Teaching is critical to human society: it is with teaching that prospective students are educated and human civilization can be inherited and advanced. A good teacher not only provides his/her students with qualified teaching materials (e.g., textbooks), but also sets up appropriate learning objectives (e.g., course projects and exams) considering different situations of a student. When it comes to artificial intelligence, treating machine learning models as students, the loss functions that are optimized act as perfect counterparts of the learning objective set by the teacher. In this work, we explore the possibility of imitating human teaching behaviors by dynamically and automatically outputting appropriate loss functions to train machine learning models. Different from typical learning settings in which the loss function of a machine learning model is predefined and fixed, in our framework, the loss function of a machine learning model (we call it student) is defined by another machine learning model (we call it teacher). The ultimate goal of teacher model is cultivating the student to have better performance measured on development dataset. Towards that end, similar to human teaching, the teacher, a parametric model, dynamically outputs different loss functions that will be used and optimized by its student model at different training stages. We develop an efficient learning method for the teacher model that makes gradient based optimization possible, exempt of the ineffective solutions such as policy optimization. We name our method as "learning to teach with dynamic loss functions" (L2T-DLF for short). Extensive experiments on real world tasks including image classification and neural machine translation demonstrate that our method significantly improves the quality of various student models.

Recommender systems recommend items more accurately by analyzing users' potential interest on different brands' items. In conjunction with users' rating similarity, the presence of users' implicit feedbacks like clicking items, viewing items specifications, watching videos etc. have been proved to be helpful for learning users' embedding, that helps better rating prediction of users. Most existing recommender systems focus on modeling of ratings and implicit feedbacks ignoring users' explicit feedbacks. Explicit feedbacks can be used to validate the reliability of the particular users and can be used to learn about the users' characteristic. Users' characteristic mean what type of reviewers they are. In this paper, we explore three different models for recommendation with more accuracy focusing on users' explicit feedbacks and implicit feedbacks. First one is RHC-PMF that predicts users' rating more accurately based on user's three explicit feedbacks (rating, helpfulness score and centrality) and second one is RV-PMF, where user's implicit feedback (view relationship) is considered. Last one is RHCV-PMF, where both type of feedbacks are considered. In this model users' explicit feedbacks' similarity indicate the similarity of their reliability and characteristic and implicit feedback's similarity indicates their preference similarity. Extensive experiments on real world dataset, i.e. Amazon.com online review dataset shows that our models perform better compare to base-line models in term of users' rating prediction. RHCV-PMF model also performs better rating prediction compare to baseline models for cold start users and cold start items.

An audiovisual speaker conversion method is presented for simultaneously transforming the facial expressions and voice of a source speaker into those of a target speaker. Transforming the facial and acoustic features together makes it possible for the converted voice and facial expressions to be highly correlated and for the generated target speaker to appear and sound natural. It uses three neural networks: a conversion network that fuses and transforms the facial and acoustic features, a waveform generation network that produces the waveform from both the converted facial and acoustic features, and an image reconstruction network that outputs an RGB facial image also based on both the converted features. The results of experiments using an emotional audiovisual database showed that the proposed method achieved significantly higher naturalness compared with one that separately transformed acoustic and facial features.

Class imbalance is a pervasive issue among classification models including deep learning, whose capacity to extract task-specific features is affected in imbalanced settings. However, the challenges of handling imbalance among a large number of classes, commonly addressed by deep learning, have not received a significant amount of attention in previous studies. In this paper, we propose an extension of the deep over-sampling framework, to exploit automatically-generated abstract-labels, i.e., a type of side-information used in weak-label learning, to enhance deep representation learning against class imbalance. We attempt to exploit the labels to guide the deep representation of instances towards different subspaces, to induce a soft-separation of inherent subtasks of the classification problem. Our empirical study shows that the proposed framework achieves a substantial improvement on image classification benchmarks with imbalanced among large and small numbers of classes.

Neural language models have been widely used in various NLP tasks, including machine translation, next word prediction and conversational agents. However, it is challenging to deploy these models on mobile devices due to their slow prediction speed, where the bottleneck is to compute top candidates in the softmax layer. In this paper, we introduce a novel softmax layer approximation algorithm by exploiting the clustering structure of context vectors. Our algorithm uses a light-weight screening model to predict a much smaller set of candidate words based on the given context, and then conducts an exact softmax only within that subset. Training such a procedure end-to-end is challenging as traditional clustering methods are discrete and non-differentiable, and thus unable to be used with back-propagation in the training process. Using the Gumbel softmax, we are able to train the screening model end-to-end on the training set to exploit data distribution. The algorithm achieves an order of magnitude faster inference than the original softmax layer for predicting top-$k$ words in various tasks such as beam search in machine translation or next words prediction. For example, for machine translation task on German to English dataset with around 25K vocabulary, we can achieve 20.4 times speed up with 98.9\% precision@1 and 99.3\% precision@5 with the original softmax layer prediction, while state-of-the-art ~\citep{MSRprediction} only achieves 6.7x speedup with 98.7\% precision@1 and 98.1\% precision@5 for the same task.

