Timezone: »

 
Spotlight
Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding
Lan-Zhe Guo · Yu-Feng Li

Tue Jul 19 10:40 AM -- 10:45 AM (PDT) @ Room 301 - 303
in MISC: Unsupervised and Semi-supervised Learning »

Semi-supervised learning (SSL) has proven to be successful in overcoming labeling difficulties by leveraging unlabeled data. Previous SSL algorithms typically assume a balanced class distribution. However, real-world datasets are usually class-imbalanced, causing the performance of existing SSL algorithms to be seriously decreased. One essential reason is that pseudo-labels for unlabeled data are selected based on a fixed confidence threshold, resulting in low performance on minority classes. In this paper, we develop a simple yet effective framework, which only involves adaptive thresholding for different classes in SSL algorithms, and achieves remarkable performance improvement on more than twenty imbalance ratios. Specifically, we explicitly optimize the number of pseudo-labels for each class in the SSL objective, so as to simultaneously obtain adaptive thresholds and minimize empirical risk. Moreover, the determination of the adaptive threshold can be efficiently obtained by a closed-form solution. Extensive experimental results demonstrate the effectiveness of our proposed algorithms.

Keywords: DL: Robustness · MISC: Unsupervised and Semi-supervised Learning

Author Information

Lan-Zhe Guo (Nanjing University)
Yu-Feng Li (Nanjing University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors