|Speaker :||Edouard Pineau|
|Safran - Telecom ParisTech|
|Time:||2:00 pm - 3:00 pm|
|Location:||LINCS / EIT Digital|
Graph classification has recently received a lot of attention from various fields of machine learning e.g. kernel methods, sequential modeling or graph embedding. We address the problem of graph classification based only on structural information. Most standard methods require either the pairwise comparisons of all graphs in the dataset or the extraction of ad-hoc features to perform classification. Those methods respectively raise scalability issues when the number of samples in the dataset is large, and flexibility issues when discriminative information is characterized by exotic features. We propose two approaches for graph classification. First we propose a simple baseline algorithm that uses spectral information as graph representation. Second, we propose a new sequential approach using recurrent neural networks to offer new possibilities for graph analysis in terms of scalability and feature learning.