Timezone: »

 
Poster
Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data
Lan-Zhe Guo · Zhen-Yu Zhang · Yuan Jiang · Yu-Feng Li · Zhi-Hua Zhou

Tue Jul 14 07:00 AM -- 07:45 AM & Tue Jul 14 07:00 PM -- 07:45 PM (PDT) @
in Poster Session 1 »
Deep semi-supervised learning (SSL) has been recently shown very effectively. However, its performance is seriously decreased when the class distribution is mismatched, among which a common situation is that unlabeled data contains some classes not seen in the labeled data. Efforts on this issue remain to be limited. This paper proposes a simple and effective safe deep SSL method to alleviate the harm caused by it. In theory, the result learned from the new method is never worse than learning from merely labeled data, and it is theoretically guaranteed that its generalization approaches the optimal in the order $O(\sqrt{d\ln(n)/n})$, even faster than the convergence rate in supervised learning associated with massive parameters. In the experiment of benchmark data, unlike the existing deep SSL methods which are no longer as good as supervised learning in 40\% of unseen-class unlabeled data, the new method can still achieve performance gain in more than 60\% of unseen-class unlabeled data. Moreover, the proposal is suitable for many deep SSL algorithms and can be easily extended to handle other cases of class distribution mismatch.
Keywords: Robust Statistics and Machine Learning · Semi-supervised learning · Unsupervised and Semi-supervised Learning

Author Information

Lan-Zhe Guo (Nanjing University)
Zhen-Yu Zhang (Nanjing University)
Yuan Jiang (Nanjing University)
Yu-Feng Li (Nanjing University)
Zhi-Hua Zhou (Nanjing University)

More from the Same Authors