routing, and uses reliability-aware aggregation to achieve up to 5.65% gains over baselines in high-missing and non-IID federated graph settings.
-
Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs
SUPRA resolves the aggregation dilemma in MAGL by decoupling modality-specific MLP paths from a shared lightweight GNN, achieving SOTA performance with 3.5x lower memory and 4.4x faster training.
-
Stable Multimodal Graph Unlearning via Feature-Dimension Aware Quantile Selection
FDQ improves stability in multimodal graph unlearning by using feature-dimension aware quantile selection to protect sensitive high-dimensional layers while preserving utility and enabling effective forgetting.