A Simple Baseline Algorithm for Graph Classification
arXiv:1810.09155
Abstract
Graph classification has recently received a lot of attention from various fields of machine learning e.g. kernel methods, sequential modeling or graph embedding. All these approaches offer promising results with different respective strengths and weaknesses. However, most of them rely on complex mathematics and require heavy computational power to achieve their best performance. We propose a simple and fast algorithm based on the spectral decomposition of graph Laplacian to perform graph classification and get a first reference score for a dataset. We show that this method obtains competitive results compared to state-of-the-art algorithms.
arXiv commentRelational Representation Learning, NIPS 2018 Workshop
References in corpus (7)
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- Mixed batches and symmetric discriminators for GAN training
- Stochastic Graphlet Embedding
- Feature-Based Classification of Networks
- Dynamics Based Features For Graph Classification
- Learning Graph-Level Representations with Recurrent Neural Networks
- Weighted Spectral Embedding of Graphs
Cited by in corpus (14)
- Identity Inference on Blockchain using Graph Neural Network
- M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification
- Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels
- A Large-Scale Database for Graph Representation Learning
- Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs
- Unsupervised Event Classification with Graphs on Classical and Photonic Quantum Computers
- Simplicial Complex Representation Learning
- Optimal quantization of the mean measure and applications to statistical learning
- MLQAOA: Graph Learning Accelerated Hybrid Quantum-Classical Multilevel QAOA
- Variational Recurrent Neural Networks for Graph Classification
- Inductive Subgraph Embedding for Link Prediction
- Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization
- Learning Propagation for Arbitrarily-structured Data
- Using Laplacian Spectrum as Graph Feature Representation