Online Adaptive Asymmetric Active Learning with Limited Budgets
Authors:
- Yifan ZhangYZYifan Zhang
- Peilin ZhaoPZPeilin Zhao
- Shuaicheng NiuSNShuaicheng Niu
- Qingyao WuQWQingyao Wu
- Jiezhang CaoJCJiezhang Cao
- Junzhou HuangJHJunzhou Huang
- Mingkui TanMTMingkui Tan
Preprint
Abstract
Online Active Learning (OAL) aims to manage unlabeled datastream by selectively querying the label of data. OAL is applicable to many real-world problems, such as anomaly detection in health-care and finance. In these problems, there are two key challenges: the query budget is often limited; the ratio between classes is highly imbalanced. In practice, it is quite difficult to handle imbalanced unlabeled datastream when only a limited budget of labels can be queried for training. To solve this, previous OAL studies adopt either asymmetric losses or queries (an isolated asymmetric strategy) to tackle the imbalance, and use first-order methods to optimize the cost-sensitive measure. However, the isolated strategy limits their performance in class imbalance, while first-order methods restrict their optimization performance. In this paper, we propose a novel Online Adaptive Asymmetric Active learning algorithm, based on a new asymmetric strategy (merging both asymmetric losses and queries strategies), and second-order optimization. We theoretically analyze its mistake bound and cost-sensitive metric bounds. Moreover, to better balance performance and efficiency, we enhance our algorithm via a sketching technique, which significantly accelerates the computational speed with quite slight performance degradation. Promising results demonstrate the effectiveness and efficiency of the proposed methods.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Collaborative Unsupervised Domain Adaptation for Medical Image DiagnosisIEEE Transactions on Image Processing, 2020
- From Whole Slide Imaging to Microscopy: Deep Microscopy Adaptation Network for Histopathology Cancer Image Classification2019
- Second-Order Online Active Learning and Its ApplicationsIEEE Transactions on Knowledge and Data Engineering, 2017
- Strategy-updating depending on local environment enhances cooperation in prisoner’s dilemma gameApplied Mathematics and Computation, 2017
- Adaptive regularization of weight vectorsMachine Learning, 2013
- Randomized algorithms for the low-rank approximation of matricesProceedings of the National Academy of Sciences, 2007
- Database-friendly random projections: Johnson-Lindenstrauss with binary coinsJournal of Computer and System Sciences, 2003
- Large Margin Classification Using the Perceptron AlgorithmMachine Learning, 1999
- On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrixJournal of Mathematical Analysis and Applications, 1985
- Simplified neuron model as a principal component analyzerJournal of Mathematical Biology, 1982