Research map / Federated learning and privacy / Communication-efficient FL
Distributed Learning over Unreliable Networks
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 |
|---|---|---|---|
| allow 1% message loss during model averaging (ablation) | RPS · CIFAR-10, ResNet110 and ResNet20 | training loss | No clear effect |
| allow 5% message loss during model averaging (ablation) | RPS · CIFAR-10, ResNet110 | training loss | No clear effect |
| allow 5% message loss during model averaging (ablation) | RPS · CIFAR-10, ResNet20 | training loss: increased by 0.02 | Hurt |
| allow 10% packet loss during model averaging (ablation) | RPS · CIFAR-10, ResNet110 and ResNet20 | training loss: 0.03; 0.11 | Hurt |
| allow 1%, 5%, or 10% packet loss (ablation) | RPS · ATIS | training loss: increase of 0.01 | Hurt |
| use gradient averaging instead of model averaging with 1% communication loss (ablation) | distributed SGD · CIFAR-10, ResNet110 and ResNet20 | accuracy | Hurt |
| prioritize Web service traffic, allowing 10% learning-update loss | colocated Web service and RPS training · emulated Web service | speed-up: 1.2× | Helped |
Closest papers by meaning
- Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training (ICML 2024 · similarity 0.83)
- Online Classification with Predictions (NeurIPS 2024 · similarity 0.83)
- Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outliers (AAAI 2024 · similarity 0.83)
- A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint) (AAAI 2024 · similarity 0.82)
- Distributed Event-Based Learning via ADMM (ICML 2025 · similarity 0.82)
- Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML (NeurIPS 2024 · 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.