Abstract
Most graph kernels are an instance of the class of R-Convolution kernels, which measure the similarity of objects by comparing their substructures. Despite their empirical success, most graph kernels use a naive aggregation of the final set of substructures, usually a sum or average, thereby potentially discarding valuable information about the distribution of individual components. Furthermore, only a limited instance of these approaches can be extended to continuously attributed graphs. We propose a novel method that relies on the Wasserstein distance between the node feature vector distributions of two graphs, which allows to find subtler differences in data sets by considering graphs as high-dimensional objects, rather than simple means. We further propose a Weisfeiler--Lehman inspired embedding scheme for graphs with continuous node attributes and weighted edges, enhance it with the computed Wasserstein distance, and thus improve the state-of-the-art prediction performance on several graph classification tasks. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000420933Publication status
publishedEditor
Book title
Advances in Neural Information Processing Systems 32Volume
Pages / Article No.
Publisher
CurranEvent
Organisational unit
09486 - Borgwardt, Karsten M. (ehemalig) / Borgwardt, Karsten M. (former)
Funding
634541 - A Clinical Decision Support system based on Quantitative multimodal brain MRI for personalized treatment in neurological and psychiatric disorders (SBFI)
Notes
Poster presentation.More
Show all metadata
ETH Bibliography
yes
Altmetrics