HO-FL: Hybrid-Order Federated Learning for Heterogeneous Edge Devices

arXiv:2609.39074 · cs.LG, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/HKU-WILL-Lab/HO-FL

Terminology

• Edge Devices — 1× in this paper · explained in 2 episodes
• Federated Learning — 1× in this paper · explained in 17 episodes

Sources

• HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
• Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
• Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning
• Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimization
• HOSL: Hybrid-Order Split Learning for Memory-Constrained Edge Training
• Decoupled Weight Decay Regularization
• Qwen2.5 Technical Report
• OPT: Open Pre-trained Transformer Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks