Research papers and code for "Wang Zhu":
Many real-world datasets are labeled with natural orders, i.e., ordinal labels. Ordinal regression is a method to predict ordinal labels that finds a wide range of applications in data-rich science domains, such as medical, social and economic sciences. Most existing approaches work well for a single ordinal regression task. However, they ignore the task relatedness when there are multiple related tasks. Multi-task learning (MTL) provides a framework to encode task relatedness, to bridge data from all tasks, and to simultaneously learn multiple related tasks to improve the generalization performance. Even though MTL methods have been extensively studied, there is barely existing work investigating MTL for data with ordinal labels. We tackle multiple ordinal regression problems via sparse and deep multi-task approaches, i.e., two regularized multi-task ordinal regression (RMTOR) models for small datasets and two deep neural networks based multi-task ordinal regression (DMTOR) models for large-scale datasets. The performance of the proposed multi-task ordinal regression models (MTOR) is demonstrated on three real-world medical datasets for multi-stage disease diagnosis. Our experimental results indicate that our proposed MTOR models markedly improve the prediction performance comparing with single-task learning (STL) ordinal regression models.

* 18 pages, 2 figures
Click to Read Paper and Get Code
In this paper, we propose an end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers of the images, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data augmentation constraint, auto-encoder reconstruction loss constraint and latent features plus noise constraint to improve clustering performance. Specifically, we perform one-to-one data augmentation such as rotation, shear, and shift before data is input to the encoder to learn the more effective features. The data and the enhanced data are simultaneously input into the auto-encoder to obtain latent features and augmented latent features whose similarity are constrained by an augmentation loss. Then, making use of the MMD distance, we combine the latent features and augmented latent features to make their distribution close to the PEDCC distribution (uniform distribution between classes, Dirac distribution within the class) to further learn the features used for clustering. At the same time, the MSE of the original input image and reconstructed image is used as reconstruction constraint, and the noise is added to the latent features to build generalization constraint to improve the generalization ability. Finally, extensive experiments on three common datasets MNIST, Fashion-MNIST, COIL20 are conducted. The experimental results show that the algorithm has achieved the best clustering results so far, and also has good generalization ability. In addition, we can use the pre-defined PEDCC class centers, and the decoding module of the auto-encoder to clearly generate the samples of each class. The code can be downloaded at xxx!

Click to Read Paper and Get Code
To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps. Different from existing pruning criteria, which are mainly based on L1-norm of convolution kernels, the proposed method utilizes Ln-norm of output feature maps after non-linear activations, where n is a variable, increasing from 1 at the first convolution layer to inf at the last convolution layer. With the ability of accurately identifying unimportant convolution kernels, the proposed method achieves a good balance between model size and inference accuracy. The experiments on ImageNet and the successful application in railway surveillance system show that the proposed method outperforms existing kernel-norm-based methods and is generally applicable to any deep neural network with convolution operations.

Click to Read Paper and Get Code
Consumers' purchase decisions are increasingly influenced by user-generated online reviews. Accordingly, there has been growing concern about the potential for posting deceptive opinion spam fictitious reviews that have been deliberately written to sound authentic, to deceive the readers. Existing approaches mainly focus on developing automatic supervised learning based methods to help users identify deceptive opinion spams. This work, we used the LSI and Sprinkled LSI technique to reduce the dimension for deception detection. We make our contribution to demonstrate what LSI is capturing in latent semantic space and reveal how deceptive opinions can be recognized automatically from truthful opinions. Finally, we proposed a voting scheme which integrates different approaches to further improve the classification performance.

* arXiv admin note: text overlap with arXiv:1204.2804 by other authors
Click to Read Paper and Get Code
Rough sets are efficient for data pre-processing in data mining. As a generalization of the linear independence in vector spaces, matroids provide well-established platforms for greedy algorithms. In this paper, we apply rough sets to matroids and study the contraction of the dual of the corresponding matroid. First, for an equivalence relation on a universe, a matroidal structure of the rough set is established through the lower approximation operator. Second, the dual of the matroid and its properties such as independent sets, bases and rank function are investigated. Finally, the relationships between the contraction of the dual matroid to the complement of a single point set and the contraction of the dual matroid to the complement of the equivalence class of this point are studied.

