Abstract: Graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks. However, existing graph CNNs generally use a fixed ...

The midnight alarms, the credit card hacks, and the reservation drops that separate amateur eaters from the professionals.

Abstract: We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, ...