A simple yet effective baseline for non-attributed graph classification

Abstract

Graphs are complex objects that do not lend themselves easily to typical learning tasks. Recently, a range of approaches based on graph kernels or graph neural networks have been developed for graph classification and for representation learning on graphs in general. As the developed methodologies become more sophisticated, it is important to understand which components of the increasingly complex methods are necessary or most effective. As a first step, we develop a simple yet meaningful graph representation, and explore its effectiveness in graph classification. We test our baseline representation for the graph classification task on a range of graph datasets. Interestingly, this simple representation achieves similar performance as the state-of-the-art graph kernels and graph neural networks for non-attributed graph classification. Its performance on classifying attributed graphs is slightly weaker as it does not incorporate attributes. However, given its simplicity and efficiency, we believe that it still serves as an effective baseline for attributed graph classification. Our graph representation is efficient (linear-time) to compute. We also provide a simple connection with the graph neural networks. Note that these observations are only for the task of graph classification while existing methods are often designed for a broader scope including node embedding and link prediction. The results are also likely biased due to the limited amount of benchmark datasets available. Nevertheless, the good performance of our simple baseline calls for the development of new, more comprehensive benchmark datasets so as to better evaluate and analyze different graph learning methods. Furthermore, given the computational efficiency of our graph summary, we believe that it is a good candidate as a baseline method for future graph classification (or even other graph learning) studies.

13 pages. Shorter version appears at 2019 ICLR Workshop: Representation Learning on Graphs and Manifolds

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• RetGK: Graph Kernels based on Return Probabilities of Random Walks

Cited by in corpus (20)

• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Principal Neighbourhood Aggregation for Graph Nets
• BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks
• Rethinking pooling in graph neural networks
• CLARE: A Semi-supervised Community Detection Algorithm
• Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily
• Just SLaQ When You Approximate: Accurate Spectral Distances for Web-Scale Graphs
• BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
• A Large-Scale Database for Graph Representation Learning
• Graph Coarsening with Neural Networks
• Self-supervised Graph Neural Networks without explicit negative sampling
• On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs
• MLQAOA: Graph Learning Accelerated Hybrid Quantum-Classical Multilevel QAOA
• Optimizing DNN Compilation for Distributed Training with Joint OP and Tensor Fusion
• Capsule Graph Neural Networks with EM Routing
• Understanding the Power of Persistence Pairing via Permutation Test
• Curriculum learning for multilevel budgeted combinatorial problems
• Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels
• Learning Graphon Autoencoders for Generative Graph Modeling