Research map / Federated learning and privacy / Communication-efficient FL
$D^2$: Decentralized Training over Decentralized Data
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the D² variance-reduction update using current and previous local models and stochastic gradients | D-PSGD · TransferLearning, unshuffled ImageNet | training loss convergence | Helped |
| Add the D² variance-reduction update using current and previous local models and stochastic gradients | D-PSGD · LeNet on CIFAR10, unshuffled | convergence | Helped |
| Add the D² variance-reduction update using current and previous local models and stochastic gradients | D-PSGD · TransferLearning and LeNet, shuffled data | convergence rate | No clear effect |
Closest papers by meaning
- DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations (AAAI 2024 · similarity 0.85)
- Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training (NeurIPS 2025 · similarity 0.84)
- From Promise to Practice: Realizing High-performance Decentralized Training (ICLR 2025 · similarity 0.83)
- Byzantine-Robust Decentralized Learning via Remove-then-Clip Aggregation (AAAI 2024 · similarity 0.83)
- Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training (ICML 2024 · similarity 0.82)
- Competitive Advantage Attacks to Decentralized Federated Learning (NeurIPS 2025 · similarity 0.82)
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.