Hello Alket

You need to go through graph embedding literature. A graph embedding is another representation of the graph (still a matrix but less sensitive to node permutations). Technically these are similar to projections (PCA, ...) but with more information about graph structure.

Anyway, read this document : https://arxiv.org/pdf/1705.02801.pdf

published as : Article Graph Embedding Techniques, Applications, and Performance: A Survey

They also provide codes : https://github.com/palash1992/GEM

Best wishes

Mohammed

Hello Alket

You need to go through graph embedding literature. A graph embedding is another representation of the graph (still a matrix but less sensitive to node permutations). Technically these are similar to projections (PCA, ...) but with more information about graph structure.

Anyway, read this document : https://arxiv.org/pdf/1705.02801.pdf

published as : Article Graph Embedding Techniques, Applications, and Performance: A Survey

They also provide codes : https://github.com/palash1992/GEM

Best wishes

Mohammed

Dear Alket,

I suggest you to see links on topic.

https://towardsdatascience.com/learning-from-graph-data-using-keras-and-tensorflow-5b54e3ddffbf

https://pathmind.com/wiki/graph-analysis

https://www.amazon.fr/Hands-Convolutional-Neural-Networks-TensorFlow/dp/1789130336

https://www.kdd.org/kdd2019/hands-on-tutorials

https://www.kdnuggets.com/2019/08/neighbours-machine-learning-graphs.html

Best regards

These tutorials might be helpful for you:

https://medium.com/@BorisAKnyazev/tutorial-on-graph-neural-networks-for-computer-vision-and-beyond-part-1-3d9fada3b80d

https://morioh.com/p/ugZkHhK0STzx