Multi-Graph-View Learning for Complicated Object Classification

Wu, Jia (University of Technology, Sydney) | Pan, Shirui (University of Technology, Sydney) | Zhu, Xingquan (Florida Atlantic University) | Cai, Zhihua (China University of Geosciences, Wuhan) | Zhang, Chengqi (University of Technology, Sydney)

AAAI Conferences 

In this paper, we propose to represent and classify complicated objects. In order to represent the objects, we propose a multi-graph-view model which uses graphs constructed from multiple graph-views to represent an object. In addition, a bag based multi-graph model is further used to relax labeling by only requiring one label for a bag of graphs, which represent one object. In order to learn classification models, we propose a multi-graph-view bag learning algorithm (MGVBL), which aims to explore subgraph features from multiple graph-views for learning. By enabling a joint regularization across multiple graph-views, and enforcing labeling constraints at the bag and graph levels, MGVBL is able to discover most effective subgraph features across all graph-views for learning. Experiments on real-world learning tasks demonstrate the performance of MGVBL for complicated object classification.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found