Research papers and code for "Xin Wang":
Sparse learning aims to learn the sparse structure of the true target function from the collected data, which plays a crucial role in high dimensional data analysis. This article proposes a unified and universal method for learning sparsity of M-estimators within a rich family of loss functions in a reproducing kernel Hilbert space (RKHS). The family of loss functions interested is very rich, including most commonly used ones in literature. More importantly, the proposed method is motivated by some nice properties in the induced RKHS, and is computationally efficient for large-scale data, and can be further improved through parallel computing. The asymptotic estimation and selection consistencies of the proposed method are established for a general loss function under mild conditions. It works for general loss function, admits general dependence structure, allows for efficient computation, and with theoretical guarantee. The superior performance of our proposed method is also supported by a variety of simulated examples and a real application in the human breast cancer study (GSE20194).

Click to Read Paper and Get Code
A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multi-layer connection of many low-dimensional fuzzy systems, where the input variables to the low-dimensional fuzzy systems are selected through a moving window (a convolution operator) across the input spaces of the layers. To design the DCFS based on input-output data pairs, we propose a bottom-up layer-by-layer scheme. Specifically, by viewing each of the first-layer fuzzy systems as a weak estimator of the output based only on a very small portion of the input variables, we can design these fuzzy systems using the WM Method. After the first-layer fuzzy systems are designed, we pass the data through the first layer and replace the inputs in the original data set by the corresponding outputs of the first layer to form a new data set, then we design the second-layer fuzzy systems based on this new data set in the same way as designing the first-layer fuzzy systems. Repeating this process we design the whole DCFS. Since the WM Method requires only one-pass of the data, this training algorithm for the DCFS is very fast. We apply the DCFS model with the training algorithm to predict a synthetic chaotic plus random time-series and the real Hang Seng Index of the Hong Kong stock market.

Click to Read Paper and Get Code
We propose a new heavy-tailed distribution --- Gaussian-Chain (GC) distribution, which is inspirited by the hierarchical structures prevailing in social organizations. We determine the mean, variance and kurtosis of the Gaussian-Chain distribution to show its heavy-tailed property, and compute the tail distribution table to give specific numbers showing how heavy is the heavy-tails. To filter out the heavy-tailed noise, we construct two filters --- 2nd and 3rd-order GC filters --- based on the maximum likelihood principle. Simulation results show that the GC filters perform much better than the benchmark least-squares algorithm when the noise is heavy-tail distributed. Using the GC filters, we propose a trading strategy, named Ride-the-Mood, to follow the mood of the market by detecting the actions of the big buyers and the big sellers in the market based on the noisy, heavy-tailed price data. Application of the Ride-the-Mood strategy to five blue-chip Hong Kong stocks over the recent two-year period from April 2, 2012 to March 31, 2014 shows that their returns are higher than the returns of the benchmark Buy-and-Hold strategy and the Hang Seng Index Fund.

Click to Read Paper and Get Code
License plate detection and recognition (LPDR) is of growing importance for enabling intelligent transportation and ensuring the security and safety of the cities. However, LPDR faces a big challenge in a practical environment. The license plates can have extremely diverse sizes, fonts and colors, and the plate images are usually of poor quality caused by skewed capturing angles, uneven lighting, occlusion, and blurring. In applications such as surveillance, it often requires fast processing. To enable real-time and accurate license plate recognition, in this work, we propose a set of techniques: 1) a contour reconstruction method along with edge-detection to quickly detect the candidate plates; 2) a simple zero-one-alternation scheme to effectively remove the fake top and bottom borders around plates to facilitate more accurate segmentation of characters on plates; 3) a set of techniques to augment the training data, incorporate SIFT features into the CNN network, and exploit transfer learning to obtain the initial parameters for more effective training; and 4) a two-phase verification procedure to determine the correct plate at low cost, a statistical filtering in the plate detection stage to quickly remove unwanted candidates, and the accurate CR results after the CR process to perform further plate verification without additional processing. We implement a complete LPDR system based on our algorithms. The experimental results demonstrate that our system can accurately recognize license plate in real-time. Additionally, it works robustly under various levels of illumination and noise, and in the presence of car movement. Compared to peer schemes, our system is not only among the most accurate ones but is also the fastest, and can be easily applied to other scenarios.