* 11 pages
Click to Read Paper and Get Code
This study proposes a framework for human-like autonomous car-following planning based on deep reinforcement learning (deep RL). Historical driving data are fed into a simulation environment where an RL agent learns from trial and error interactions based on a reward function that signals how much the agent deviates from the empirical data. Through these interactions, an optimal policy, or car-following model that maps in a human-like way from speed, relative speed between a lead and following vehicle, and inter-vehicle spacing to acceleration of a following vehicle is finally obtained. The model can be continuously updated when more data are fed in. Two thousand car-following periods extracted from the 2015 Shanghai Naturalistic Driving Study were used to train the model and compare its performance with that of traditional and recent data-driven car-following models. As shown by this study results, a deep deterministic policy gradient car-following model that uses disparity between simulated and observed speed as the reward function and considers a reaction delay of 1s, denoted as DDPGvRT, can reproduce human-like car-following behavior with higher accuracy than traditional and recent data-driven car-following models. Specifically, the DDPGvRT model has a spacing validation error of 18% and speed validation error of 5%, which are less than those of other models, including the intelligent driver model, models based on locally weighted regression, and conventional neural network-based models. Moreover, the DDPGvRT demonstrates good capability of generalization to various driving situations and can adapt to different drivers by continuously learning. This study demonstrates that reinforcement learning methodology can offer insight into driver behavior and can contribute to the development of human-like autonomous driving algorithms and traffic-flow models.

* Transportation Research Part C: Emerging Technologies 2018
Click to Read Paper and Get Code
In this work we develop a distributed least squares approximation (DLSA) method, which is able to solve a large family of regression problems (e.g., linear regression, logistic regression, Cox's model) on a distributed system. By approximating the local objective function using a local quadratic form, we are able to obtain a combined estimator by taking a weighted average of local estimators. The resulting estimator is proved to be statistically as efficient as the global estimator. In the meanwhile it requires only one round of communication. We further conduct the shrinkage estimation based on the DLSA estimation by using an adaptive Lasso approach. The solution can be easily obtained by using the LARS algorithm on the master node. It is theoretically shown that the resulting estimator enjoys the oracle property and is selection consistent by using a newly designed distributed Bayesian Information Criterion (DBIC). The finite sample performance as well as the computational efficiency are further illustrated by extensive numerical study and an airline dataset. The airline dataset is 52GB in memory size. The entire methodology has been implemented by Python for a de-facto standard Spark system. By using the proposed DLSA algorithm on the Spark system, it takes 26 minutes to obtain a logistic regression estimator whereas a full likelihood algorithm takes 15 hours to reaches an inferior result.

Click to Read Paper and Get Code
In recent years, perceptual-quality driven super-resolution methods show satisfactory results. However, super-resolved images have uncertain texture details and unpleasant artifact. We build a novel perceptual loss function composed of morphological components adversarial loss and color adversarial loss and salient content loss to ameliorate these problems. The adversarial loss is applied to constrain color and morphological components distribution of super-resolved images and the salient content loss highlights the perceptual similarity of feature-rich regions. Experiments show that proposed method achieves significant improvements in terms of perceptual index and visual quality compared with the state-of-the-art methods.

* 11 pages, 7 figures, 1 table
Click to Read Paper and Get Code
Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words. Recently a new language representation model, BERT (Bidirectional Encoder Representations from Transformers), facilitates pre-training deep bidirectional representations on large-scale unlabeled corpora, and has created state-of-the-art models for a wide variety of natural language processing tasks after simple fine-tuning. However, there has not been much effort on exploring BERT for natural language understanding. In this work, we propose a joint intent classification and slot filling model based on BERT. Experimental results demonstrate that our proposed model achieves significant improvement on intent classification accuracy, slot filling F1, and sentence-level semantic frame accuracy on several public benchmark datasets, compared to the attention-based recurrent neural network models and slot-gated models.

* 4 pages, 1 figure
Click to Read Paper and Get Code
In computer vision applications, such as domain adaptation (DA), few shot learning (FSL) and zero-shot learning (ZSL), we encounter new objects and environments, for which insufficient examples exist to allow for training "models from scratch," and methods that adapt existing models, trained on the presented training environment, to the new scenario are required. We propose a novel visual attribute encoding method that encodes each image as a low-dimensional probability vector composed of prototypical part-type probabilities. The prototypes are learnt to be representative of all training data. At test-time we utilize this encoding as an input to a classifier. At test-time we freeze the encoder and only learn/adapt the classifier component to limited annotated labels in FSL; new semantic attributes in ZSL. We conduct extensive experiments on benchmark datasets. Our method outperforms state-of-art methods trained for the specific contexts (ZSL, FSL, DA).

* 11 pages, 3 figures, 3 tables
Click to Read Paper and Get Code
The popularity of mobile devices results in the availability of enormous data and computational resources at the network edge. To leverage the data and resources, a new machine learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing fast and intelligent services to mobile users. While computing speeds are advancing rapidly, the communication latency is becoming the bottleneck of fast edge learning. To address this issue, this work is focused on designing a low latency multi-access scheme for edge learning. We consider a popular framework, federated edge learning (FEEL), where edge-server and on-device learning are synchronized to train a model without violating user-data privacy. It is proposed that model updates simultaneously transmitted by devices over broadband channels should be analog aggregated "over-the-air" by exploiting the superposition property of a multi-access channel. Thereby, "interference" is harnessed to provide fast implementation of the model aggregation. This results in dramatical latency reduction compared with the traditional orthogonal access (i.e., OFDMA). In this work, the performance of FEEL is characterized targeting a single-cell random network. First, due to power alignment between devices as required for aggregation, a fundamental tradeoff is shown to exist between the update-reliability and the expected update-truncation ratio. This motivates the design of an opportunistic scheduling scheme for FEEL that selects devices within a distance threshold. This scheme is shown using real datasets to yield satisfactory learning performance in the presence of high mobility. Second, both the multi-access latency of the proposed analog aggregation and the OFDMA scheme are analyzed. Their ratio, which quantifies the latency reduction of the former, is proved to scale almost linearly with device population.

* This is an extended version of a submission to IEEE journal
Click to Read Paper and Get Code
We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Prior works in this context propose to map high-dimensional visual features to the semantic domain, we believe contributes to the semantic gap. To bridge the gap, we propose a novel low-dimensional embedding of visual instances that is "visually semantic." Analogous to semantic data that quantifies the existence of an attribute in the presented instance, components of our visual embedding quantifies existence of a prototypical part-type in the presented instance. In parallel, as a thought experiment, we quantify the impact of noisy semantic data by utilizing a novel visual oracle to visually supervise a learner. These factors, namely semantic noise, visual-semantic gap and label noise lead us to propose a new graphical model for inference with pairwise interactions between label, semantic data, and inputs. We tabulate results on a number of benchmark datasets demonstrating significant improvement in accuracy over state-of-the-art under both semantic and visual supervision.

* 9 pages, 3 figures, 6 tables
Click to Read Paper and Get Code
Deep transfer learning has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer learning is arguably the most frequently used method. However, very little work has been devoted to enhancing deep transfer learning by focusing on the influence of data. In this work, we propose an instance-based approach to improve deep transfer learning in target domain. Specifically, we choose a pre-trained model which is learned from a source domain, and utilize this model to estimate the influence of each training sample in a target domain. Then we optimize training data of the target domain by removing the training samples that will lower the performance of the pre-trained model. We then fine-tune the pre-trained model with the optimized training data in the target domain, or build a new model which can be initialized partially based on the pre-trained model, and fine-tune it with the optimized training data in the target domain. Using this approach, transfer learning can help deep learning models to learn more useful features. Extensive experiments demonstrate the effectiveness of our approach on further boosting deep learning models for typical high-level computer vision tasks, such as image classification.

Click to Read Paper and Get Code
In this paper, we propose a new pipeline of training a monocular UAV to fly a collision-free trajectory along the dense forest trail. As gathering high-precision images in the real world is expensive and the off-the-shelf dataset has some deficiencies, we collect a new dense forest trail dataset in a variety of simulated environment in Unreal Engine. Then we formulate visual perception of forests as a classification problem. A ResNet-18 model is trained to decide the moving direction frame by frame. To transfer the learned strategy to the real world, we construct a ResNet-18 adaptation model via multi-kernel maximum mean discrepancies to leverage the relevant labelled data and alleviate the discrepancy between simulated and real environment. Simulation and real-world flight with a variety of appearance and environment changes are both tested. The ResNet-18 adaptation and its variant model achieve the best result of 84.08% accuracy in reality.

* Accepted by IJCAI-ECAI 2018, 7 pages, 5 figures
Click to Read Paper and Get Code
A multitude of publicly-available driving datasets and data platforms have been raised for autonomous vehicles (AV). However, the heterogeneities of databases in size, structure and driving context make existing datasets practically ineffective due to a lack of uniform frameworks and searchable indexes. In order to overcome these limitations on existing public datasets, this paper proposes a data unification framework based on traffic primitives with ability to automatically unify and label heterogeneous traffic data. This is achieved by two steps: 1) Carefully arrange raw multidimensional time series driving data into a relational database and then 2) automatically extract labeled and indexed traffic primitives from traffic data through a Bayesian nonparametric learning method. Finally, we evaluate the effectiveness of our developed framework using the collected real vehicle data.

