RetGK: Graph Kernels based on Return Probabilities of Random Walks
arXiv:1809.02670
Abstract
Graph-structured data arise in wide applications, such as computer vision, bioinformatics, and social networks. Quantifying similarities among graphs is a fundamental problem. In this paper, we develop a framework for computing graph kernels, based on return probabilities of random walks. The advantages of our proposed kernels are that they can effectively exploit various node attributes, while being scalable to large datasets. We conduct extensive graph classification experiments to evaluate our graph kernels. The experimental results show that our graph kernels significantly outperform existing state-of-the-art approaches in both accuracy and computational efficiency.
Cited by in corpus (21)
- A Survey on Graph Kernels
- A Comprehensive Survey on Deep Graph Representation Learning
- Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
- Graph Kernels: A Survey
- PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signatures
- Graph Kernels: State-of-the-Art and Future Challenges
- Learning metrics for persistence-based summaries and applications for graph classification
- A simple yet effective baseline for non-attributed graph classification
- Convolutional Kernel Networks for Graph-Structured Data
- Distance Metric Learning for Graph Structured Data
- Neighborhood Preserving Kernels for Attributed Graphs
- A Hierarchy of Graph Neural Networks Based on Learnable Local Features
- Optimal quantization of the mean measure and applications to statistical learning
- Wasserstein Embedding for Graph Learning
- ATOL: Measure Vectorization for Automatic Topologically-Oriented Learning
- Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels
- Graph Filtration Learning
- Graph Self-Supervised Learning with Learnable Structural and Positional Encodings
- Generating the Graph Gestalt: Kernel-Regularized Graph Representation Learning
- Transport based Graph Kernels
- Ordinal Pattern Kernel for Brain Connectivity Network Classification