Reusable model design becomes desirable with the rapid expansion of machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the image co-localization problem. We propose a simple but effective method, named Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then obtaining the category-consistent regions, which can accurately locate the common object in a set of images. Empirical studies validate the effectiveness of the proposed DDT method. On benchmark image co-localization datasets, DDT consistently outperforms existing state-of-the-art methods by a large margin. Moreover, DDT also demonstrates good generalization ability for unseen categories and robustness for dealing with noisy data.

* Accepted by IJCAI 2017
Click to Read Paper
Disagreement-based approaches generate multiple classifiers and exploit the disagreement among them with unlabeled data to improve learning performance. Co-training is a representative paradigm of them, which trains two classifiers separately on two sufficient and redundant views; while for the applications where there is only one view, several successful variants of co-training with two different classifiers on single-view data instead of two views have been proposed. For these disagreement-based approaches, there are several important issues which still are unsolved, in this article we present theoretical analyses to address these issues, which provides a theoretical foundation of co-training and disagreement-based approaches.

Click to Read Paper
AUC (area under ROC curve) is an important evaluation criterion, which has been popularly used in many learning tasks such as class-imbalance learning, cost-sensitive learning, learning to rank, etc. Many learning approaches try to optimize AUC, while owing to the non-convexity and discontinuousness of AUC, almost all approaches work with surrogate loss functions. Thus, the consistency of AUC is crucial; however, it has been almost untouched before. In this paper, we provide a sufficient condition for the asymptotic consistency of learning approaches based on surrogate loss functions. Based on this result, we prove that exponential loss and logistic loss are consistent with AUC, but hinge loss is inconsistent. Then, we derive the $q$-norm hinge loss and general hinge loss that are consistent with AUC. We also derive the consistent bounds for exponential loss and logistic loss, and obtain the consistent bounds for many surrogate loss functions under the non-noise setting. Further, we disclose an equivalence between the exponential surrogate loss of AUC and exponential surrogate loss of accuracy, and one straightforward consequence of such finding is that AdaBoost and RankBoost are equivalent.

Click to Read Paper
Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed, however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which was motivated from the intuition of preventing complex co-adaptation of feature detectors. In this paper, we study the Rademacher complexity of different types of dropout, and our theoretical results disclose that for shallow neural networks (with one or none hidden layer) dropout is able to reduce the Rademacher complexity in polynomial, whereas for deep neural networks it can amazingly lead to an exponential reduction of the Rademacher complexity.

* 20 pagea
Click to Read Paper
Margin theory provides one of the most popular explanations to the success of \texttt{AdaBoost}, where the central point lies in the recognition that \textit{margin} is the key for characterizing the performance of \texttt{AdaBoost}. This theory has been very influential, e.g., it has been used to argue that \texttt{AdaBoost} usually does not overfit since it tends to enlarge the margin even after the training error reaches zero. Previously the \textit{minimum margin bound} was established for \texttt{AdaBoost}, however, \cite{Breiman1999} pointed out that maximizing the minimum margin does not necessarily lead to a better generalization. Later, \cite{Reyzin:Schapire2006} emphasized that the margin distribution rather than minimum margin is crucial to the performance of \texttt{AdaBoost}. In this paper, we first present the \textit{$k$th margin bound} and further study on its relationship to previous work such as the minimum margin bound and Emargin bound. Then, we improve the previous empirical Bernstein bounds \citep{Maurer:Pontil2009,Audibert:Munos:Szepesvari2009}, and based on such findings, we defend the margin-based explanation against Breiman's doubts by proving a new generalization error bound that considers exactly the same factors as \cite{Schapire:Freund:Bartlett:Lee1998} but is sharper than \cite{Breiman1999}'s minimum margin bound. By incorporating factors such as average margin and variance, we present a generalization error bound that is heavily related to the whole margin distribution. We also provide margin distribution bounds for generalization error of voting classifiers in finite VC-dimension space.

