Node Classification on The Citation Network Using Graph Neural Network

Research on Graph Neural Networks has influenced various current real-world problems. The graph-based approach is considered capable of effectively representing the actual state surrounding data by utilizing nodes, edges, and features. Consider feedforward neural network graph approaches, we determine accuracy each method. In baseline experiment, training testing were performed using NN approach. resulting FNN was 72.59% GNN model increased 81.65%. There a 9.06% increase in between model. new utilized predictions showcases probabilities class through randomly generated examples.