Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Few-Shot Learning with Graph Neural Networks
Victor Garcia Satorras, Joan Bruna Estrach
Feb 15, 2018 (modified: Feb 20, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic message-passing inference algorithms with their neural-network counterparts, we define a graph neural network architecture that generalizes several of the recently proposed few-shot learning models. Besides providing improved numerical performance, our framework is easily extended to variants of few-shot learning, such as semi-supervised or active learning, demonstrating the ability of graph-based models to operate well on ‘relational’ tasks.
Enter your feedback below and we'll get back to you as soon as possible.