Deep Unsupervised Active Learning on Learnable Graphs

Handong Ma, Changsheng Li*, Xinchu Shi, Ye Yuan, Guoren Wang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)2894-2900
Number of pages7
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume35
Issue number2
DOIs
Publication statusPublished - 1 Feb 2024

Keywords

  • Active learning
  • graph structure
  • unsupervised learning

Fingerprint

Dive into the research topics of 'Deep Unsupervised Active Learning on Learnable Graphs'. Together they form a unique fingerprint.

Cite this

Ma, H., Li, C., Shi, X., Yuan, Y., & Wang, G. (2024). Deep Unsupervised Active Learning on Learnable Graphs. IEEE Transactions on Neural Networks and Learning Systems, 35(2), 2894-2900. https://doi.org/10.1109/TNNLS.2022.3190420