FATE
FATE copied to clipboard
An Industrial Grade Federated Learning Framework
评分卡模型在实际使用当中需要模型中的逻辑回归的权重都大于零,那么在fate中如何实现这个呢?
Version: 1.9.0 I have developped a new HomoGraph plugin similar to HomoNN(the demo in FATE). but it always stucked when try to get the loss and other variables from the...
1 问题描述: SBT 算法 regression 任务 使用 tweedie loss 无法收敛。 如下图 2 所用数据:scikit learn 种的 tweedie loss 样例,所使用的“ French Motor Third-Party Liability Claims dataset”。该数据符合 tweedie distribution,适合测试 tweedie loss。 https://scikit- learn.org/stable/auto_examples/linear_model/plot_tweedie_regression_insurance_...
用已编译安装包安装单机版时执行bash init.sh init时出现: [INFO] env dir: /root/standalone_fate_install_1.9.0_release/env [INFO] jdk dir: /root/standalone_fate_install_1.9.0_release/env/jdk/jdk-8u192 [INFO] venv dir: /root/standalone_fate_install_1.9.0_release/env/python/venv [INFO] kernel: Linux [INFO] linux system: CentOS Linux [INFO] os: CentOS [INFO] is root user...
1.安装了pycharm,怎么将fate作为项目添加进去并调试? 2.pycharm是不是只能安专业版的? 3.有没有用pycharm调试FATE的教程?
hetero_feature_selection特征选择模块怎样使用的呢?按照里面的示例试完在之后的步骤特征数量并未减少
能否在 python/federatedml/ensemble/secureboost/hetero_secoreboost/hetero_secureboost_guest.py/host.py 目录下直接修改代码逻辑,进行一些自己的实验运行呢?
在加入特征选择模块后报错RuntimeError:The model weights are overflow,please check if the input data has been normalized
**Describe the bug** Running failed when I increase number of trees in homo secure boost algorithm. **To Reproduce** Steps to reproduce the behavior: when I change num_trees from 10 to...
**Describe the bug** Hi, I am trying to have confusion matrix for homo secure boost algorithm. I will appreciate it if you let me know how can I add and...