Research map / Federated learning and privacy / Communication-efficient FL
Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM
Ziba Parsons, Fei Dou, Houyi Du, Zheng Song, Jin Lu
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 RWSADMM instead of Ditto | personalized FL · MNIST, MLR | test accuracy (%): 97.37 \pm 0.02 -> 98.63 $ \pm $ 0.01 | Improved |
| Use RWSADMM instead of pFedMe | personalized FL · MNIST, MLP | test accuracy (%): 99.46$\pm$ 0.01 -> 99.29 $ \pm $ 0.02 | Hurt |
| Use RWSADMM instead of Ditto | personalized FL · MNIST, CNN | test accuracy (%): 99.20 \pm 0.11 -> 99.52 $ \pm $ 0.04 | Improved |
| Use RWSADMM instead of Ditto | personalized FL · Synthetic, MLR | test accuracy (%): 86.24 \pm 0.03 -> 96.44 $ \pm $ 0.12 | Improved |
| Use RWSADMM instead of pFedMe | personalized FL · Synthetic, MLP | test accuracy (%): 86.36\pm 0.15 -> 97.17 $ \pm $ 0.18 | Improved |
| Use RWSADMM instead of Ditto | personalized FL · CIFAR10, MLR | test accuracy (%): 75.2 \pm 0.01 -> 80.72 $\pm $ 0.11 | Improved |
| Use RWSADMM instead of Ditto | personalized FL · CIFAR10, MLP | test accuracy (%): 81.37 \pm 0.13 -> 84.99 $ \pm $ 0.20 | Improved |
| Use RWSADMM instead of Ditto | personalized FL · CIFAR10, CNN | test accuracy (%): 83.86 \pm 0.02 -> 87.08 $ \pm $ 0.03 | Improved |
| Use random-walk server movement and stochastic ADMM updates | mobilizing personalized FL · MNIST, MLP and CNN | convergence iterations: 200 iterations -> 600 iterations | Improved |
| Use RWSADMM instead of FedAvg | mobilizing FL · MNIST, MLR | training time (s): 384 -> 500 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Ditto — Ditto: Fair and Robust Federated Learning Through Personalization (ICML 2021) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability (NeurIPS 2024 · similarity 0.89)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.89)
- WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling (AAAI 2025 · similarity 0.88)
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.87)
- Decentralized Directed Collaboration for Personalized Federated Learning (CVPR 2024 · similarity 0.87)
- Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis (NeurIPS 2024 · similarity 0.87)
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.
