in batch 负采样

[yexiao1107]

Please refer to the FAQ in doc and search for the related issues before you ask the question.

Describe the question(问题描述) A clear and concise description of what the question is. 大佬，不知道dssm对于in batch 负采样如何实现，我自己在训练数据时候发现如果随机负采样，user embedding没有区分度，但是item embedding是有区分度的，查阅资料有同学说可能是将item的冷热做了区分，并没有学习到user的兴趣，请问对于双塔模型这块 有什么调优的经验吗 Additional context Add any other context about the problem here.

Operating environment(运行环境):

• python version [e.g. 3.6]
• tensorflow version [e.g. 1.4.0,]
• deepmatch version [e.g. 0.2.0,]

[johndkl]

https://zhuanlan.zhihu.com/p/358544636 实测有效

[guixianjin]

in-batach 负采样 还可以参考：https://zhuanlan.zhihu.com/p/336509201 或者 https://zhuanlan.zhihu.com/p/518561076

[shenweichen]

deepmatch v0.3.0版本开始已经支持了inbatch负采样，使用方法可参考 https://github.com/shenweichen/DeepMatch/blob/master/examples/colab_MovieLen1M_DSSM_InBatchSoftmax.ipynb