graph classification
Graph classification involves categorizing entire graph-structured objects based on their properties and characteristics. This is crucial in domains like social network analysis, molecule structure identification, and recommendation systems.
- A Few Moments Please: Scalable Graphon Learning via Moment Matching
- Enhancing Graph Classification Robustness with Singular Pooling
- GLNCD: Graph-Level Novel Category Discovery
- GMV: A Unified and Efficient Graph Multi-View Learning Framework
- Geometry-Aware Edge Pooling for Graph Neural Networks
- Interpretable and Parameter Efficient Graph Neural Additive Models with Random Fourier Features
- Learning Crossmodal Interaction Patterns via Attributed Bipartite Graphs for Single-Cell Omics
- MultiNet: Adaptive Multi-Viewed Subgraph Convolutional Networks for Graph Classification
- On Logic-based Self-Explainable Graph Neural Networks
- On topological descriptors for graph products
- Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
- Robust Explanations of Graph Neural Networks via Graph Curvatures
- Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
- Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming