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
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.
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
-
2023 Oral: ODS: Test-Time Adaptation in the Presence of Open-World Data Shift »
Zhi Zhou · Lan-Zhe Guo · Lin-Han Jia · Dingchu Zhang · Yu-Feng Li -
2023 Oral: Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions »
Lin-Han Jia · Lan-Zhe Guo · Zhi Zhou · Jie-Jing Shao · Yuke Xiang · Yu-Feng Li -
2023 Poster: Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions »
Lin-Han Jia · Lan-Zhe Guo · Zhi Zhou · Jie-Jing Shao · Yuke Xiang · Yu-Feng Li -
2023 Poster: Identifying Useful Learnwares for Heterogeneous Label Spaces »
Lan-Zhe Guo · Zhi Zhou · Yu-Feng Li · Zhi-Hua Zhou -
2023 Poster: ODS: Test-Time Adaptation in the Presence of Open-World Data Shift »
Zhi Zhou · Lan-Zhe Guo · Lin-Han Jia · Dingchu Zhang · Yu-Feng Li -
2022 Poster: Fast Provably Robust Decision Trees and Boosting »
Jun-Qi Guo · Ming-Zhuo Teng · Wei Gao · Zhi-Hua Zhou -
2022 Spotlight: Fast Provably Robust Decision Trees and Boosting »
Jun-Qi Guo · Ming-Zhuo Teng · Wei Gao · Zhi-Hua Zhou -
2022 Poster: Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding »
Lan-Zhe Guo · Yu-Feng Li -
2022 Spotlight: Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding »
Lan-Zhe Guo · Yu-Feng Li -
2021 Poster: Dash: Semi-Supervised Learning with Dynamic Thresholding »
Yi Xu · Lei Shang · Jinxing Ye · Qi Qian · Yu-Feng Li · Baigui Sun · Hao Li · rong jin -
2021 Oral: Dash: Semi-Supervised Learning with Dynamic Thresholding »
Yi Xu · Lei Shang · Jinxing Ye · Qi Qian · Yu-Feng Li · Baigui Sun · Hao Li · rong jin -
2020 Poster: Learning with Feature and Distribution Evolvable Streams »
Zhen-Yu Zhang · Peng Zhao · Yuan Jiang · Zhi-Hua Zhou -
2018 Poster: Rectify Heterogeneous Models with Semantic Mapping »
Han-Jia Ye · De-Chuan Zhan · Yuan Jiang · Zhi-Hua Zhou -
2018 Oral: Rectify Heterogeneous Models with Semantic Mapping »
Han-Jia Ye · De-Chuan Zhan · Yuan Jiang · Zhi-Hua Zhou -
2017 Poster: Multi-Class Optimal Margin Distribution Machine »
Teng Zhang · Zhi-Hua Zhou -
2017 Talk: Multi-Class Optimal Margin Distribution Machine »
Teng Zhang · Zhi-Hua Zhou