Skip to main content

Augmenting Graph Convolution with Distance Preserving Embedding for Improved Learning

by Guojing Cong, Seung-hwan Lim, Steven R Young
Publication Type
Conference Paper
Book Title
2022 IEEE International Conference on Data Mining Workshops (ICDMW)
Publication Date
Page Numbers
23 to 30
Publisher Location
New Jersey, United States of America
Conference Name
IEEE International Conference on Data Mining Workshops (ICDMW)
Conference Location
Orlando, Florida, United States of America
Conference Sponsor
Conference Date

Graph convolution incorporates topological information of a graph into learning. Message passing corresponds to traversal of a local neighborhood in classical graph algorithms. We show that incorporating additional global structures, such as shortest paths, through distance preserving embedding can improve performance. Our approach, Gavotte, significantly improves the performance of a range of popular graph neu-ral networks such as GCN, GA T,Graph SAGE, and GCNII for transductive learning. Gavotte also improves the performance of graph neural networks for full-supervised tasks, albeit to a smaller degree. As high-quality embeddings are generated by Gavotte as a by-product, we leverage clustering algorithms on these embed dings to augment the training set and introduce Gavotte+. Our results of Gavotte+ on datasets with very few labels demonstrate the advantage of augmenting graph convolution with distance preserving embedding.