DeepAI AI Chat
Log In Sign Up

Semi-supervised Learning for Convolutional Neural Networks via Online Graph Construction

by   Sheng-Yi Bai, et al.

The recent promising achievements of deep learning rely on the large amount of labeled data. Considering the abundance of data on the web, most of them do not have labels at all. Therefore, it is important to improve generalization performance using unlabeled data on supervised tasks with few labeled instances. In this work, we revisit graph-based semi-supervised learning algorithms and propose an online graph construction technique which suits deep convolutional neural network better. We consider an EM-like algorithm for semi-supervised learning on deep neural networks: In forward pass, the graph is constructed based on the network output, and the graph is then used for loss calculation to help update the network by back propagation in the backward pass. We demonstrate the strength of our online approach compared to the conventional ones whose graph is constructed on static but not robust enough feature representations beforehand.


Semi-supervised Learning with Robust Loss in Brain Segmentation

In this work, we used a semi-supervised learning method to train deep le...

Mutual Exclusivity Loss for Semi-Supervised Deep Learning

In this paper we consider the problem of semi-supervised learning with d...

Neural Graph Machines: Learning Neural Networks Using Graphs

Label propagation is a powerful and flexible semi-supervised learning te...

Data driven algorithms for limited labeled data learning

We consider a novel data driven approach for designing learning algorith...

Graph-based Active Learning for Semi-supervised Classification of SAR Data

We present a novel method for classification of Synthetic Aperture Radar...

Semi-Supervised Learning on Graphs with Feature-Augmented Graph Basis Functions

For semi-supervised learning on graphs, we study how initial kernels in ...

A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning

In this paper, we proposed a general framework for data poisoning attack...