Research map / Federated learning and privacy / Personalized and heterogeneous FL
Practical Federated Gradient Boosting Decision Trees
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 SimFL similarity-based weighted-gradient training instead of local-only GBDT | GBDT · a9a, unbalanced partition | test error: 19.1% -> 17.0% | Helped |
| Use SimFL similarity-based weighted-gradient training instead of local-only GBDT | GBDT · cod-rna, unbalanced partition | test error: 8.2% -> 6.5% | Helped |
| Use SimFL similarity-based weighted-gradient training instead of local-only GBDT | GBDT · real-sim, unbalanced partition | test error: 11.8% -> 8.3% | Helped |
| Use SimFL similarity-based weighted-gradient training instead of local-only GBDT | GBDT · ijcnn1, unbalanced partition | test error: 4.9% -> 4.5% | Helped |
| Use SimFL similarity-based weighted-gradient training instead of local-only GBDT | GBDT · SUSY, unbalanced partition | test error: 25.4% -> 23.3% | Helped |
| Use SimFL similarity-based weighted-gradient training instead of local-only GBDT | GBDT · HIGGS, unbalanced partition | test error: 37.1% -> 30.9% | Helped |
| Use SimFL instead of local-only GBDT | GBDT · a9a, balanced partition | test error: 15.5% -> 15.1% | Helped |
| Use SimFL instead of local-only GBDT | GBDT · cod-rna, balanced partition | test error: 6.4% -> 6.0% | Helped |
| Use SimFL instead of local-only GBDT | GBDT · real-sim, balanced partition | test error: 8.4% -> 7.1% | Helped |
| Use SimFL instead of local-only GBDT | GBDT · ijcnn1, balanced partition | test error: 3.8% -> 3.6% | Helped |
| Use SimFL instead of local-only GBDT | GBDT · SUSY, balanced partition | test error: 20.1% -> 19.6% | Helped |
| Use SimFL instead of local-only GBDT | GBDT · HIGGS, balanced partition | test error: 30.2% -> 29.3% | Helped |
Closest papers by meaning
- Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning (AAAI 2025 · similarity 0.87)
- Effective and Efficient Federated Tree Learning on Hybrid Data (ICLR 2024 · similarity 0.86)
- Principled Federated Random Forests for Heterogeneous Data (NeurIPS 2026 · similarity 0.86)
- DictPFL: Efficient and Private Federated Learning on Encrypted Gradients (NeurIPS 2025 · similarity 0.85)
- FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees (ICML 2024 · similarity 0.85)
- Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data (NeurIPS 2024 · similarity 0.85)
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.