Research map / Federated learning and privacy / Personalized and heterogeneous FL
Flash: Concept Drift Adaptation in Federated Learning
Kunjal Panchal, Sunav Choudhary, Subrata Mitra, Koyel Mukherjee, Somdeb Sarkhel, Saayan Mitra, Hui Guan
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 FLASH (drift-aware adaptive optimizer with early-stopping client training) instead of FedYogi | FL with no concept drift · EMNIST, Stackoverflow, Shakespeare, CIFAR10/100 (Table 1) | generalized accuracy | Mixed |
| Use FLASH instead of FedYogi under incremental concept drift | FL with incremental drift · EMNIST, CIFAR10, CIFAR100 incremental drift (Table 2) | accuracy dip (%) | Improved |
| Use FLASH instead of FedYogi under incremental concept drift | FL with incremental drift · EMNIST, CIFAR10, CIFAR100 incremental drift (Table 2) | rounds till recovery | Improved |
| Use early-stopping client training instead of fixed-epoch training (E=5) (ablation) | FLASH on CIFAR10 · no drift and sudden drift at round 2000 | personalized accuracy | Improved |
| Use FLASH instead of FedYogi (computation savings) | FL after sudden concept drift · CIFAR10, CIFAR100 sudden drift | epochs per round after drift: 11.18-11.79% fewer epochs | Improved |
Later papers that compared with this method
3 later accepted papers report Flash as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- SFedPO: Streaming Federated Learning with a Prediction Oracle under Temporal Shifts (ICML 2026 · better on 8 of 8 shared results)
- SparsyFed: Sparse Adaptive Federated Learning (ICLR 2025 · better on 6 of 6 shared results)
- Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning (NeurIPS 2023 · better on 3 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- FedDC — FedDC: Federated Learning With Non-IID Data via Local Drift Decoupling and Correction (CVPR 2022) · better on 0 of 1 shared result
- DITTO — Ditto: Fair and Robust Federated Learning Through Personalization (ICML 2021) · better on 1 of 1 shared result
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
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.88)
- Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift (NeurIPS 2024 · similarity 0.88)
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning (NeurIPS 2025 · similarity 0.86)
- Adaptive Federated Learning with Auto-Tuned Clients (ICLR 2024 · similarity 0.86)
- FedImpro: Measuring and Improving Client Update in Federated Learning (ICLR 2024 · similarity 0.86)
- Efficient Adaptive Federated Optimization (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.