* License Plate Detection and Recognition, Computer Vision, Supervised Learning
Click to Read Paper and Get Code
Deep neural networks are typically highly over-parameterized with pruning techniques able to remove a significant fraction of network parameters with little loss in accuracy. Recently, techniques based on dynamic re-allocation of non-zero parameters have emerged for training sparse networks directly without having to train a large dense model beforehand. We present a parameter re-allocation scheme that addresses the limitations of previous methods such as their high computational cost and the fixed number of parameters they allocate to each layer. We investigate the performance of these dynamic re-allocation methods in deep convolutional networks and show that our method outperforms previous static and dynamic parameterization methods, yielding the best accuracy for a given number of training parameters, and performing on par with networks obtained by iteratively pruning a trained dense model. We further investigated the mechanisms underlying the superior performance of the resulting sparse networks. We found that neither the structure, nor the initialization of the sparse networks discovered by our parameter reallocation scheme are sufficient to explain their superior generalization performance. Rather, it is the continuous exploration of different sparse network structures during training that is critical to effective learning. We show that it is more fruitful to explore these structural degrees of freedom than to add extra parameters to the network.

Click to Read Paper and Get Code
Real-time crime forecasting is important. However, accurate prediction of when and where the next crime will happen is difficult. No known physical model provides a reasonable approximation to such a complex system. Historical crime data are sparse in both space and time and the signal of interests is weak. In this work, we first present a proper representation of crime data. We then adapt the spatial temporal residual network on the well represented data to predict the distribution of crime in Los Angeles at the scale of hours in neighborhood-sized parcels. These experiments as well as comparisons with several existing approaches to prediction demonstrate the superiority of the proposed model in terms of accuracy. Finally, we present a ternarization technique to address the resource consumption issue for its deployment in real world. This work is an extension of our short conference proceeding paper [Wang et al, Arxiv 1707.03340].

* 14 pages, 7 figures
Click to Read Paper and Get Code
Variable selection is central to high-dimensional data analysis, and various algorithms have been developed. Ideally, a variable selection algorithm shall be flexible, scalable, and with theoretical guarantee, yet most existing algorithms cannot attain these properties at the same time. In this article, a three-step variable selection algorithm is developed, involving kernel-based estimation of the regression function and its gradient functions as well as a hard thresholding. Its key advantage is that it assumes no explicit model assumption, admits general predictor effects, allows for scalable computation, and attains desirable asymptotic sparsistency. The proposed algorithm can be adapted to any reproducing kernel Hilbert space (RKHS) with different kernel functions, and can be extended to interaction selection with slight modification. Its computational cost is only linear in the data dimension, and can be further improved through parallel computing. The sparsistency of the proposed algorithm is established for general RKHS under mild conditions, including linear and Gaussian kernels as special cases. Its effectiveness is also supported by a variety of simulated and real examples.

* 27 pages, 5 figures
Click to Read Paper and Get Code
Based on API call sequences, semantic-aware and machine learning (ML) based malware classifiers can be built for malware detection or classification. Previous works concentrate on crafting and extracting various features from malware binaries, disassembled binaries or API calls via static or dynamic analysis and resorting to ML to build classifiers. However, they tend to involve too much feature engineering and fail to provide interpretability. We solve these two problems with the recent advances in deep learning: 1) RNN-based autoencoders (RNN-AEs) can automatically learn low-dimensional representation of a malware from its raw API call sequence. 2) Multiple decoders can be trained under different supervisions to give more information, other than the class or family label of a malware. Inspired by the works of document classification and automatic sentence summarization, each API call sequence can be regarded as a sentence. In this paper, we make the first attempt to build a multi-task malware learning model based on API call sequences. The model consists of two decoders, one for malware classification and one for $\emph{file access pattern}$ (FAP) generation given the API call sequence of a malware. We base our model on the general seq2seq framework. Experiments show that our model can give competitive classification results as well as insightful FAP information.

Click to Read Paper and Get Code
The sequential order of utterances is often meaningful in coherent dialogues, and the order changes of utterances could lead to low-quality and incoherent conversations. We consider the order information as a crucial supervised signal for dialogue learning, which, however, has been neglected by many previous dialogue systems. Therefore, in this paper, we introduce a self-supervised learning task, inconsistent order detection, to explicitly capture the flow of conversation in dialogues. Given a sampled utterance pair triple, the task is to predict whether it is ordered or misordered. Then we propose a sampling-based self-supervised network SSN to perform the prediction with sampled triple references from previous dialogue history. Furthermore, we design a joint learning framework where SSN can guide the dialogue systems towards more coherent and relevant dialogue learning through adversarial training. We demonstrate that the proposed methods can be applied to both open-domain and task-oriented dialogue scenarios, and achieve the new state-of-the-art performance on the OpenSubtitiles and Movie-Ticket Booking datasets.

