Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume -, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2022.3190420
Keywords
Learning systems; Decoding; Task analysis; Deep learning; Data models; Training; Feature extraction; Active learning; graph structure; unsupervised learning
Categories
Funding
- National Natural Science Foundation of China [62122013, U2001211]
Ask authors/readers for more resources
This paper introduces a new deep unsupervised active learning model that utilizes learnable graphs to improve sample representation and selection of representative samples. By learning optimal graph structures and incorporating shortcut connections, this approach achieves good results in unsupervised active learning.
Recently, deep learning has been successfully applied to unsupervised active learning. However, the current method attempts to learn a nonlinear transformation via an auto-encoder while ignoring the sample relation, leaving huge room to design more effective representation learning mechanisms for unsupervised active learning. In this brief, we propose a novel deep unsupervised active learning model via learnable graphs, named ALLGs. ALLG benefits from learning optimal graph structures to acquire better sample representation and select representative samples. To make the learned graph structure more stable and effective, we take into account k-nearest neighbor graph as a priori and learn a relation propagation graph structure. We also incorporate shortcut connections among different layers, which can alleviate the well-known over-smoothing problem to some extent. To the best of our knowledge, this is the first attempt to leverage graph structure learning for unsupervised active learning. Extensive experiments performed on six datasets demonstrate the efficacy of our method.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available