Improved tri-training semi-supervised classification algorithm based on adaptive neighborhood entropy
TL;DR
The results show that the improved Tri-training semi-supervised classification algorithm based on adaptive neighborhood entropy, denoted as ANET, effectively suppresses pseudo-label noise and has stronger robustness and practicality in real classification tasks.
Abstract
Tri-training is a classic semi-supervised learning framework that improves classifier performance by exploiting unlabeled data. However, it suffers from invalid view redundancy assumption and severe pseudo-label noise in real-world applications, which leads to performance degradation. To address these problems, this paper proposes an improved Tri-training semi-supervised classification algorithm based on adaptive neighborhood entropy, denoted as ANET. The algorithm retains the basic Tri-training structure and introduces a lightweight noise suppression module. Specifically, it constructs local neighborhoods for pseudo-labeled samples through k-nearest neighbor search, quantifies sample reliability by calculating neighborhood distribution entropy, and removes low-confidence noise samples with an adaptive threshold. Experiments are conducted on nine UCI datasets with four evaluation metrics: accuracy, precision, recall, and F1-measure. Compared with the standard Tri-training and five state-of-the-art improved algorithms, ANET achieves higher accuracy on 8 datasets, and the average accuracy is increased by 4.2%–8.7%. The results show that the algorithm effectively suppresses pseudo-label noise and has stronger robustness and practicality in real classification tasks.