STAGE builds a shared semantic space through feature translation and controlled graph propagation to reduce semantic drift in multimodal federated graph learning, delivering state-of-the-art results with lower communication cost.
Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks
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
-
STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning
STAGE builds a shared semantic space through feature translation and controlled graph propagation to reduce semantic drift in multimodal federated graph learning, delivering state-of-the-art results with lower communication cost.