GNN Project
Counterfactuals of GNNs
Useful Links :
Python Geometric : https://pytorch-geometric.readthedocs.io/en/latest/ Usable Datasets : https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html
The Cora dataset consists of 2708 scientific publications classified into one of seven classes. Each publication in the dataset is described by a 0/1-valued word vector indicating the absence/presence of the corresponding word from the dictionary. The dictionary consists of 1433 unique words.
Nodes = Publications (Papers, Books ...) Edges = Citations Node Features = word vectors 7 Labels = Pubilcation type e.g. Neural_Networks, Rule_Learning, Reinforcement_Learning, Probabilistic_Methods...