Academy of Mathematics and Systems Science, CAS
Colloquia & Seminars

Speaker:	吴佳博士，澳大利亚麦考瑞大学
Inviter:
Title:	Multi-structure-view learning for complicated object classification
Time & Venue:	2020.09.25 10:00-11:00 腾讯会议号：369 5380 4489
Abstract:	Many applications involve objects containing structure and rich content information, each describing different feature aspects of the object. Graph learning and classification is a common tool for handling such objects. To date, existing graph classification has been limited to the single-graph setting with each object being represented as one graph from a single structure-view. This inherently limits its use to the classification of complicated objects containing complex structures and uncertain labels. We advance graph classification to handle multiple graph learning for complicated objects from multiple structure views, which aims to explore substructure features across multiple structure views for learning.