Research map / Federated learning and privacy / Communication-efficient FL
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning
Robert Hönig, Yiren Zhao, Robert Mullins
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 |
|---|---|---|---|
| Combine time-adaptive and client-adaptive quantization | Federated QSGD · Synthetic | compression factor vs. Federated QSGD: 2.81× | Improved |
| Combine time-adaptive and client-adaptive quantization | Federated QSGD · FEMNIST | compression factor vs. Federated QSGD: 1.70× | Improved |
| Combine time-adaptive and client-adaptive quantization | Federated QSGD · Sent140 | compression factor vs. Federated QSGD: 1.19× | Improved |
| Combine time-adaptive and client-adaptive quantization | Federated QSGD · Shakespeare | compression factor vs. Federated QSGD: 2.21× | Improved |
| Combine time-adaptive and client-adaptive quantization | Federated QSGD · CelebA | compression factor vs. Federated QSGD: 1.20× | Improved |
| Add client-adaptive quantization (ablation) | DAdaQuant time · Synthetic | compression factor vs. uncompressed: 37× -> 48× | Improved |
| Add client-adaptive quantization (ablation) | DAdaQuant time · FEMNIST | compression factor vs. uncompressed: 4518× -> 4772× | Improved |
| Add client-adaptive quantization (ablation) | DAdaQuant time · Sent140 | compression factor vs. uncompressed: 93× -> 108× | Improved |
| Add client-adaptive quantization (ablation) | DAdaQuant time · Shakespeare | compression factor vs. uncompressed: 12× -> 21× | Improved |
| Add client-adaptive quantization (ablation) | DAdaQuant time · CelebA | compression factor vs. uncompressed: 716× -> 775× | Improved |
| Add time-adaptive quantization (ablation) | DAdaQuant clients · Synthetic | compression factor vs. uncompressed: 26× -> 48× | Improved |
| Add time-adaptive quantization (ablation) | DAdaQuant clients · FEMNIST | compression factor vs. uncompressed: 3017× -> 4772× | Improved |
Closest papers by meaning
- FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates (ICML 2025 · similarity 0.88)
- Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices (CVPR 2024 · similarity 0.87)
- Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity (AAAI 2024 · similarity 0.87)
- Stochastic Controlled Averaging for Federated Learning with Communication Compression (ICLR 2024 · similarity 0.87)
- Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization (ICLR 2025 · similarity 0.87)
- Accelerating Federated Learning with Quick Distributed Mean Estimation (ICML 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.
