同步操作将从 zhj/neural_factorization_machine 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
This is our implementation for the paper:
Xiangnan He and Tat-Seng Chua (2017). Neural Factorization Machines for Sparse Predictive Analytics. In Proceedings of SIGIR '17, Shinjuku, Tokyo, Japan, August 07-11, 2017.
We have additionally released our TensorFlow implementation of Factorization Machines under our proposed neural network framework.
Please cite our SIGIR'17 paper if you use our codes. Thanks!
Author: Dr. Xiangnan He (http://www.comp.nus.edu.sg/~xiangnan/)
python NeuralFM.py --dataset frappe --hidden_factor 64 --layers [64] --keep_prob [0.8,0.5] --loss_type square_loss --activation relu --pretrain 0 --optimizer AdagradOptimizer --lr 0.05 --batch_norm 1 --verbose 1 --early_stop 1 --epoch 200
The instruction of commands has been clearly stated in the codes (see the parse_args function).
The current implementation supports two tasks: regression and binary classification. The regression task optimizes RMSE, and the binary classification task optimizes Log Loss.
We use the same input format as the LibFM toolkit (http://www.libfm.org/).
Split the data to train/test/validation files to run the codes directly (examples see data/frappe/).
Last Update Date: May 11, 2017
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。