* 6 pages, 7 figures, 1 table, ITSC 2018
Click to Read Paper and Get Code
For massive data, the family of subsampling algorithms is popular to downsize the data volume and reduce computational burden. Existing studies focus on approximating the ordinary least squares estimate in linear regression, where statistical leverage scores are often used to define subsampling probabilities. In this paper, we propose fast subsampling algorithms to efficiently approximate the maximum likelihood estimate in logistic regression. We first establish consistency and asymptotic normality of the estimator from a general subsampling algorithm, and then derive optimal subsampling probabilities that minimize the asymptotic mean squared error of the resultant estimator. An alternative minimization criterion is also proposed to further reduce the computational cost. The optimal subsampling probabilities depend on the full data estimate, so we develop a two-step algorithm to approximate the optimal subsampling procedure. This algorithm is computationally efficient and has a significant reduction in computing time compared to the full data approach. Consistency and asymptotic normality of the estimator from a two-step algorithm are also established. Synthetic and real data sets are used to evaluate the practical performance of the proposed method.

Click to Read Paper and Get Code
Efficient and accurate segmentation of light field is an important task in computer vision and graphics. The large volume of input data and the redundancy of light field make it an open challenge. In the paper, we propose a novel graph representation for interactive light field segmentation based on light field super-pixel (LFSP). The LFSP not only maintains light field redundancy, but also greatly reduces the graph size. These advantages make LFSP useful to improve segmentation efficiency. Based on LFSP graph structure, we present an efficient light field segmentation algorithm using graph-cuts. Experimental results on both synthetic and real dataset demonstrate that our method is superior to previous light field segmentation algorithms with respect to accuracy and efficiency.

* 12 pages, 9 figures
Click to Read Paper and Get Code
In this paper, we propose a novel convolutional neural network (CNN) for image denoising, which uses exponential linear unit (ELU) as the activation function. We investigate the suitability by analyzing ELU's connection with trainable nonlinear reaction diffusion model (TNRD) and residual denoising. On the other hand, batch normalization (BN) is indispensable for residual denoising and convergence purpose. However, direct stacking of BN and ELU degrades the performance of CNN. To mitigate this issue, we design an innovative combination of activation layer and normalization layer to exploit and leverage the ELU network, and discuss the corresponding rationale. Moreover, inspired by the fact that minimizing total variation (TV) can be applied to image denoising, we propose a TV regularized L2 loss to evaluate the training effect during the iterations. Finally, we conduct extensive experiments, showing that our model outperforms some recent and popular approaches on Gaussian denoising with specific or randomized noise levels for both gray and color images.

* 10 pages, Accepted by the 24th International Conference on Neural Information Processing (2017)
Click to Read Paper and Get Code
Discovering automatically the semantic structure of tagged visual data (e.g. web videos and images) is important for visual data analysis and interpretation, enabling the machine intelligence for effectively processing the fast-growing amount of multi-media data. However, this is non-trivial due to the need for jointly learning underlying correlations between heterogeneous visual and tag data. The task is made more challenging by inherently sparse and incomplete tags. In this work, we develop a method for modelling the inherent visual data concept structures based on a novel Hierarchical-Multi-Label Random Forest model capable of correlating structured visual and tag information so as to more accurately interpret the visual semantics, e.g. disclosing meaningful visual groups with similar high-level concepts, and recovering missing tags for individual visual data samples. Specifically, our model exploits hierarchically structured tags of different semantic abstractness and multiple tag statistical correlations in addition to modelling visual and tag interactions. As a result, our model is able to discover more accurate semantic correlation between textual tags and visual features, and finally providing favourable visual semantics interpretation even with highly sparse and incomplete tags. We demonstrate the advantages of our proposed approach in two fundamental applications, visual data clustering and missing tag completion, on benchmarking video (i.e. TRECVID MED 2011) and image (i.e. NUS-WIDE) datasets.

* Artificial Intelligence journal 2017
Click to Read Paper and Get Code
Representation learning of knowledge graphs encodes entities and relation types into a continuous low-dimensional vector space, learns embeddings of entities and relation types. Most existing methods only concentrate on knowledge triples, ignoring logic rules which contain rich background knowledge. Although there has been some work aiming at leveraging both knowledge triples and logic rules, they ignore the transitivity and antisymmetry of logic rules. In this paper, we propose a novel approach to learn knowledge representations with entities and ordered relations in knowledges and logic rules. The key idea is to integrate knowledge triples and logic rules, and approximately order the relation types in logic rules to utilize the transitivity and antisymmetry of logic rules. All entries of the embeddings of relation types are constrained to be non-negative. We translate the general constrained optimization problem into an unconstrained optimization problem to solve the non-negative matrix factorization. Experimental results show that our model significantly outperforms other baselines on knowledge graph completion task. It indicates that our model is capable of capturing the transitivity and antisymmetry information, which is significant when learning embeddings of knowledge graphs.

* This paper has been withdrawn by the authors due to a crucial sign error in equations
Click to Read Paper and Get Code