DSIN icon indicating copy to clipboard operation
DSIN copied to clipboard

Code for the IJCAI'19 paper "Deep Session Interest Network for Click-Through Rate Prediction"

Results 17 DSIN issues
Sort by recently updated
recently updated
newest added

Hello, I am running you baseline train_dien.py add ` names = [weight.name for layer in model.layers for weight in layer.weights] weights = model.get_weights() for name, weight in zip(names, weights): print(name,...

从2_gen_dien_input.py 和 2_gen_dsin_input.py 这两个文件中,看到dien生成的数据是选择第1个session中最新的数据;而dsin生成的数据是把最新的session中最新数据放至sess_0。 所以,这里我有两个问题: 1.dsin和dien本身输入的数据不同,是否因为这个会导致实验结果有差异 2.dsin是将最新数据放在sess_0,因此在段间兴趣提取层,实际上是学习了一个从现在到过去的演化过程(当然,您论文中用的是bi-lstm,是双向学习)。那如果是换个顺序存储sess数据,那结果是否会有变化。 嗯,上面这些只是一些想法,还没有进行验证。 或许,您能帮忙解释一下,当初您为什么采用这种策略生成输入数据。

作者你好,以下有两个问题,希望您能解答. 第一点:在你论文中Qk应该指用户的第k个session矩阵, 但是在论文后面 ![image](https://user-images.githubusercontent.com/17669403/59249204-d2030480-8c56-11e9-82a5-5cd1d5b105b7.png) 这个Qk好像和原来意思不一样啊?能帮忙解释一下具体含义吗? 第二点:我看过Attention is All your need论文,我发现你论文中的参数矩阵应该是不同session之间是不同的.而你的论文中看起来所有参数矩阵W^Q都一样. ![image](https://user-images.githubusercontent.com/17669403/59249550-a6344e80-8c57-11e9-82c7-0d230c96f5d0.png)

想问一下您,在taobao ad数据集上,最终的AUC是能够得到论文中结果的嘛? 因为我按照您的这个流程走下来,使用了5%的ad数据集(受硬件环境限制),但是最后AUC只有0.5+, 我就很怀疑是我哪里没有弄对吗?

Bumps [joblib](https://github.com/joblib/joblib) from 0.13.2 to 1.2.0. Changelog Sourced from joblib's changelog. Release 1.2.0 Fix a security issue where eval(pre_dispatch) could potentially run arbitrary code. Now only basic numerics are supported....

dependencies

Bumps [requests](https://github.com/psf/requests) from 2.27.1 to 2.31.0. Release notes Sourced from requests's releases. v2.31.0 2.31.0 (2023-05-22) Security Versions of Requests between v2.3.0 and v2.30.0 are vulnerable to potential forwarding of Proxy-Authorization...

dependencies

Bumps [tensorflow-gpu](https://github.com/tensorflow/tensorflow) from 1.4.0 to 2.12.0. Release notes Sourced from tensorflow-gpu's releases. TensorFlow 2.12.0 Release 2.12.0 TensorFlow Breaking Changes Build, Compilation and Packaging Removed redundant packages tensorflow-gpu and tf-nightly-gpu. These...

dependencies