This repository provides the official PyTorch implementation of experiments from the ICLR 2019 paper ‘How Powerful are Graph Neural Networks?’ by Xu et al. It implements the GIN (Graph Isomorphism Network) algorithm, a provably expressive GNN architecture, along with baseline GNN variants for comparison. The code supports graph-level classification tasks on datasets like TU-Molecule, COLLAB, and IMDB, using node features augmented with degree information.