Light

cgao-comp / dgcn Goto Github PK

The code of paper "A Novel Representation Learning for Dynamic Graphs Based on Graph Convolutional Networks, IEEE Transactions on Cybernetics".

Python 100.00%

deep-learning mutual-information proteins representation-learning training marine-vehicles task-analysis

dgcn's Introduction

DGCN-TCYB2022

The code related to the paper below：Chao Gao, Junyou Zhu, Fan Zhang, Zhen Wang, Xuelong Li, A novel representation learning for dynamic graphs based on graph convolutional networks, IEEE Transactions on Cybernetics, 2022, doi: 10.1109/TCYB.2022.3159661.

Run

train_dgcn.py is used to execute a full training run. After cd the file, using 'python train_dgcn.py' to run.

experiment for link prediction: please make sure isone_hot = True, islabel = False experiment for node clustering: please make sure isone_hot = False, islabel = True

Reference

If you make advantage of DGCN in your research, please cite the following in your manuscript:

@article{gao2022novel,
  title={A Novel Representation Learning for Dynamic Graphs Based on Graph Convolutional Networks},
  author={Gao, Chao and Zhu, Junyou and Zhang, Fan and Wang, Zhen and Li, Xuelong},
  journal={IEEE Transactions on Cybernetics},
  year={2022},
  doi={10.1109/TCYB.2022.3159661} 
  publisher={IEEE}
}

dgcn's People

Contributors

Stargazers

Watchers

Forkers

xiaoheng-zhang99 jukebox333 kajimacn

dgcn's Issues

Dataset description

"Hello,

I recently read your paper and found the GitHub repository with the provided source code. I have a question regarding the description of the data, particularly regarding the three datasets for node clustering. Taking 'Cellphone Calls' dataset as an example, I noticed that the original dataset only includes the caller ID, receiver ID, time, call duration, and the base station ID during the call. I'm curious to know how the labels for this particular dataset are determined. Could you please provide some insight into the process of assigning labels to the nodes in this category?

Thank you for your attention and I look forward to your response.

Best regards,

java dataset

The 20 edges.txt files of the java dataset have exactly the same content, are you sure about this?

Some errors

time_weight 会随时间变化进行更新吗？

layers.py 34行
”self.GCN_weights = self.evolve_weights(self.time_weight)“ 报错，因为此时的”self.time_weight=0“

parameters

hello, thank you for your wonderful work. May I ask if you can provide your training parameters? According to the default parameters in your code, there are some differences with your results

There seems to be some bugs in the code

Could you provide the dependencies needed to run the code?
In addition, I had some problems running the code with the following error message:

Traceback (most recent call last):
File "train_dgcn.py", line 165, in
adj, features, idx_train, idx_val, idx_test, args, graph = get_data(dice, node_num, time_edges_path)
File "train_dgcn.py", line 68, in get_data
adj, features, graph = get_afldata(dice, node_num, edges_path)
File "/DGCN/code/pygcn/utils.py", line 89, in get_afldata
similairity_matirx, graph = getSimilariy_modified(adj,node_num,edges_path)
File "/DGCN/code/pygcn/utils.py", line 153, in getSimilariy_modified
node_list = list(graph.node())
AttributeError: 'Graph' object has no attribute 'node'

Recommend Projects

React

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

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

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

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
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.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

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

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.