* 11pages, 2 figures, accepted to ACL 2019
Click to Read Paper and Get Code
Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model, WaveNet is limited by a slow sequential waveform generation process. Some new models that use the inverse-autoregressive flow (IAF) can generate a whole waveform in a one-shot manner. However, these IAF-based models require sequential transformation during training, which severely slows down the training speed. Other models such as Parallel WaveNet and ClariNet bring together the benefits of AR and IAF-based models and train an IAF model by transferring the knowledge from a pre-trained AR teacher to an IAF student without any sequential transformation. However, both models require additional training criteria, and their implementation is prohibitively complicated. We propose a framework for neural source-filter (NSF) waveform modeling without AR nor IAF-based approaches. This framework requires only three components for waveform generation: a source module that generates a sine-based signal as excitation, a non-AR dilated-convolution-based filter module that transforms the excitation into a waveform, and a conditional module that pre-processes the acoustic features for the source and filer modules. This framework minimizes spectral-amplitude distances for model training, which can be efficiently implemented by using short-time Fourier transform routines. Under this framework, we designed three NSF models and compared them with WaveNet. It was demonstrated that the NSF models generated waveforms at least 100 times faster than WaveNet, and the quality of the synthetic speech from the best NSF model was better than or equally good as that from WaveNet.

* Submitted to IEEE/ACM TASLP
Click to Read Paper and Get Code
The overreliance on large parallel corpora significantly limits the applicability of machine translation systems to the majority of language pairs. Back-translation has been dominantly used in previous approaches for unsupervised neural machine translation, where pseudo sentence pairs are generated to train the models with a reconstruction loss. However, the pseudo sentences are usually of low quality as translation errors accumulate during training. To avoid this fundamental issue, we propose an alternative but more effective approach, extract-edit, to extract and then edit real sentences from the target monolingual corpora. Furthermore, we introduce a comparative translation loss to evaluate the translated target sentences and thus train the unsupervised translation systems. Experiments show that the proposed approach consistently outperforms the previous state-of-the-art unsupervised machine translation systems across two benchmarks (English-French and English-German) and two low-resource language pairs (English-Romanian and English-Russian) by more than 2 (up to 3.63) BLEU points.

* 11 pages, 3 figures. Accepted to NAACL 2019
Click to Read Paper and Get Code
In this paper, we propose and study opportunistic contextual bandits - a special case of contextual bandits where the exploration cost varies under different environmental conditions, such as network load or return variation in recommendations. When the exploration cost is low, so is the actual regret of pulling a sub-optimal arm (e.g., trying a suboptimal recommendation). Therefore, intuitively, we could explore more when the exploration cost is relatively low and exploit more when the exploration cost is relatively high. Inspired by this intuition, for opportunistic contextual bandits with Linear payoffs, we propose an Adaptive Upper-Confidence-Bound algorithm (AdaLinUCB) to adaptively balance the exploration-exploitation trade-off for opportunistic learning. We prove that AdaLinUCB achieves O((log T)^2) problem-dependent regret upper bound, which has a smaller coefficient than that of the traditional LinUCB algorithm. Moreover, based on both synthetic and real-world dataset, we show that AdaLinUCB significantly outperforms other contextual bandit algorithms, under large exploration cost fluctuations.

Click to Read Paper and Get Code
In the era of Internet, recognizing pornographic images is of great significance for protecting children's physical and mental health. However, this task is very challenging as the key pornographic contents (e.g., breast and private part) in an image often lie in local regions of small size. In this paper, we model each image as a bag of regions, and follow a multiple instance learning (MIL) approach to train a generic region-based recognition model. Specifically, we take into account the region's degree of pornography, and make three main contributions. First, we show that based on very few annotations of the key pornographic contents in a training image, we can generate a bag of properly sized regions, among which the potential positive regions usually contain useful contexts that can aid recognition. Second, we present a simple quantitative measure of a region's degree of pornography, which can be used to weigh the importance of different regions in a positive image. Third, we formulate the recognition task as a weighted MIL problem under the convolutional neural network framework, with a bag probability function introduced to combine the importance of different regions. Experiments on our newly collected large scale dataset demonstrate the effectiveness of the proposed method, achieving an accuracy with 97.52% true positive rate at 1% false positive rate, tested on 100K pornographic images and 100K normal images.

* IEEE transactions on cybernetics, 2018
* 9 pages, 3 figures
Click to Read Paper and Get Code
We introduce a novel encoder-decoder architecture to embed functional processes into latent vector spaces. This embedding can then be decoded to sample the encoded functions over any arbitrary domain. This autoencoder generalizes the recently introduced Conditional Neural Process (CNP) model of random processes. Our architecture employs the latest advances in graph neural networks to process irregularly sampled functions. Thus, we refer to our model as Conditional Graph Neural Process (CGNP). Graph neural networks can effectively exploit `local' structures of the metric spaces over which the functions/processes are defined. The contributions of this paper are twofold: (i) a novel graph-based encoder-decoder architecture for functional and process embeddings, and (ii) a demonstration of the importance of using the structure of metric spaces for this type of representations.

