- Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
- What graph neural networks cannot learn: depth vs width
- On the Equivalence between Node Embeddings and Structural Graph Representations
- Pruned Graph Scattering Transforms
- The Logical Expressiveness of Graph Neural Networks
- Composition-based Multi-Relational Graph Convolutional Networks
- Efficient Probabilistic Logic Reasoning with Graph Neural Networks
- Dynamically Pruned Message Passing Networks for Large-scale Knowledge Graph Reasoning
- Automated Relational Meta-learning
- Geom-GCN: Geometric Graph Convolutional Networks
- Curvature Graph Network
- Adaptive Structural Fingerprints for Graph Attention Networks
- Graph inference learning for semi-supervised classification
- Measuring and Improving the Use of Graph Information in Graph Neural Networks
- PairNorm: Tackling Oversmoothing in GNNs
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- Inductive Matrix Completion Based on Graph Neural Networks
- Inductive representation learning on temporal graphs
- Inductive and Unsupervised Representation Learning on Graph Structured Objects
- GraphSAINT: Graph Sampling Based Inductive Learning Method
- GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding
- Strategies for Pre-training Graph Neural Networks
- InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
- Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measure
- A Fair Comparison of Graph Neural Networks for Graph Classification
- StructPool: Structured Graph Pooling via Conditional Random Fields
- Memory-Based Graph Networks
- Directional Message Passing for Molecular Graphs
- GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
- Learning deep graph matching with channel-independent embedding and Hungarian attention
- Deep Graph Matching Consensus
- LambdaNet: Probabilistic Type Inference using Graph Neural Networks
- Hoppity: Learning Graph Tranformations To Detect and Fix Bugs in Programs
- Global Relational Models of Source Code
- Contrastive Learning of Structured World Models
- Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
- Graph Convolutional Reinforcement Learning
- Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
- DeepSphere: a graph-based spherical CNN
- Mathematical Reasoning in Latent Space
- Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics
- On the geometry and learning low-dimensional embeddings for directed graphs
- Abstract Diagrammatic Reasoning with Multiplex Graph Networks