Research map / Federated learning and privacy / Communication-efficient FL
An Efficient Framework for Clustered Federated Learning
Avishek Ghosh, Jichan Chung, Dong Yin, Kannan Ramchandran
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 IFCA cluster-specific models instead of a single global model | IFCA · Rotated MNIST (m=4800, n=50) | test accuracy (%): 86.74 -> 94.20 | Improved |
| use IFCA instead of a single global model | IFCA · Rotated MNIST (m=1200, n=200) | test accuracy (%): 89.73 -> 95.25 | Improved |
| use IFCA instead of a single global model | IFCA · Rotated CIFAR (m=200, n=500) | test accuracy (%): 77.87 -> 81.51 | Improved |
| use IFCA instead of purely local training | IFCA · Rotated CIFAR (m=200, n=500) | test accuracy (%): 33.97 -> 81.51 | Improved |
| use IFCA instead of purely local training | IFCA · Rotated MNIST (m=4800, n=50) | test accuracy (%): 63.32 -> 94.20 | Improved |
| more samples per machine n (fewer machines m), with mn fixed | local model baseline · Rotated MNIST | test accuracy (%): 63.32 -> 80.05 | Improved |
| more samples per machine n (fewer machines m), with mn fixed | IFCA · Rotated MNIST | test accuracy (%): 94.20 -> 95.25 | Improved |
| use IFCA with weight sharing instead of global model | IFCA · FEMNIST | test accuracy (%): 84.45 -> 87.99 | Improved |
| use IFCA with weight sharing instead of local model | IFCA · FEMNIST | test accuracy (%): 75.85 -> 87.99 | Improved |
| replace one-shot centralized clustering with iterative IFCA (k=2) | IFCA · FEMNIST | test accuracy (%): 87.41 -> 87.99 | No clear effect |
| replace one-shot clustering with IFCA (k=3) | IFCA · FEMNIST | test accuracy (%): 87.38 -> 87.89 | No clear effect |
| increase number of clusters k from 2 to 3 (ablation) | IFCA · FEMNIST | test accuracy (%): 87.99 -> 87.89 | No clear effect |
Closest papers by meaning
- Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies (ICLR 2025 · similarity 0.91)
- Clustered Federated Learning via Gradient-based Partitioning (ICML 2024 · similarity 0.91)
- Interaction-Aware Gaussian Weighting for Clustered Federated Learning (ICML 2025 · similarity 0.89)
- Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis (NeurIPS 2024 · similarity 0.88)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.88)
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · 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.
