Research map / Federated learning and privacy / Personalized and heterogeneous FL
SFedPO: Streaming Federated Learning with a Prediction Oracle under Temporal Shifts
Jinrui Zhou, Haotian Xu, Xichong zhang, He Sun, Mingjun Xiao
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 |
|---|---|---|---|
| add SFedPO sampling and aggregation to FedAvg | FedAvg · CIFAR-10 (partial access) | test accuracy (%): +4.01 | Improved |
| add SFedPO sampling and aggregation to FedEXP | FedEXP · CIFAR-10 (partial access) | test accuracy (%): +7.76 | Improved |
| add SFedPO sampling and aggregation to FedAvg | FedAvg · Fashion-MNIST (partial access) | test accuracy (%): +0.13 | Improved |
| add SFedPO sampling and aggregation to FedProx | FedProx · CIFAR-10 (partial access) | test accuracy (%): +4.58 | Improved |
| add SFedPO sampling and aggregation to FedNTD | FedNTD · CINIC-10 (partial access) | test accuracy (%): +0.80 | Improved |
| add the Distribution-guided Data Sampling module (vs uniform sampling across latent states) (ablation) | SFedPO · CIFAR-10 (partial access) | test accuracy (%) | Improved |
| add the Shift-aware Aggregation Weights module (vs uniform aggregation) (ablation) | SFedPO · CIFAR-10 / CINIC-10 | test accuracy (%) | Improved |
| add oracle prediction noise eps from 0.00 to 0.10 | SFedPO · CIFAR-10 (full access) | test accuracy (%): 67.45 -> 66.95 | No clear effect |
| add oracle prediction noise eps from 0.00 to 0.10 | SFedPO · CIFAR-10 (partial access) | test accuracy (%): 63.52 -> 61.90 | Hurt |
| use SFedPO instead of DRSR | coreset/data selection · CIFAR-10 (partial access) | test accuracy (%): 48.42 -> 63.53 | Improved |
| use SFedPO instead of Flash with VGG16 | FL method · CIFAR-10 (full access, VGG16) | test accuracy (%): 27.45 -> 54.64 | Improved |
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.
- Flash — Flash: Concept Drift Adaptation in Federated Learning (ICML 2023) · better on 8 of 8 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
- Streaming Federated Learning with Markovian Data (NeurIPS 2025 · similarity 0.89)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.88)
- Adaptive Federated Learning with Auto-Tuned Clients (ICLR 2024 · similarity 0.87)
- Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability (NeurIPS 2024 · similarity 0.87)
- Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shifts (AAAI 2024 · similarity 0.86)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.86)
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.
