yueliu1999 / dcrn Goto Github PK
View Code? Open in Web Editor NEW[AAAI 2022] An official source code for paper Deep Graph Clustering via Dual Correlation Reduction.
License: MIT License
[AAAI 2022] An official source code for paper Deep Graph Clustering via Dual Correlation Reduction.
License: MIT License
您好,请问能权重的预训练代码在哪里呢 项目里没找到?
您好,我根据您给出的预训练代码进行预训练,将该预训练参数文件放到模型中训练,acm和cite得到的acc在论文的acc范围内,但dblp的acc最好也才是77.42,始终比论文中的要低2,可是所有的预训练步骤都一样,该改的超参数也会相应的修改,这样可能是出了什么问题呢?
在`def model_init(model, X, y, A_norm):
"""
load the pre-train model and calculate similarity and cluster centers
Args:
model: Dual Correlation Reduction Network
X: input feature matrix
y: input label
A_norm: normalized adj
Returns: embedding similarity matrix
"""
# load pre-train model
model = load_pretrain_parameter(model)
# calculate embedding similarity
with torch.no_grad():
_, _, _, sim, _, _, _, Z, _, _ = model(X, A_norm, X, A_norm)
# calculate cluster centers
acc, nmi, ari, f1, centers = clustering(Z, y)
return sim, centers`中
_, _, _, sim, _, _, _, Z, _, _ = model(X, A_norm, X, A_norm)中X,A_norm出现了两次
在传入forward(self, X_tilde1, Am, X_tilde2, Ad)函数时是应该是x1一波和x2一波,
这样的话取平均好像好不取平均是一样的了 Z_ae = (Z_ae1 + Z_ae2) / 2
Z_igae = (Z_igae1 + Z_igae2) / 2
这个地方不太理解,可以解答一下吗?
Hello, I am also doing research on graph network now. Your article is very enlightening. I would like to ask, when I was looking for data sets, I found that data sets like CITEand DBLP are all in text or json format, and I could not find dataset with adjacency matrix and attribute data. I want to know whether your experimental data is processed by yourself and then experimented with these original data sets, or where you can find the data in graph format?
您好!請問一下DCRN可以用在類似於OFFICE數據集等無監督圖想聚類任務嗎?如果要應用,怎麼生成符合要求的.npy文件呢?
你好,我想请问一下,跑10次取平均,这10次的参数设置有什么不一样吗,是随机种子的设置不一样吗,如果是的话,那具体取什么值
你好,可以提供一下创建邻接矩阵的代码吗?
Congratulations to your paper, great work! I have some issues for your help. How can I can other datasets reported in your paper, like CITE, ACM, etc. Besides, how can I run the algorithm on my own datasets?
您好,請問使用batch-DCRN進行訓練時顯示
size mismatch for b: copying a param with shape torch.Size([10000, 20]) from checkpoint, the shape in current model is torch.Size([1]).
請問該怎麼解決呢?
你好,请问一下,预训练的代码在哪里呢?
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.