One-pass AUC optimization

Weakly Supervised AUC Optimization: A Unified Partial AUC Approach

Since acquiring perfect supervision is usually difficult, real-world machine learning tasks often confront inaccurate, incomplete, or inexact supervision, collectively referred to as weak supervision. In this work, we present WSAUC, a unified framework for weakly supervised AUC optimization problems, which covers noisy label learning, positive-unlabeled learning, multi-instance learning, and semi-supervised learning scenarios. Within the WSAUC framework, we first frame the AUC optimization problems in various weakly supervised scenarios as a common formulation of minimizing the AUC risk on contaminated sets, and demonstrate that the empirical risk minimization problems are consistent with the true AUC. Then, we introduce a new type of partial AUC, specifically, the reversed partial AUC (rpAUC), which serves as a robust training objective for AUC maximization in the presence of contaminated labels. WSAUC offers a universal solution for AUC optimization in various weakly supervised scenarios by maximizing the empirical rpAUC. Theoretical and experimental results under multiple settings support the effectiveness of WSAUC on a range of weakly supervised AUC optimization tasks.

Imbalanced Data Classification via Cooperative Interaction Between Classifier and Generator

Learning classifiers with imbalanced data can be strongly biased toward the majority class. To address this issue, several methods have been proposed using generative adversarial networks (GANs). Existing GAN-based methods, however, do not effectively utilize the relationship between a classifier and a generator. This article proposes a novel three-player structure consisting of a discriminator, a generator, and a classifier, along with decision boundary regularization. Our method is distinctive in which the generator is trained in cooperation with the classifier to provide minority samples that gradually expand the minority decision region, improving performance for imbalanced data classification. The proposed method outperforms the existing methods on real data sets as well as synthetic imbalanced data sets.

Task-Feature Collaborative Learning with Application to Personalized Attribute Prediction

As an effective learning paradigm against insufficient training samples, multi-task learning (MTL) encourages knowledge sharing across multiple related tasks so as to improve the overall performance. In MTL, a major challenge springs from the phenomenon that sharing the knowledge with dissimilar and hard tasks, known as negative transfer, often results in a worsened performance. Though a substantial amount of studies have been carried out against the negative transfer, most of the existing methods only model the transfer relationship as task correlations, with the transfer across features and tasks left unconsidered. Different from the existing methods, our goal is to alleviate negative transfer collaboratively across features and tasks. To this end, we propose a novel multi-task learning method called task-feature collaborative learning (TFCL). Specifically, we first propose a base model with a heterogeneous block-diagonal structure regularizer to leverage the collaborative grouping of features and tasks and suppressing inter-group knowledge sharing. We then propose an optimization method for the model. Extensive theoretical analysis shows that our proposed method has the following benefits: (a) it enjoys the global convergence property and (b) it provides a block-diagonal structure recovery guarantee. As a practical extension, we extend the base model by allowing overlapping features and differentiating the hard tasks. We further apply it to the personalized attribute prediction problem with fine-grained modeling of user behaviors. Finally, experimental results on both simulated dataset and real-world datasets demonstrate the effectiveness of our proposed method.

A Hybrid Ensemble Algorithm Combining AdaBoost and Genetic Algorithm for Cancer Classification with Gene Expression Data

The diversity of base classifiers and integration of multiple classifiers are two key issues in the field of ensemble learning. This paper puts forward a hybrid ensemble algorithm combining AdaBoost and genetic algorithm(GA) for cancer classification with gene expression data. The decision group is designed to increase the diversity of base classifier pool, and the GA is used to assign weight to each base classifier, thus to improve the classification performance by avoiding local extrema. The decision groups composed by using base classifiers, including K-nearest neighbor (KNN), Naïve Bayes (NB), and Decision Tree (C4.5). Experimental results show that the proposed algorithm is superior to those existing ensemble learning methods, such as Bagging, Random Forest (RF), Rotation Forest (RoF), AdaBoost, AdaBoost-BPNN, AdaBoost-SVM, and AdaBoost-RF, especially it has better performance on small samples and unbalanced gene expression data processing.

Learning with mitigating random consistency from the accuracy measure

Human beings may make random guesses in decision-making. Occasionally, their guesses may generate consistency with the real situation. This kind of consistency is termed random consistency. In the area of machine leaning, the randomness is unavoidable and ubiquitous in learning algorithms. However, the accuracy (A), which is a fundamental performance measure for machine learning, does not recognize the random consistency. This causes that the classifiers learnt by A contain the random consistency. The random consistency may cause an unreliable evaluation and harm the generalization performance. To solve this problem, the pure accuracy (PA) is defined to eliminate the random consistency from the A. In this paper, we mainly study the necessity, learning consistency and leaning method of the PA. We show that the PA is insensitive to the class distribution of classifier and is more fair to the majority and the minority than A. Subsequently, some novel generalization bounds on the PA and A are given. Furthermore, we show that the PA is Bayes-risk consistent in finite and infinite hypothesis space. We design a plug-in rule that maximizes the PA, and the experiments on twenty benchmark data sets demonstrate that the proposed method performs statistically better than the kernel logistic regression in terms of PA and comparable performance in terms of A. Compared with the other plug-in rules, the proposed method obtains much better performance.

MSCS-DeepLN: Evaluating lung nodule malignancy using multi-scale cost-sensitive neural networks

The accurate identification of malignant lung nodules using computed tomography (CT) screening images is vital for the early detection of lung cancer. It also offers patients the best chance of cure, because non-invasive CT imaging has the ability to capture intra-tumoral heterogeneity. Deep learning methods have obtained promising results for the malignancy identification problem; however, two substantial challenges still remain. First, small datasets cannot insufficiently train the model and tend to overfit it. Second, category imbalance in the data is a problem. In this paper, we propose a method called MSCS-DeepLN that evaluates lung nodule malignancy and simultaneously solves these two problems. Three light models are trained and combined to evaluate the malignancy of a lung nodule. Three-dimensional convolutional neural networks (CNNs) are employed as the backbone of each light model to extract the lung nodule features from CT images and preserve lung nodule spatial heterogeneity. Multi-scale input cropped from CT images enables the sub-networks to learn the multi-level contextual features and preserve diverse. To tackle the imbalance problem, our proposed method employs an AUC approximation as the penalty term. During training, the error in this penalty term is generated from each major and minor class pair, so that negatives and positives can contribute equally to updating this model. Based on these methods, we obtain state-of-the-art results on the LIDC-IDRI dataset. Furthermore, we constructed a new dataset collected from a grade-A tertiary hospital and annotated using biopsy-based cytological analysis to verify the performance of our method in clinical practice.

Direct AUC optimization of regulatory motifs

Motivation

The discovery of transcription factor binding site (TFBS) motifs is essential for untangling the complex mechanism of genetic variation under different developmental and environmental conditions. Among the huge amount of computational approaches for de novo identification of TFBS motifs, discriminative motif learning (DML) methods have been proven to be promising for harnessing the discovery power of accumulated huge amount of high-throughput binding data. However, they have to sacrifice accuracy for speed and could fail to fully utilize the information of the input sequences.

Results

We propose a novel algorithm called CDAUC for optimizing DML-learned motifs based on the area under the receiver-operating characteristic curve (AUC) criterion, which has been widely used in the literature to evaluate the significance of extracted motifs. We show that when the considered AUC loss function is optimized in a coordinate-wise manner, the cost function of each resultant sub-problem is a piece-wise constant function, whose optimal value can be found exactly and efficiently. Further, a key step of each iteration of CDAUC can be efficiently solved as a computational geometry problem. Experimental results on real world high-throughput datasets illustrate that CDAUC outperforms competing methods for refining DML motifs, while being one order of magnitude faster. Meanwhile, preliminary results also show that CDAUC may also be useful for improving the interpretability of convolutional kernels generated by the emerging deep learning approaches for predicting TF sequences specificities.

Availability and Implementation

CDAUC is available at: https://drive.google.com/drive/folders/0BxOW5MtIZbJjNFpCeHlBVWJHeW8.

Supplementary information

Supplementary data are available at Bioinformatics online.

Online Nonlinear AUC Maximization for Imbalanced Data Sets

Classifying binary imbalanced streaming data is a significant task in both machine learning and data mining. Previously, online area under the receiver operating characteristic (ROC) curve (AUC) maximization has been proposed to seek a linear classifier. However, it is not well suited for handling nonlinearity and heterogeneity of the data. In this paper, we propose the kernelized online imbalanced learning (KOIL) algorithm, which produces a nonlinear classifier for the data by maximizing the AUC score while minimizing a functional regularizer. We address four major challenges that arise from our approach. First, to control the number of support vectors without sacrificing the model performance, we introduce two buffers with fixed budgets to capture the global information on the decision boundary by storing the corresponding learned support vectors. Second, to restrict the fluctuation of the learned decision function and achieve smooth updating, we confine the influence on a new support vector to its -nearest opposite support vectors. Third, to avoid information loss, we propose an effective compensation scheme after the replacement is conducted when either buffer is full. With such a compensation scheme, the performance of the learned model is comparable to the one learned with infinite budgets. Fourth, to determine good kernels for data similarity representation, we exploit the multiple kernel learning framework to automatically learn a set of kernels. Extensive experiments on both synthetic and real-world benchmark data sets demonstrate the efficacy of our proposed approach.