Research map / Federated learning and privacy / Personalized and heterogeneous FL
OPTION: An Online Pricing Strategy for Asynchronous Federated Learning Against Free-Riding Attacks
Bangqi Pan, Jianfeng Lu, Shuqin Cao, Xiao Zhang, Gang Li, Guanghui Wen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use OPTION online pricing instead of FRAD | asynchronous FL · CIFAR-10 | global test accuracy: 78.35 -> 85.25 | Improved |
| use OPTION instead of ANALYTICS | asynchronous FL · CIFAR-10 | global test accuracy: 72.21 -> 85.25 | Improved |
| use OPTION instead of OIMAF | asynchronous FL · CIFAR-10 | average client accuracy: 73.34 -> 81.65 | Improved |
| use OPTION instead of FRAD | asynchronous FL · CINIC-10 | global test accuracy: 24.49 -> 40.95 | Improved |
| use OPTION instead of OIMAF | asynchronous FL · MNIST | global test accuracy: 92.42 -> 93.76 | Improved |
| replace linear convergence model with non-convex objective (NCX-OPTION) (ablation) | OPTION · CINIC-10 | global test accuracy: 40.95 -> 42.47 | Improved |
| replace linear convergence model with non-convex objective (NCX-OPTION) (ablation) | OPTION · CIFAR-10 | global test accuracy: 85.25 -> 82.33 | Hurt |
| replace linear convergence model with non-convex objective (NCX-OPTION) (ablation) | OPTION · MNIST | average client accuracy: 93.41 -> 91.43 | Hurt |
| use OPTION closed-form pricing instead of FRAD/OIMAF pricing | pricing computation · cumulative calculation time | computation time reduction: 75.42% and 85.78% reduction | Improved |
| use OPTION online pricing instead of next best online pricing | asynchronous FL · offline devices | valid client updates: 23.97% | Improved |
| lower penalty coefficient mu (0.01 to 0.001) (ablation) | utility queue length · UTYLength | queue length | Improved |
Closest papers by meaning
- FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning (AAAI 2025 · similarity 0.87)
- Efficient Asynchronous Federated Learning with Prospective Momentum Aggregation and Fine-Grained Correction (AAAI 2024 · similarity 0.87)
- Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning (ICML 2025 · similarity 0.87)
- Multi-Session Budget Optimization for Forward Auction-based Federated Learning (ICML 2025 · similarity 0.87)
- Reputation-aware Revenue Allocation for Auction-based Federated Learning (AAAI 2025 · similarity 0.86)
- Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learning (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