The world is witnessing an unprecedented growth of cyber-physical systems (CPS), which are foreseen to revolutionize our world {via} creating new services and applications in a variety of sectors such as environmental monitoring, mobile-health systems, intelligent transportation systems and so on. The {information and communication technology }(ICT) sector is experiencing a significant growth in { data} traffic, driven by the widespread usage of smartphones, tablets and video streaming, along with the significant growth of sensors deployments that are anticipated in the near future. {It} is expected to outstandingly increase the growth rate of raw sensed data. In this paper, we present the CPS taxonomy {via} providing a broad overview of data collection, storage, access, processing and analysis. Compared with other survey papers, this is the first panoramic survey on big data for CPS, where our objective is to provide a panoramic summary of different CPS aspects. Furthermore, CPS {require} cybersecurity to protect {them} against malicious attacks and unauthorized intrusion, which {become} a challenge with the enormous amount of data that is continuously being generated in the network. {Thus, we also} provide an overview of the different security solutions proposed for CPS big data storage, access and analytics. We also discuss big data meeting green challenges in the contexts of CPS.

We consider the semi-supervised clustering problem where crowdsourcing provides noisy information about the pairwise comparisons on a small subset of data, i.e., whether a sample pair is in the same cluster. We propose a new approach that includes a deep generative model (DGM) to characterize low-level features of the data, and a statistical relational model for noisy pairwise annotations on its subset. The two parts share the latent variables. To make the model automatically trade-off between its complexity and fitting data, we also develop its fully Bayesian variant. The challenge of inference is addressed by fast (natural-gradient) stochastic variational inference algorithms, where we effectively combine variational message passing for the relational part and amortized learning of the DGM under a unified framework. Empirical results on synthetic and real-world datasets show that our model outperforms previous crowdsourced clustering methods.

Abstract--Vehicle location prediction or vehicle tracking is a significant topic within connected vehicles. This task, however, is difficult if only a single modal data is available, probably causing bias and impeding the accuracy. With the development of sensor networks in connected vehicles, multimodal data are becoming accessible. Therefore, we propose a framework for vehicle tracking with multimodal data fusion. Images, being processed in the module of vehicle detection, provide direct information about the features of vehicles, whereas velocity estimation can further evaluate the possible location of the target vehicles, which reduces the number of features being compared, and decreases the time consumption and computational cost. Vehicle detection is designed with a color-faster R-CNN, which takes both the shape and color of the vehicles into consideration. Meanwhile, velocity estimation is through the Kalman filter, which is a classical method for tracking. Finally, a multimodal data fusion method is applied to integrate these outcomes so that vehicle-tracking tasks can be achieved. Experimental results suggest the efficiency of our methods, which can track vehicles using a series of surveillance cameras in urban areas. ITH technological advancements in vehicles and transportation system, motorists require comfort and intelligent driving, not only mobility. Thus, there has been a great deal of research which mainly falls into one of two directions. On one hand, researchers tend to develop more intelligent vehicles, or devices that can be attached to vehicles, bringing up several popular topics such as autonomous vehicles or driverless vehicles [1].

Abstract--Internet of vehicles is a promising area related to D2D communication and internet of things. We present a novel perspective for vehicular communications, social vehicle swarms, to study and analyze socially aware internet of vehicles with the assistance of an agent-based model intended to reveal hidden patterns behind superficial data. After discussing its components, namely its agents, environments, and rules, we introduce supportive technology and methods, deep reinforcement learning, privacy preserving data mining and sub-cloud computing, in order to detect the most significant and interesting information for each individual effectively, which is the key desire. Finally, several relevant research topics and challenges are discussed. NETNET of vehicles (IoV) is a particular case, with vehicles being basic units, of internet of things (IoT) [1], which allows objects or devices to interact and communicate, indicating that an intrinsic component of IoT or IoV is device-to-device (D2D) communication [2]. IoV aims to build an intelligent system to improve the quality of driving or living; formally, to increase the quality of experience (QoE) or quality of service (QoS) [3]. Further study of IoV could lead to integration with smart cities, where each building, house, or even each individual device is capable of communication via wired or wireless access. On the other hand, online social networks (OSNs) have gained a growing amount of attention during recent years, and their use has almost become a daily necessity. This work has been supported by the National Natural Science Foundation of China (Nos.61271173 and 61372068), the Research Fund for the Doctoral Program of Higher Education of China (No.20130203110005), the Fundamental Research Funds for the Central Universities (No.K5051301033), the 111 Project(No. B08038), and also supported by the ISN State Key Laboratory. Y. Zhang, F. Tian and B. Song are with the State Key Laboratory of Integrated Services Networks, Xidian University, 710071, China (email: y.zhang@stu.xidian.edu.cn,

It's the stuff of horror films: an intruder in your house, impossible to find but undeniably somewhere, watching you at your most private moments. Or perhaps it's the plot of a thriller, where you are recruited into international crime without even knowing it, at the behest of smart criminals. If the worst fears about the prevalence of weakly secured smart home gadgets materialise, those terrifying situations could become all too real. As we fill our homes with internet-enabled and smart devices, we are opening ourselves up to attacks that exploit houses themselves – and we might not even realise they are happening. Everything from washing machines to baby monitors is being hooked up to the internet by companies convinced that features such as remote control and artificial intelligence will make our lives easier and safer.