Pytorch implementation of DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks
This is a pytorch implementation of DySAT. All codes are adapted from official implementation in TensorFlow. This implementation is only tested using dataset Enron, and the results is inconsistent with official results (better than that). Code review and contribution is welcome!
cd raw_data/Enron
pyhton process.py
The processed data will stored at 'data/Enron"
python train --dataset Enron --time_steps 16
Hi. I would like to ask which version of python are you using?
Hi, I am using the original implementation, successfully ran the codes run_script.py and generated the embeddings for each timestep. However, I lost the index of each generated embeddings after I changed my laptop, so now I cannot match each embeddings with my nodes. Do you know how is the output emb.npz sorted? OR how can I get back the index of each embedding file when I lost the data of my old laptop?
祝您生活愉快，成果多多
sometimes it runs this error
but sometimes it not
Since you mention that the results are inconsistent with official results (better than that), could you please tell me whether the official results are in Table 2?
Hello, I want to know why I reported this error,thanks.
Can you add support for dataset yelp and movielens？ it really helps. Thank you !
React
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
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
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.
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.