Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
cs.DC
Submitted: 2025-12-05
Updated: 2026-08-09
Code: https://github.com/machengjie321/FedGMR
Terminology
Sources
- LEAF: A Benchmark for Federated Settings
- Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
- Asynchronous Federated Optimization
Related papers
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends
- AgentWeave: Efficient Distributed Agent Serving via Flow Decomposition