Giter VIP home page Giter VIP logo

clsr's People

Contributors

davymorgan avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

clsr's Issues

对比学习实现的疑问

您好,我这里有三处疑虑希望跟您讨论交流。

  1. 文章中使用了Attention作为长期兴趣的编码器,LSTM+Attention作为短期兴趣的编码器,然而,他们的输入,都是等长的全历史序列。那么,Attention和LSTM+Attention这两个模块是如何体现所谓的对长期和短期的偏好的呢?还是说这种偏好是通过对比学习实现的?
  2. 文章中使用了Attention对全历史序列提取长期兴趣,用全历史序列的平均池化作为长期兴趣的代理。然而,我认为这个实现可能会使得Attention失效:因为可能存在平凡解——当Attention Score全部相等,且转换矩阵W为Identity的时候。您在实验中是否观察到这个问题?
  3. 这里的代理任务的设计,会不会使得长短期兴趣的编码能力最终退化到对长短期序列的平均池化的能力一致?

跑模型报错

Traceback (most recent call last):
ValueError: could not broadcast input array from shape (40) into shape (50)

跑模型遇到上面这个问题,是哪里出现问题了?直接改成40,跑出来精度很低,希望有空可以解答一下,谢谢

模型训练问题

作者您好,为什么我每次训练都是用的CPU跑的,更改了GPU-id,还是不行,请问怎么解决

Bug

请问一下作者sequential_reviews里面的kmeans_cuda是什么,一直在报错,是漏了代码还是安装包吗

模型相关问题

请问CLSR模型是如何解决冷启动问题,当用户是全新的/没有历史记录时,该模型是如何进展的?另外,需要的当前会话的最短长度是多少呢?

dataset

Hello, has the Kuaishou dataset been released? How to obtain the dataset?

请教一个小问题

请问您在调试代码的时候是怎么输出tensor的具体值的,我尝试了往上的各种方法都报错或者只是输出Tensor("mask:0", shape=(?, 50), dtype=int32),我也尝试了用tf.enable_eager_execution去掉问号问号的维度再进行sess.run输出值,依然报错,想跟您请教一下您项目调试的方法

Differences between the code and the paper

Hello,

Thank you for providing the code. I wonder if there are some differences between the code and the description in the paper? For example, you use a user_short_embedding as the initial state of the interest_evolve GRU and also propose a discrepency loss between the long and short-term user embedding. But these are not mentioned in the paper. Moreover, the short-term query in the paper is the q_s^{u,t} but you use the concatenation of the short_term_intention and the target_item_embedding as the short-term query in the code.

Thank you!

对比试验疑问

你好,我对您的实验十分感兴趣,请问您代码里的其他模型能不能直接拿来做对比实验,我试了一下您代码里集成的其他模型,但是失败了,请问需要做哪些调整?十分感谢!

data

感谢作者的贡献,本人小白入门,想咨询下您的数据集有下载链接吗?可以分享一下吗,感谢。

comparison experiments

Hello, the kuaishou dataset has not been published yet. Apart from Taobao dataset,are there any other datasets available for comparison experiments in this code? Any suggestions?Thanks!

Tensorflow版本问题

感谢作者的贡献,我想咨询一下您用的Tensorflow版本是1.15.2吗,为什么我用这个版本的tf跑代码的时候,一直报TF警告,比如The name tf.train.AdamOptimizer is deprecated. Please use tf.compat.v1.train.AdamOptimizer instead.之类的

Bug in model SLIREC

Thank u for your contribution
When I use SLIREC to do comparative experiments, It has the following error:
command i used: python sequential.py --dataset taobao --model SLIREC

File "sequential.py", line 350, in main
model = get_model(flags_obj, model_path, summary_path, user_vocab, item_vocab, cate_vocab, train_num_ngs)
File "sequential.py", line 116, in get_model
counterfactual_recent_k=flags_obj.counterfactual_recent_k,
File "/home/wb415/miniconda3/envs/ly3.6/lib/python3.6/site-packages/absl/flags/_flagvalues.py", line 481, in getattr
raise AttributeError(name)
AttributeError: counterfactual_recent_k

What's the reason? Thank you for your attention!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.