* 3 pages, 1 figure, 1 table, published in the Third Workshop on Bayesian Deep Learning (NeurIPS 2018), Montr\'eal, Canada
Click to Read Paper and Get Code
Neural waveform models such as the WaveNet are used in many recent text-to-speech systems, but the original WaveNet is quite slow in waveform generation because of its autoregressive (AR) structure. Although faster non-AR models were recently reported, they may be prohibitively complicated due to the use of a distilling training method and the blend of other disparate training criteria. This study proposes a non-AR neural source-filter waveform model that can be directly trained using spectrum-based training criteria and the stochastic gradient descent method. Given the input acoustic features, the proposed model first uses a source module to generate a sine-based excitation signal and then uses a filter module to transform the excitation signal into the output speech waveform. Our experiments demonstrated that the proposed model generated waveforms at least 100 times faster than the AR WaveNet and the quality of its synthetic speech is close to that of speech generated by the AR WaveNet. Ablation test results showed that both the sine-wave excitation signal and the spectrum-based training criteria were essential to the performance of the proposed model.

* Submitted to ICASSP 2019
Click to Read Paper and Get Code
We present Accel, a novel semantic video segmentation system that achieves high accuracy at low inference cost by combining the predictions of two network branches: (1) a reference branch that extracts high-detail features on a reference keyframe, and warps these features forward using frame-to-frame optical flow estimates, and (2) an update branch that computes features of adjustable quality on the current frame, performing a temporal update at each video frame. The modularity of the update branch, where feature subnetworks of varying layer depth can be inserted (e.g. ResNet-18 to ResNet-101), enables operation over a new, state-of-the-art accuracy-throughput trade-off spectrum. Over this curve, Accel models achieve both higher accuracy and faster inference times than the closest comparable single-frame segmentation networks. In general, Accel significantly outperforms previous work on efficient semantic video segmentation, correcting warping-related error that compounds on datasets with complex dynamics. Accel is end-to-end trainable and highly modular: the reference network, the optical flow network, and the update network can each be selected independently, depending on application requirements, and then jointly fine-tuned. The result is a robust, general system for fast, high-accuracy semantic segmentation on video.

* 8 pages
Click to Read Paper and Get Code
Network embedding has become a hot research topic recently which can provide low-dimensional feature representations for many machine learning applications. Current work focuses on either (1) whether the embedding is designed as an unsupervised learning task by explicitly preserving the structural connectivity in the network, or (2) whether the embedding is a by-product during the supervised learning of a specific discriminative task in a deep neural network. In this paper, we focus on bridging the gap of the two lines of the research. We propose to adapt the Generative Adversarial model to perform network embedding, in which the generator is trying to generate vertex pairs, while the discriminator tries to distinguish the generated vertex pairs from real connections (edges) in the network. Wasserstein-1 distance is adopted to train the generator to gain better stability. We develop three variations of models, including GANE which applies cosine similarity, GANE-O1 which preserves the first-order proximity, and GANE-O2 which tries to preserves the second-order proximity of the network in the low-dimensional embedded vector space. We later prove that GANE-O2 has the same objective function as GANE-O1 when negative sampling is applied to simplify the training process in GANE-O2. Experiments with real-world network datasets demonstrate that our models constantly outperform state-of-the-art solutions with significant improvements on precision in link prediction, as well as on visualizations and accuracy in clustering tasks.

Click to Read Paper and Get Code
A major challenge for video captioning is to combine audio and visual cues. Existing multi-modal fusion methods have shown encouraging results in video understanding. However, the temporal structures of multiple modalities at different granularities are rarely explored, and how to selectively fuse the multi-modal representations at different levels of details remains uncharted. In this paper, we propose a novel hierarchically aligned cross-modal attention (HACA) framework to learn and selectively fuse both global and local temporal dynamics of different modalities. Furthermore, for the first time, we validate the superior performance of the deep audio features on the video captioning task. Finally, our HACA model significantly outperforms the previous best systems and achieves new state-of-the-art results on the widely used MSR-VTT dataset.

* NAACL 2018
Click to Read Paper and Get Code
Sparse coding approximates the data sample as a sparse linear combination of some basic codewords and uses the sparse codes as new presentations. In this paper, we investigate learning discriminative sparse codes by sparse coding in a semi-supervised manner, where only a few training samples are labeled. By using the manifold structure spanned by the data set of both labeled and unlabeled samples and the constraints provided by the labels of the labeled samples, we learn the variable class labels for all the samples. Furthermore, to improve the discriminative ability of the learned sparse codes, we assume that the class labels could be predicted from the sparse codes directly using a linear classifier. By solving the codebook, sparse codes, class labels and classifier parameters simultaneously in a unified objective function, we develop a semi-supervised sparse coding algorithm. Experiments on two real-world pattern recognition problems demonstrate the advantage of the proposed methods over supervised sparse coding methods on partially labeled data sets.

Click to Read Paper and Get Code