Online reviews have become a vital source of information in purchasing a service (product). Opinion spammers manipulate reviews, affecting the overall perception of the service. A key challenge in detecting opinion spam is obtaining ground truth. Though there exists a large set of reviews online, only a few of them have been labeled spam or non-spam. In this paper, we propose spamGAN, a generative adversarial network which relies on limited set of labeled data as well as unlabeled data for opinion spam detection. spamGAN improves the state-of-the-art GAN based techniques for text classification. Experiments on TripAdvisor dataset show that spamGAN outperforms existing spam detection techniques when limited labeled data is used. Apart from detecting spam reviews, spamGAN can also generate reviews with reasonable perplexity.

Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnerable to adversarial perturbations, which raised a serious robustness issue of deep networks. Adversarial training, typically formulated as a robust optimization problem, is an effective way of improving the robustness of deep networks. A major drawback of existing adversarial training algorithms is the computational overhead of the generation of adversarial examples, typically far greater than that of the network training. This leads to the unbearable overall computational cost of adversarial training. In this paper, we show that adversarial training can be cast as a discrete time differential game. Through analyzing the Pontryagin's Maximal Principle (PMP) of the problem, we observe that the adversary update is only coupled with the parameters of the first layer of the network. This inspires us to restrict most of the forward and back propagation within the first layer of the network during adversary updates. This effectively reduces the total number of full forward and backward propagation to only one for each group of adversary updates. Therefore, we refer to this algorithm YOPO (You Only Propagate Once). Numerical experiments demonstrate that YOPO can achieve comparable defense accuracy with approximately 1/5 ~ 1/4 GPU time of the projected gradient descent (PGD) algorithm. Our codes are available at https://https://github.com/a1600012888/YOPO-You-Only-Propagate-Once.

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this work, we propose a novel feed-forward network based on Transformer to generate mel-spectrogram in parallel for TTS. Specifically, we extract attention alignments from an encoder-decoder based teacher model for phoneme duration prediction, which is used by a length regulator to expand the source phoneme sequence to match the length of target mel-spectrogram sequence for parallel mel-spectrogram generation. Experiments on the LJSpeech dataset show that our parallel model matches autoregressive models in terms of speech quality, nearly eliminates the problem of word skipping and repeating in particularly hard cases, and can adjust voice speed smoothly. Most importantly, compared with autoregressive Transformer TTS, our model speeds up the mel-spectrogram generation by 270x and the end-to-end speech synthesis by 38x. Therefore, we call our model FastSpeech. We will release the code on Github (anonymous.url). Synthesized speech samples can be found in https://speechresearch.github.io/fastspeech/.

Recent progress in machine learning techniques have revived interest in building artificial general intelligence using these particular tools. There has been a tremendous success in applying them for narrow intellectual tasks such as pattern recognition, natural language processing and playing Go. The latter application vastly outperforms the strongest human player in recent years. However, these tasks are formalized by people in such ways that it has become "easy" for automated recipes to find better solutions than humans do. In the sense of John Searle's Chinese Room Argument, the computer playing Go does not actually understand anything from the game. Thinking like a human mind requires to go beyond the curve fitting paradigm of current systems. There is a fundamental limit to what they can achieve currently as only very specific problem formalization can increase their performances in particular tasks. In this paper, we argue than one of the most important aspects of the human mind is its capacity for logical thinking, which gives rise to many intellectual expressions that differentiate us from animal brains. We propose to model the emergence of logical thinking based on Piaget's theory of cognitive development.

Performing knowledge transfer from a large teacher network to a smaller student is a popular task in modern deep learning applications. However, due to growing dataset sizes and stricter privacy regulations, it is increasingly common not to have access to the data that was used to train the teacher. We propose a novel method which trains a student to match the predictions of its teacher without using any data or metadata. We achieve this by training an adversarial generator to search for images on which the student poorly matches the teacher, and then using them to train the student. Our resulting student closely approximates its teacher for simple datasets like SVHN, and on CIFAR10 we improve on the state-of-the-art for few-shot distillation (with 100 images per class), despite using no data. Finally, we also propose a metric to quantify the degree of belief matching between teacher and student in the vicinity of decision boundaries, and observe a significantly higher match between our zero-shot student and the teacher, than between a student distilled with real data and the teacher. Code available at: https://github.com/polo5/ZeroShotKnowledgeTransfer

Advertising and feed ranking are essential to many Internet companies such as Facebook and Sina Weibo. Among many real-world advertising and feed ranking systems, click through rate (CTR) prediction plays a central role. There are many proposed models in this field such as logistic regression, tree based models, factorization machine based models and deep learning based CTR models. However, many current works calculate the feature interactions in a simple way such as Hadamard product and inner product and they care less about the importance of features. In this paper, a new model named FiBiNET as an abbreviation for Feature Importance and Bilinear feature Interaction NETwork is proposed to dynamically learn the feature importance and fine-grained feature interactions. On the one hand, the FiBiNET can dynamically learn the importance of features via the Squeeze-Excitation network (SENET) mechanism; on the other hand, it is able to effectively learn the feature interactions via bilinear function. We conduct extensive experiments on two real-world datasets and show that our shallow model outperforms other shallow models such as factorization machine(FM) and field-aware factorization machine(FFM). In order to improve performance further, we combine a classical deep neural network(DNN) component with the shallow model to be a deep model. The deep FiBiNET consistently outperforms the other state-of-the-art deep models such as DeepFM and extreme deep factorization machine(XdeepFM).

Training large deep neural networks on massive datasets is very challenging. One promising approach to tackle this issue is through the use of large batch stochastic optimization. However, our understanding of this approach in the context of deep learning is still very limited. Furthermore, the current approaches in this direction are heavily hand-tuned. To this end, we first study a general adaptation strategy to accelerate training of deep neural networks using large minibatches. Using this strategy, we develop a new layer-wise adaptive large batch optimization technique called LAMB. We also provide a formal convergence analysis of LAMB as well as the previous published layerwise optimizer LARS, showing convergence to a stationary point in general nonconvex settings. Our empirical results demonstrate the superior performance of LAMB for BERT and ResNet-50 training. In particular, for BERT training, our optimization technique enables use of very large batches sizes of 32868; thereby, requiring just 8599 iterations to train (as opposed to 1 million iterations in the original paper). By increasing the batch size to the memory limit of a TPUv3 pod, BERT training time can be reduced from 3 days to 76 minutes. Finally, we also demonstrate that LAMB outperforms previous large-batch training algorithms for ResNet-50 on ImageNet; obtaining state-of-the-art performance in just a few minutes.

In many machine learning applications, we are faced with incomplete datasets. In the literature, missing data imputation techniques have been mostly concerned with filling missing values. However, the existence of missing values is synonymous with uncertainties not only over the distribution of missing values but also over target class assignments that require careful consideration. The objectives of this paper are twofold. First, we proposed a method for generating imputations from the conditional distribution of missing values given observed values. Second, we use the generated samples to estimate the distribution of target assignments given incomplete data. In order to generate imputations, we train a simple and effective generator network to generate imputations that a discriminator network is tasked to distinguish. Following this, a predictor network is trained using imputed samples from the generator network to capture the classification uncertainties and make predictions accordingly. The proposed method is evaluated on CIFAR-10 image dataset as well as two real-world tabular classification datasets, under various missingness rates and structures. Our experimental results show the effectiveness of the proposed method in generating imputations, as well as providing estimates for the class uncertainties in a classification task when faced with missing values.