Imbalanced Lifelong Learning with AUC Maximization

Xiangyu Zhu, Jie Hao, Yunhui Guo, Mingrui Liu

Keywords: Imbalanced Lifelong Learning, AUC Maximization

TL;DR: We propose a new approach to empower continual learning with imbalanced data: designing an algorithm to directly maximize one widely used metric in an imbalanced data setting: Area Under the ROC Curve (AUC).

Abstract: Imbalanced data is ubiquitous in machine learning, such as medical or fine-grained image datasets. The existing continual learning methods employ various techniques such as balanced sampling to improve classification accuracy in this setting. However, classification accuracy is not a suitable metric for imbalanced data, and hence these methods may not obtain a good classifier as measured by other metrics (e.g., recall, F1-score, Area under the ROC Curve). In this paper, we propose a solution to enable efficient imbalanced continual learning by designing an algorithm to effectively maximize one widely used metric in an imbalanced data setting: Area Under the ROC Curve (AUC). We find that simply replacing accuracy with AUC will cause \textit{gradient interference problem} due to the imbalanced data distribution. To address this issue, we propose a new algorithm, namely DIANA, which performs a novel synthesis of model \underline{D}ecoupl\underline{I}ng \underline{AN}d \underline{A}lignment. In particular, the algorithm updates two models simultaneously: one focuses on learning the current knowledge while the other concentrates on reviewing previously-learned knowledge, and the two models gradually align during training. We conduct extensive experiments on datasets across various imbalanced domains, ranging from natural images to medical and satellite images. The results show that DIANA achieves state-of-the-art performance on all the imbalanced datasets compared with several competitive baselines. We further consider standard balanced benchmarks used in lifelong learning to show the effectiveness of DIANA as a general lifelong learning method.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning