Learning with Label Proportions (LLP) copes with the problem that training instances are grouped as bags, where the class proportions in each bag rather than the labels of individual training instances are provided. Feature selection, which preserves only a subset of original features, is vital in LLP as it might impact the subsequent disambiguation and classification performances. Accordingly, a new work termed Feature Generation Machine for LLP (FGM-LLP), is proposed to tackle the feature selection, disambiguation and classification challenges simultaneously. In specific, FGM-LLP learns the instance-level labels, the feature selection vector and the maximum margin classifier under a unified framework. To solve FGM-LLP efficiently, a two-layer Cutting Plane (CP) method is also developed with a convergence guarantee. Empirical studies justify not only the superiority of FGM-LLP in classification compared with competing work, but also the high-efficiency of the two-layer CP optimization method.

Semi-supervised Partial Label Learning (SPLL) aims to learn from a dataset comprised of both partial label examples each of which is associated with a candidate label set and unlabeled examples. The mainstream of SPLL methods usually construct a confidence matrix for training examples and by which to operate label disambiguation and classifier training. However, they treat examples with different confidence levels in the same strategy during training, which might result in degenerated learning performance. In this work, a novel method named COnfidence-DRiven (CODR) is proposed to deal with the above drawback. In specific, we iteratively update the confidence matrix and predictive network, and employ different strategies to deal with high-confidence and remaining low-confidence examples. Extensive experiments on real-world datasets demonstrate the superiority of CODR in classification accuracy compared with several other state-of-the-art methods.

Learning with label proportions (LLP) deals with the problem that the training data are provided as bags, where the label proportions of training bags rather than the labels of individual training instances are accessible. Existing LLP studies assume that the label proportions of all training bags are accessible. However, in many applications, it is time-consuming to mark all training bags with label proportions, which leads to the problem of learning with both marked and unmarked bags, namely, semisupervised LLP (SLLP). In this work, we propose semisupervised proportional support vector machine (SS- ∝ SVM), which extends the proportional SVM ( ∝ SVM) model to its semisupervised version. To the best of our knowledge, SS- ∝ SVM is the first attempt to cope with the SLLP problem. Two realizations, alter-SS- ∝ SVM and conv-SS- ∝ SVM, which are based on alternating optimization and convex relaxation, respectively, are developed to solve the proposed SS- ∝ SVM model. Moreover, we design a cutting plane (CP) method to optimize conv-SS- ∝ SVM with a guaranteed convergence rate and present a fast accelerated proximal gradient method to solve the multiple kernel learning subproblem in conv-SS- ∝ SVM efficiently. Empirical experiments not only justify the superiority of SS- ∝ SVM over its supervised counterpart in classification accuracy but also demonstrate the high competitive computational efficiency of the CP optimization of conv-SS- ∝ SVM.

A new Usability Metric for User Experience (UMUX) is translated and validated for native Chinese speakers in this study. The forward-backward translation method is applied to translate the UMUX. The results are optimized through structure-back interviews to obtain a final, unambiguous UMUX version. The Chinese version of the UMUX questionnaire is proven to have high reliability, sensitivity, and effectiveness. The correspondence between the Chinese UMUX version, UMUX-LITE, and SUS is also investigated. The results of this work may provide Chinese usability practitioners with a standardized scale after rigorous testing, as well as a closer understanding of the relationship between the three questionnaires in assisting users to make sound choices.

Partial label learning (PLL) is a multi-class weakly supervised learning problem where each training instance is associated with a set of candidate labels but only one label is the ground truth. The main challenge of PLL is how to deal with the label ambiguities. Among various disambiguation techniques, large margin (LM)-based algorithms attract much attention due to their powerful discriminative performance. However, existing LM-based algorithms either neglect some potential candidate labels in constructing the margin or introduce auxiliary estimation of class capacities which is generally inaccurate. As a result, their generalization performances are deteriorated. To address the above-mentioned drawbacks, motivated by the optimistic superset loss, we propose an LM Partial LAbel machiNE (LM-PLANE) by extending multi-class support vector machines (SVM) to PLL. Compared with existing LM-based disambiguation algorithms, LM-PLANE considers the margin of all potential candidate labels without auxiliary estimation of class capacities. Furthermore, an efficient cutting plane (CP) method is developed to train LM-PLANE in the dual space. Theoretical insights into the effectiveness and convergence of our CP method are also presented. Extensive experiments on various PLL tasks demonstrate the superiority of LM-PLANE over existing LM based and other representative PLL algorithms in terms of classification accuracy.

The weakly supervised Multiple-Instance Learning (MIL) problem has been successfully applied in information retrieval tasks. Two related issues might affect the performance of MIL algorithms: how to cope with label ambiguities and how to deal with non-discriminative components, and we propose COmpact MultiPle-Instance LEarning (COMPILE) to consider them simultaneously. To treat label ambiguities, COMPILE seeks ground-truth positive instances in positive bags. By using weakly supervised information to learn data's short binary representations, COMPILE enhances discrimination via strengthening discriminative components and suppressing non-discriminative ones. We adapt block coordinate descent to optimize COMPILE efficiently. Experiments on text categorization empirically show: 1) COMPILE unifies disambiguation and data preprocessing successfully; 2) it generates short binary representations efficiently to enhance discrimination at significantly reduced storage cost.

The problem of feature selection is a difficult combinatorial task in machine learning and of high practical relevance. In this paper, we consider feature selection method for multimodally distributed data, and present a large margin feature weighting method for k-nearest neighbor (kNN) classifiers. The method learns the feature weighting factors by minimizing a cost function, which aims at separating different classes by large local margins and pulling closer together points from the same class, based on using as few features as possible. The consequent optimization problem can be efficiently solved by linear programming. Finally, the proposed approach is assessed through a series of experiments with UCI and microarray data sets, as well as a more specific and challenging task, namely, radar high-resolution range profiles (HRRP) automatic target recognition (ATR). The experimental results demonstrate the effectiveness of the proposed algorithms.