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.
Federated mutual learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
FedTSP builds class prototypes from LLM-generated text descriptions via PLMs and trainable prompts to preserve semantic relationships and reduce heterogeneity effects in federated learning.
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.
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.
-
Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
FedTSP builds class prototypes from LLM-generated text descriptions via PLMs and trainable prompts to preserve semantic relationships and reduce heterogeneity effects in federated learning.
-
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.