A simple yet effective baseline for non-attributed graph classification

8 Nov 2018  ·  Chen Cai, Yusu Wang ·

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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Classification D&D LDP Accuracy 75.5% # 33
Graph Classification D&D LDP + distance Accuracy 77.5% # 25
Graph Classification ENZYMES LDP Accuracy 35.3% # 31
Graph Classification MUTAG LDP Accuracy 90.1% # 15
Graph Classification NCI1 LDP Accuracy 73.0% # 36
Graph Classification PROTEINS LDP + distance Accuracy 74.7% # 52
Graph Classification PROTEINS LDP + Labels Accuracy 73.7% # 59
Graph Classification PROTEINS LDP Accuracy 72.7% # 67
Graph Classification PTC LDP Accuracy 61.7% # 26

Methods


No methods listed for this paper. Add relevant methods here