librahu / hegan Goto Github PK
View Code? Open in Web Editor NEWSource code for KDD 2019 paper "Adversarial Learning on Heterogeneous Information Networks"
Source code for KDD 2019 paper "Adversarial Learning on Heterogeneous Information Networks"
您好,非常感谢您所做的工作!有个问题我不太明白:
在链路预测任务中使用的yelp数据集只是包含user和business吗?就是yelp_ub.train_0.8_lr,而不是用的yelp_triple,不知道我理解的对吗?
期待您的回复。
您好,我想问一下,在你论文中,dblp_pre_train.emb这个文件中的embedding在代码中是什么作用呢,
self.node_embed_init_d = utils.read_embeddings(filename=config.pretrain_node_emb_filename_d,
n_node=self.n_node,
n_embed=config.n_emb)且在这个read_embedding中,embedding_matrix = np.random.rand(n_node, n_embed),为什么会随机生成矩阵呢,这个embedding是节点的初始信息吗?如果是,那不同类型的节点信息维度是不是应该不一样??
Hello, I want to have a try on aminer dataset but there is no aminer pre-train file in the pre-train folder, can you please tell me how to get the aminer dataset`s pre-train flie or is there any way to generate it?
请问从generator和discriminator得到的向量哪个更好呢?是采用训练20个epoch后得到的节点向量吗?
Hi! It seems that several key files are missed like “*_ap.train_0.8_lr, *_ap.test_0.8_new, *rel_embeddings.txt, etc.” or the scripts to generate those input files, for link prediction experiment. Would you like to submit those files for a kind reproducible source code?
hello,Can you provide the “rel_embedding.txt” file or explain it?
你好,我在阅读代码的时候发现dblp_evaluation.py 和 yelp_evaluation.py 中需要用到 dblp_ap.train_0.8_lr 和 yelp_ub.train_0.8_lr 等等数据集,但是没有找到对应的文件,请问这两个数据集如何得到呢?
感谢你所做的工作,期待你的回复
What relations do the values of "relation" represent in a and b? as in dblp.dat:
p -> a : 0
a -> p : 1
p -> c : 2
c -> p : 3
p -> t : 4
t -> p : 5
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.