search

fani-lab / OpeNTF

Neural machine learning methods for Team Formation problem.
Other
18 stars 13 forks source link

Implementation of Attention Based Spatial-Temporal GCN for Traffic Flow Forecasting #149

Open karan96 opened 2 years ago

karan96 commented 2 years ago

This is the link towards github repo for the paper: - Guo, S., Lin, Y., Feng, N., Song, C., & Wan, H. (2019, July). Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In Proceedings of the AAAI conference on artificial intelligence (Vol. 33, No. 01, pp. 922-929).

https://github.com/Davidham3/ASTGCN

The summary of which will be posted later, currently I have begun implementation of this code. Since this is not directly related to team formation, but this is using spatial information in GCN, I thought It might give us an idea on how others are using spatial information in their networks, kindly review and let me know if I should continue with the implementation of the code.

This paper was found on the link you shared: - https://github.com/benedekrozemberczki/pytorch_geometric_temporal.

hosseinfani commented 2 years ago

@karan96 thanks for the update. Not sure what do you mean by "implementing" when the code is already available. I think you mean to make an initial run of it. You have to think how we can cast team formation as a spatio-temporal graph such that we can use this method. That's the main challenge.

karan96 commented 2 years ago

@hosseinfani Initial run of it is successful. Now I am trying to find out how they are processing datasets for their use case.