Research map / Federated learning and privacy / Communication-efficient FL
FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout
Irene Wang, Prashant J. Nair, Divya Mahajan
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 invariant-neuron dropout instead of Ordered Dropout | Federated learning with stragglers · Shakespeare, CIFAR10, FEMNIST | accuracy: maximum increase of 1.4% | Improved |
| Use invariant-neuron dropout instead of Random Dropout | Federated learning with stragglers · Shakespeare, CIFAR10, FEMNIST | accuracy: maximum accuracy gain of 1.6% points | Improved |
| Dynamically recalibrate stragglers and sub-model sizes at runtime | FLuID · Mobile-client training with changing stragglers | training time: 18% to 26% faster training time compared to the baseline | Improved |
| Use dynamic rather than static straggler selection | FLuID · Mobile-client training with changing stragglers | training time: 14% to 18% faster training time | Improved |
| Increase the invariant-neuron threshold from 1% to 8% (ablation) | Invariant Dropout · FEMNIST, sub-model size 0.75 | accuracy: 80.1 -> 80.7 | Improved |
| Increase the invariant-neuron threshold from 8% to 10% (ablation) | Invariant Dropout · FEMNIST, sub-model size 0.75 | accuracy: 80.7 -> 80.5 | Hurt |
| Cluster stragglers by capability and assign multiple sub-model sizes | FLuID · CIFAR10, FEMNIST, Shakespeare | accuracy: Invariant: 72.7, 78.2, 54.1; Ordered: 72.3, 77.4, 53.9 | Improved |
| Train stragglers on a 0.75-sized sub-model as straggler percentage rises (ablation) | Invariant Dropout · Shakespeare, CIFAR10, FEMNIST | accuracy | Hurt |
Closest papers by meaning
- FedSPU: Personalized Federated Learning for Resource-Constrained Devices with Stochastic Parameter Update (AAAI 2025 · similarity 0.89)
- FedEL: Federated Elastic Learning for Heterogeneous Devices (NeurIPS 2025 · similarity 0.88)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.88)
- TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients (AAAI 2024 · similarity 0.88)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.88)
- FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization (NeurIPS 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.
