Performance evaluation of Graph Convolutional Networks with Siamese training for few-shot classification of nodes

Bridge between perception and reasoning: Graph neural networks and beyond - ICML 2020 workshop (2020) .


Abstract

Siamese networks learn embeddings which impose geometric constraints on the embedding space and are used in the context of one-few-shot learning. In this paper, we empirically investigate applying this framework to Graph Convolutional Networks (GCNs). We test whether some lightweight architectures yield performance increases over plain Multi-Layer Perceptrons (MLPs) in tasks of one-/few-shot learning for nodes. We show that, for our benchmark, good performance can be achieved even with a fast Simplified Graph Convolutional Network (SGCN).



Add your rating and review

If all scientific publications that you have read were ranked according to their scientific quality and importance from 0% (worst) to 100% (best), where would you place this publication? Please rate by selecting a range.


0% - 100%

This publication ranks between % and % of publications that I have read in terms of scientific quality and importance.


Keep my rating and review anonymous
Show publicly that I gave the rating and I wrote the review



Notice: Undefined index: publicationsCaching in /www/html/epistemio/application/controllers/PublicationController.php on line 2240