Browsing School of Business and Management by Author "Expert, P"
Now showing items 1-2 of 2
-
Geometric graphs from data to aid classification tasks with Graph Convolutional Networks.
Qian, Y; Expert, P; Panzarasa, P; Barahona, M (2021-04-09)Traditional classification tasks learn to assign samples to given classes based solely on sample features. This paradigm is evolving to include other sources of information, such as known relations between samples. Here, ... -
Quantifying the Alignment of Graph and Features in Deep Learning
Qian, Y; Expert, P; Rieu, T; Panzarasa, P; Barahona, M (2021-01-01)IEEE We show that the classification performance of graph convolutional networks (GCNs) is related to the alignment between features, graph, and ground truth, which we quantify using a subspace alignment measure (SAM) ...