Research map / Federated learning and privacy / Personalized and heterogeneous FL
FATE: An Industrial Grade Platform for Collaborative Learning With Data Protection
Yang Liu, Tao Fan, Tianjian Chen, Qian Xu, Qiang Yang
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 distributed instead of standalone deployment | FATE logistic regression · LIBSVM two-party LR, 10000k samples, 100/100 features | per-iteration cost (seconds): 12754s -> 2267s | Improved |
| use distributed instead of standalone deployment | FATE logistic regression · LIBSVM two-party LR, 400k samples, 1000/1000 features | per-iteration cost (seconds): 4420s -> 1252s | Improved |
| use distributed instead of standalone deployment | FATE XGBoost · LIBSVM two-party XGBoost, 400k samples, 1000/1000 features | per-iteration cost (seconds): 2021s -> 960s | Improved |
| use distributed instead of standalone deployment | FATE XGBoost · LIBSVM two-party XGBoost, 10000k samples, 100/100 features | per-iteration cost (seconds): 9499s -> 1112s | Improved |
| use distributed instead of standalone deployment | FATE logistic regression · LIBSVM two-party LR, 100k samples, 200/20 features | per-iteration cost (seconds): 128s -> 67s | Improved |
| use distributed instead of standalone deployment | FATE XGBoost · LIBSVM two-party XGBoost, 100k samples, 200/20 features | per-iteration cost (seconds): 198s -> 206s | No clear effect |
| add privacy-preserving encrypted computation vs plain Sklearn | logistic regression · LIBSVM two-party LR, 100k samples, 200/20 features | per-iteration cost (seconds): 0.3s -> 67s | Hurt |
| add privacy-preserving distributed training vs plain Sklearn | XGBoost · LIBSVM two-party XGBoost, 10000k samples, 100/100 features | per-iteration cost (seconds): 1170s -> 1112s | No clear effect |
Closest papers by meaning
- Federated Learning via Input-Output Collaborative Distillation (AAAI 2024 · similarity 0.84)
- PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture (NeurIPS 2025 · similarity 0.83)
- Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data (NeurIPS 2024 · similarity 0.83)
- Co-Dream: Collaborative Dream Synthesis over Decentralized Models (AAAI 2025 · similarity 0.83)
- Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration (NeurIPS 2024 · similarity 0.82)
- Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning (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.
