Skip to Content
EntropyEntropy
  • Article
  • Open Access

31 January 2024

22 Pages

Ensemble Transductive Propagation Network for Semi-Supervised Few-Shot Learning

,
and
1
Beijing Key Lab of Petroleum Data Mining, Department of Geophysics, China University of Petroleum, Beijing 102249, China
2
College of Information Science and Engineering, China University of Petroleum, Beijing 102249, China
3
School of Computer Science, Minnan Normal University, Zhangzhou 363000, China
4
Key Laboratory of Data Science and Intelligence Application, Fujian Province University, Zhangzhou 363000, China

Abstract

Few-shot learning aims to solve the difficulty in obtaining training samples, leading to high variance, high bias, and over-fitting. Recently, graph-based transductive few-shot learning approaches supplement the deficiency of label information via unlabeled data to make a joint prediction, which has become a new research hotspot. Therefore, in this paper, we propose a novel ensemble semi-supervised few-shot learning strategy via transductive network and Dempster–Shafer (D-S) evidence fusion, named ensemble transductive propagation networks (ETPN). First, we present homogeneity and heterogeneity ensemble transductive propagation networks to better use the unlabeled data, which introduce a preset weight coefficient and provide the process of iterative inferences during transductive propagation learning. Then, we combine the information entropy to improve the D-S evidence fusion method, which improves the stability of multi-model results fusion from the pre-processing of the evidence source. Third, we combine the L2 norm to improve an ensemble pruning approach to select individual learners with higher accuracy to participate in the integration of the few-shot model results. Moreover, interference sets are introduced to semi-supervised training to improve the anti-disturbance ability of the mode. Eventually, experiments indicate that the proposed approaches outperform the state-of-the-art few-shot model. The best accuracy of ETPN increases by 0.3% and 0.28% in the 5-way 5-shot, and by 3.43% and 7.6% in the 5-way 1-shot on miniImagNet and tieredImageNet, respectively.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.