* Artificial Intelligence 203:1-18 2013
* 35 pages
Click to Read Paper
The sample complexity of active learning under the realizability assumption has been well-studied. The realizability assumption, however, rarely holds in practice. In this paper, we theoretically characterize the sample complexity of active learning in the non-realizable case under multi-view setting. We prove that, with unbounded Tsybakov noise, the sample complexity of multi-view active learning can be $\widetilde{O}(\log\frac{1}{\epsilon})$, contrasting to single-view setting where the polynomial improvement is the best possible achievement. We also prove that in general multi-view setting the sample complexity of active learning with unbounded Tsybakov noise is $\widetilde{O}(\frac{1}{\epsilon})$, where the order of $1/\epsilon$ is independent of the parameter in Tsybakov noise, contrasting to previous polynomial bounds where the order of $1/\epsilon$ is related to the parameter in Tsybakov noise.

* 22 pages, 1 figure
Click to Read Paper
A major challenge in paraphrase research is the lack of parallel corpora. In this paper, we present a new method to collect large-scale sentential paraphrases from Twitter by linking tweets through shared URLs. The main advantage of our method is its simplicity, as it gets rid of the classifier or human in the loop needed to select data before annotation and subsequent application of paraphrase identification algorithms in the previous work. We present the largest human-labeled paraphrase corpus to date of 51,524 sentence pairs and the first cross-domain benchmarking for automatic paraphrase identification. In addition, we show that more than 30,000 new sentential paraphrases can be easily and continuously captured every month at ~70% precision, and demonstrate their utility for downstream NLP tasks through phrasal paraphrase extraction. We make our code and data freely available.

* 11 pages, accepted to EMNLP 2017
Click to Read Paper
Printed text recognition is an important problem for industrial OCR systems. Printed text is constructed in a standard procedural fashion in most settings. We develop a mathematical model for this process that can be applied to the backward inference problem of text recognition from an image. Through ablation experiments we show that this model is realistic and that a multi-task objective setting can help to stabilize estimation of its free parameters, enabling use of conventional deep learning methods. Furthermore, by directly modeling the geometric perturbations of text synthesis we show that our model can help recover missing characters from incomplete text regions, the bane of multicomponent OCR systems, enabling recognition even when the detection returns incomplete information.

Click to Read Paper
We propose a novel linear discriminant analysis approach for the classification of high-dimensional matrix-valued data that commonly arises from imaging studies. Motivated by the equivalence of the conventional linear discriminant analysis and the ordinary least squares, we consider an efficient nuclear norm penalized regression that encourages a low-rank structure. Theoretical properties including a non-asymptotic risk bound and a rank consistency result are established. Simulation studies and an application to electroencephalography data show the superior performance of the proposed method over the existing approaches.

Click to Read Paper
Nearest neighbor has always been one of the most appealing non-parametric approaches in machine learning, pattern recognition, computer vision, etc. Previous empirical studies partly shows that nearest neighbor is resistant to noise, yet there is a lack of deep analysis. This work presents the finite-sample and distribution-dependent bounds on the consistency of nearest neighbor in the random noise setting. The theoretical results show that, for asymmetric noises, k-nearest neighbor is robust enough to classify most data correctly, except for a handful of examples, whose labels are totally misled by random noises. For symmetric noises, however, k-nearest neighbor achieves the same consistent rate as that of noise-free setting, which verifies the resistance of k-nearest neighbor to random noisy labels. Motivated by the theoretical analysis, we propose the Robust k-Nearest Neighbor (RkNN) approach to deal with noisy labels. The basic idea is to make unilateral corrections to examples, whose labels are totally misled by random noises, and classify the others directly by utilizing the robustness of k-nearest neighbor. We verify the effectiveness of the proposed algorithm both theoretically and empirically.

* 35 pages
Click to Read Paper
The incidence of thyroid nodule is very high and generally increases with the age. Thyroid nodule may presage the emergence of thyroid cancer. The thyroid nodule can be completely cured if detected early. Fine needle aspiration cytology is a recognized early diagnosis method of thyroid nodule. There are still some limitations in the fine needle aspiration cytology, and the ultrasound diagnosis of thyroid nodule has become the first choice for auxiliary examination of thyroid nodular disease. If we could combine medical imaging technology and fine needle aspiration cytology, the diagnostic rate of thyroid nodule would be improved significantly. The properties of ultrasound will degrade the image quality, which makes it difficult to recognize the edges for physicians. Image segmentation technique based on graph theory has become a research hotspot at present. Normalized cut (Ncut) is a representative one, which is suitable for segmentation of feature parts of medical image. However, how to solve the normalized cut has become a problem, which needs large memory capacity and heavy calculation of weight matrix. It always generates over segmentation or less segmentation which leads to inaccurate in the segmentation. The speckle noise in B ultrasound image of thyroid tumor makes the quality of the image deteriorate. In the light of this characteristic, we combine the anisotropic diffusion model with the normalized cut in this paper. After the enhancement of anisotropic diffusion model, it removes the noise in the B ultrasound image while preserves the important edges and local details. This reduces the amount of computation in constructing the weight matrix of the improved normalized cut and improves the accuracy of the final segmentation results. The feasibility of the method is proved by the experimental results.

* 15pages,13figures
Click to Read Paper
Recommender system has attracted much attention during the past decade. Many attack detection algorithms have been developed for better recommendations, mostly focusing on shilling attacks, where an attack organizer produces a large number of user profiles by the same strategy to promote or demote an item. This work considers a different attack style: unorganized malicious attacks, where attackers individually utilize a small number of user profiles to attack different items without any organizer. This attack style occurs in many real applications, yet relevant study remains open. We first formulate the unorganized malicious attacks detection as a matrix completion problem, and propose the Unorganized Malicious Attacks detection (UMA) approach, a proximal alternating splitting augmented Lagrangian method. We verify, both theoretically and empirically, the effectiveness of our proposed approach.

Click to Read Paper
Despite being so vital to success of Support Vector Machines, the principle of separating margin maximisation is not used in deep learning. We show that minimisation of margin variance and not maximisation of the margin is more suitable for improving generalisation in deep architectures. We propose the Halfway loss function that minimises the Normalised Margin Variance (NMV) at the output of a deep learning models and evaluate its performance against the Softmax Cross-Entropy loss on the MNIST, smallNORB and CIFAR-10 datasets.

Click to Read Paper
AUC is an important performance measure and many algorithms have been devoted to AUC optimization, mostly by minimizing a surrogate convex loss on a training data set. In this work, we focus on one-pass AUC optimization that requires only going through the training data once without storing the entire training dataset, where conventional online learning algorithms cannot be applied directly because AUC is measured by a sum of losses defined over pairs of instances from different classes. We develop a regression-based algorithm which only needs to maintain the first and second order statistics of training data in memory, resulting a storage requirement independent from the size of training data. To efficiently handle high dimensional data, we develop a randomized algorithm that approximates the covariance matrices by low rank matrices. We verify, both theoretically and empirically, the effectiveness of the proposed algorithm.

* Proceeding of 30th International Conference on Machine Learning
Click to Read Paper
Traffic prediction has drawn increasing attention in AI research field due to the increasing availability of large-scale traffic data and its importance in the real world. For example, an accurate taxi demand prediction can assist taxi companies in pre-allocating taxis. The key challenge of traffic prediction lies in how to model the complex spatial dependencies and temporal dynamics. Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i.e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical. However, in practice, the spatial dependence could be dynamic (i.e., changing from time to time), and the temporal dynamics could have some perturbation from one period to another period. In this paper, we make two important observations: (1) the spatial dependencies between locations are dynamic; and (2) the temporal dependency follows daily and weekly pattern but it is not strictly periodic for its dynamic temporal shifting. To address these two issues, we propose a novel Spatial-Temporal Dynamic Network (STDN), in which a flow gating mechanism is introduced to learn the dynamic similarity between locations, and a periodically shifted attention mechanism is designed to handle long-term periodic temporal shifting. To the best of our knowledge, this is the first work that tackles both issues in a unified framework. Our experimental results on real-world traffic datasets verify the effectiveness of the proposed method.

