librahu / mcrec Goto Github PK
View Code? Open in Web Editor NEWSource code for KDD 2018 paper "Leverage Meta-path based Context for Top-N Recommendation with a Neural Co-Attention Model"
Source code for KDD 2018 paper "Leverage Meta-path based Context for Top-N Recommendation with a Neural Co-Attention Model"
麻烦你,我想问一下,论文4.4.1中,基于元路径上下文的注意力中,两层注意力分别表示什么意思啊?即公式(6)(7).
Hello,
Thank you for the code.
I am curious how do you process the data?
It seems to already be in embedding state, do you have the code
where you embed the user, movie, and the meta-path?
my environment is Theano (1.0.1) , Keras (2.1.1) ubuntu 16.04, here is the specific error
Traceback (most recent call last):
File "/home/zxj/PycharmProjects/MCRec/code/MCRec.py", line 495, in
model = get_model(num_users, num_items, path_nums, timestamps, length, layers, reg_layes, latent_dim, reg_latent)
File "/home/zxj/PycharmProjects/MCRec/code/MCRec.py", line 267, in get_model
umtm_latent = get_umtm_embedding(umtm_input, path_nums[0], timestamps[0], length, user_latent, item_latent, path_attention_layer_1, path_attention_layer_2)
File "/home/zxj/PycharmProjects/MCRec/code/MCRec.py", line 103, in get_umtm_embedding
output = Dropout(0.5)(output)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 603, in call
output = self.call(inputs, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/layers/core.py", line 117, in call
training=training)
File "/usr/local/lib/python2.7/dist-packages/keras/backend/theano_backend.py", line 1503, in in_train_phase
x = theano.ifelse.ifelse(training, x, alt)
AttributeError: 'module' object has no attribute 'ifelse'
I hope you can kindly help me solve this problems! Thank you very much!
Hi! The contents in ml-100k.test.rating
and ml-100k.test.negative
do not match the descriptions in README.md. Could you please update README.md for a revised dataset description?
Hi author:
I just want to know whether there is a batch implementation available? Than you very much!
作者好,我今年刚上研一,接触HIN。想请教一下作者,如何利用Knn处理u-u和m-m的关系。如果方便的话能提供下处理的代码吗,万分感谢
您好,想请问一下关于Yelp数据集的预处理,希望您方便的时候公开一下这部分的代码
如何生成User_embedding, Item_embedding, Cate_embedding, City_embedding,
看到您在别的回答里面提到用Metapath2Vec, HIN2vec,以及HERec中的处理方式得到embedding
我首先试图尝试HERec中的处理方法,发现一个问题
通过UBU UBCaBU等MetaPath得到, UU的邻接矩阵,通过DeepWalk得到user_embedding
通过BCaB, BUB等MetaPath得到, BB的邻接矩阵,通过DeepWalk得到bussiness_embedding
然而这两个embedding是不同空间的,彼此也没有约束
在您现在MCRec的代码里,直接用user_embedding和bussiness_embedding来计算sim是由问题的,请问用HERec中的方法生成embedding是否合适?
另外非常迫切希望您能公布一下Yelp预处理的代码,以及模型运行的代码。
我们也在做HIN中的Link Prediction的工作,希望能够引用您的论文。如果您能提供处理Yelp的代码的话,应该会比我们复现有着更好的精度和效果
您好,movielens数据集中并没有user-user以及movie-movie的关系,从下面的代码可以看出您是通过k近邻获取这两个关系的,请问方便提供生成uufile、mmfile的代码或者这两个文件吗?谢谢!
uufile = '../data/ml-100k.uu_knn_50'
mmfile = '../data/ml-100k.mm_knn_50'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.