Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Nearest Neighbor Classification with a Colony of Fruit-Flies
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 |
|---|---|---|---|
| Use sparse FlyHash with per-class bloom filters instead of binary SimHash bloom filters (ablation) | FlyNN · OpenML classification datasets | normalized accuracy: 25.4% | Helped |
| Use FlyNN instead of tuned kNNC | OpenML classification datasets · OpenML classification datasets | normalized accuracy: 0.35% | No clear effect |
| Use FlyNN instead of 1NNC | OpenML classification datasets · OpenML classification datasets | normalized accuracy: 2.36% | Helped |
| Increase FlyHash lifted dimensionality m (ablation) | FlyNN · Classification datasets | accuracy | Helped |
| Increase FlyHash sparsity parameter ρ beyond a suitable point without also increasing m (ablation) | FlyNN · Classification datasets | accuracy | Hurt |
| Increase decay rate γ from 0 to a positive value (ablation) | FlyNN · Classification datasets | accuracy | Helped |
| Vary γ among positive values (ablation) | FlyNN · Classification datasets | accuracy | No clear effect |
| Enable differential privacy and increase the number of sampled entries T (ablation) | FlyNNFL · Synthetic data | performance | Mixed |
| Increase privacy parameter ϵ (ablation) | FlyNNFL · Synthetic data | performance | Helped |
| Train FlyNN across 16 parties rather than on one party | FlyNNFL · Distributed training | speedup: up to 8× | Helped |
Closest papers by meaning
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.84)
- Recurrent Early Exits for Federated Learning with Heterogeneous Clients (ICML 2024 · similarity 0.83)
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data (ICLR 2024 · similarity 0.83)
- Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation (NeurIPS 2025 · similarity 0.83)
- HaCore: Efficient Coreset Construction with Locality Sensitive Hashing for Vertical Federated Learning (AAAI 2025 · similarity 0.83)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.83)
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.