* Accepted by AAAI 2019
Click to Read Paper
Chinese poetry generation is a very challenging task in natural language processing. In this paper, we propose a novel two-stage poetry generating method which first plans the sub-topics of the poem according to the user's writing intent, and then generates each line of the poem sequentially, using a modified recurrent neural network encoder-decoder framework. The proposed planning-based method can ensure that the generated poem is coherent and semantically consistent with the user's intent. A comprehensive evaluation with human judgments demonstrates that our proposed approach outperforms the state-of-the-art poetry generating methods and the poem quality is somehow comparable to human poets.

* Accepted paper at COLING 2016
Click to Read Paper
With the explosive growth of web-based cameras and mobile devices, billions of photographs are uploaded to the internet. We can trivially collect a huge number of photo streams for various goals, such as 3D scene reconstruction and other big data applications. However, this is not an easy task due to the fact the retrieved photos are neither aligned nor calibrated. Furthermore, with the occlusion of unexpected foreground objects like people, vehicles, it is even more challenging to find feature correspondences and reconstruct realistic scenes. In this paper, we propose a structure based image completion algorithm for object removal that produces visually plausible content with consistent structure and scene texture. We use an edge matching technique to infer the potential structure of the unknown region. Driven by the estimated structure, texture synthesis is performed automatically along the estimated curves. We evaluate the proposed method on different types of images: from highly structured indoor environment to the natural scenes. Our experimental results demonstrate satisfactory performance that can be potentially used for subsequent big data processing: 3D scene reconstruction and location recognition.

* 6 pages, IEEE International Conference on Computer Communications (INFOCOM 14), Workshop on Security and Privacy in Big Data, Toronto, Canada, 2014
Click to Read Paper
Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform natural language inference (NLI) from these data? If not, how can neural-network-based NLI models benefit from external knowledge and how to build NLI models to leverage it? In this paper, we enrich the state-of-the-art neural natural language inference models with external knowledge. We demonstrate that the proposed models improve neural NLI models to achieve the state-of-the-art performance on the SNLI and MultiNLI datasets.

* Accepted by ACL 2018
Click to Read Paper
Deep convolutional neural network models pre-trained for the ImageNet classification task have been successfully adopted to tasks in other domains, such as texture description and object proposal generation, but these tasks require annotations for images in the new domain. In this paper, we focus on a novel and challenging task in the pure unsupervised setting: fine-grained image retrieval. Even with image labels, fine-grained images are difficult to classify, let alone the unsupervised retrieval task. We propose the Selective Convolutional Descriptor Aggregation (SCDA) method. SCDA firstly localizes the main object in fine-grained images, a step that discards the noisy background and keeps useful deep descriptors. The selected descriptors are then aggregated and dimensionality reduced into a short feature vector using the best practices we found. SCDA is unsupervised, using no image label or bounding box annotation. Experiments on six fine-grained datasets confirm the effectiveness of SCDA for fine-grained image retrieval. Besides, visualization of the SCDA features shows that they correspond to visual attributes (even subtle ones), which might explain SCDA's high mean average precision in fine-grained retrieval. Moreover, on general image retrieval datasets, SCDA achieves comparable retrieval results with state-of-the-art general image retrieval approaches.

* IEEE Transactions on Image Processing (TIP), 2017, 26(6): 2868-2881
Click to Read Paper
While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation. Since parallel corpora are usually limited in quantity, quality, and coverage, especially for low-resource languages, it is appealing to exploit monolingual corpora to improve NMT. We propose a semi-supervised approach for training NMT models on the concatenation of labeled (parallel corpora) and unlabeled (monolingual corpora) data. The central idea is to reconstruct the monolingual corpora using an autoencoder, in which the source-to-target and target-to-source translation models serve as the encoder and decoder, respectively. Our approach can not only exploit the monolingual corpora of the target language, but also of the source language. Experiments on the Chinese-English dataset show that our approach achieves significant improvements over state-of-the-art SMT and NMT systems.

* Corrected a typo
Click to Read Paper