AI Paper Atlas

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

JMLR 2021 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Vertical federated learning · 156 citations (OpenAlex)

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 changedWhereMeasuredEffect
use distributed instead of standalone deploymentFATE logistic regression · LIBSVM two-party LR, 10000k samples, 100/100 featuresper-iteration cost (seconds): 12754s -> 2267sImproved
use distributed instead of standalone deploymentFATE logistic regression · LIBSVM two-party LR, 400k samples, 1000/1000 featuresper-iteration cost (seconds): 4420s -> 1252sImproved
use distributed instead of standalone deploymentFATE XGBoost · LIBSVM two-party XGBoost, 400k samples, 1000/1000 featuresper-iteration cost (seconds): 2021s -> 960sImproved
use distributed instead of standalone deploymentFATE XGBoost · LIBSVM two-party XGBoost, 10000k samples, 100/100 featuresper-iteration cost (seconds): 9499s -> 1112sImproved
use distributed instead of standalone deploymentFATE logistic regression · LIBSVM two-party LR, 100k samples, 200/20 featuresper-iteration cost (seconds): 128s -> 67sImproved
use distributed instead of standalone deploymentFATE XGBoost · LIBSVM two-party XGBoost, 100k samples, 200/20 featuresper-iteration cost (seconds): 198s -> 206sNo clear effect
add privacy-preserving encrypted computation vs plain Sklearnlogistic regression · LIBSVM two-party LR, 100k samples, 200/20 featuresper-iteration cost (seconds): 0.3s -> 67sHurt
add privacy-preserving distributed training vs plain SklearnXGBoost · LIBSVM two-party XGBoost, 10000k samples, 100/100 featuresper-iteration cost (seconds): 1170s -> 1112sNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy