DiffPool is proposed, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion.
GnExplainer is proposed, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task.
The experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50 times larger than previous deep models.
Graph Convolutional Policy Network (GCPN) is proposed, a general graph convolutional network based model for goal-directed graph generation through reinforcement learning that can achieve 61% improvement on chemical property optimization over state-of-the-art baselines while resembling known molecules, and achieve 184% improved on the constrained property optimization task.
Position-aware Graph Neural Networks (P-GNNs) are proposed, a new class of GNNs for computing position-aware node embeddings that are inductive, scalable, and can incorporate node feature information.
This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities, to their applications, and what they are even capable of due to their emergent properties.
The experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50 times larger than previous deep models.
This work defines and systematically study the architectural design space for GNNs which consists of 315,000 different designs over 32 different predictive tasks, and offers a principled and scalable approach to transition from studying individual GNN designs for specific tasks, to systematically studying the GNN design space and the task space.
GnExplainer is proposed, a general model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task (node and graph classification, link prediction).
A novel graph-based representation of neural networks called relational graph is developed, where layers of neural network computation correspond to rounds of message exchange along the graph structure, which shows that a "sweet spot" of relational graphs leads to neural networks with significantly improved predictive performance.