Graph convolutional networks are really cool and widely applicable. The fastest intro to the field me was actually not a paper or blog post, but the docs of Pytorch Geometric. The definition of their message passing framework [0] gets you to the right frame of mind, after which there are well documented and cited implementations of various papers which you can reuse [1].

[0] https://pytorch-geometric.readthedocs.io/en/latest/notes/cre...

[1] https://pytorch-geometric.readthedocs.io/en/latest/modules/n...