A recent line of research on deep learning focuses on the extremely over-parameterized setting, and shows that when the network width is larger than a high degree polynomial of the training sample size $n$ and the inverse of the target accuracy $\epsilon^{-1}$, deep neural networks learned by (stochastic) gradient descent enjoy nice optimization and generalization guarantees. Very recently, it is shown that under certain margin assumption on the training data, a polylogarithmic width condition suffices for two-layer ReLU networks to converge and generalize (Ji and Telgarsky, 2019). However, how much over-parameterization is sufficient to guarantee optimization and generalization for deep neural networks still remains an open question. In this work, we establish sharp optimization and generalization guarantees for deep ReLU networks. Under various assumptions made in previous work, our optimization and generalization guarantees hold with network width polylogarithmic in $n$ and $\epsilon^{-1}$. Our results push the study of over-parameterized deep neural networks towards more practical settings.

As neural networks revolutionize many applications, significant privacy concerns emerge. Owners of private data wish to use remote neural network services while ensuring their data cannot be interpreted by others. Service providers wish to keep their model private to safeguard its intellectual property. Such privacy conflicts may slow down the adoption of neural networks in sensitive domains such as healthcare. Privacy issues have been addressed in the cryptography community in the context of secure computation. However, secure computation protocols have known performance issues. E.g., runtime of secure inference in deep neural networks is three orders of magnitude longer comparing to non-secure inference. Therefore, much research efforts address the optimization of cryptographic protocols for secure inference. We take a complementary approach, and provide design principles for optimizing the crypto-oriented neural network architectures to reduce the runtime of secure inference. The principles are evaluated on three state-of-the-art architectures: SqueezeNet, ShuffleNetV2, and MobileNetV2. Our novel method significantly improves the efficiency of secure inference on common evaluation metrics.

One of the best ways for developers to test and improve their skills in a fun and challenging way are programming challenges, offered by a plethora of websites. For the inexperienced ones, some of the problems might appear too challenging, requiring some suggestions to implement a solution. On the other hand, tagging problems can be a tedious task for problem creators. In this paper, we focus on automating the task of tagging a programming challenge description using machine and deep learning methods. We observe that the deep learning methods implemented outperform well-known IR approaches such as tf-idf, thus providing a starting point for further research on the task.

Predicting the patient's clinical outcome from the historical electronic medical records (EMR) is a fundamental research problem in medical informatics. Most deep learning-based solutions for EMR analysis concentrate on learning the clinical visit embedding and exploring the relations between visits. Although those works have shown superior performances in healthcare prediction, they fail to explore the personal characteristics during the clinical visits thoroughly. Moreover, existing works usually assume that the more recent record weights more in the prediction, but this assumption is not suitable for all conditions. In this paper, we propose ConCare to handle the irregular EMR data and extract feature interrelationship to perform individualized healthcare prediction. Our solution can embed the feature sequences separately by modeling the time-aware distribution. ConCare further improves the multi-head self-attention via the cross-head decorrelation, so that the inter-dependencies among dynamic features and static baseline information can be effectively captured to form the personal health context. Experimental results on two real-world EMR datasets demonstrate the effectiveness of ConCare. The medical findings extracted by ConCare are also empirically confirmed by human experts and medical literature.

Deep learning-based health status representation learning and clinical prediction have raised much research interest in recent years. Existing models have shown superior performance, but there are still several major issues that have not been fully taken into consideration. First, the historical variation pattern of the biomarker in diverse time scales plays a vital role in indicating the health status, but it has not been explicitly extracted by existing works. Second, key factors that strongly indicate the health risk are different among patients. It is still challenging to adaptively make use of the features for patients in diverse conditions. Third, using prediction models as the black box will limit the reliability in clinical practice. However, none of the existing works can provide satisfying interpretability and meanwhile achieve high prediction performance. In this work, we develop a general health status representation learning model, named AdaCare. It can capture the long and short-term variations of biomarkers as clinical features to depict the health status in multiple time scales. It also models the correlation between clinical features to enhance the ones which strongly indicate the health status and thus can maintain a state-of-the-art performance in terms of prediction accuracy while providing qualitative interpretability. We conduct a health risk prediction experiment on two real-world datasets. Experiment results indicate that AdaCare outperforms state-of-the-art approaches and provides effective interpretability, which is verifiable by clinical experts.

Traffic forecasting is of great importance to transportation management and public safety, and very challenging due to the complicated spatial - temporal dependency and essential uncertainty brought about by the road network and traffic conditions. Latest studies ma inly focus on modeling the spatial dependency by utilizing graph convolutional networks (GCNs) throughout a fixed weighted graph. However, edges, i.e., the correlations between pair - wise nodes, are much more complicated and interact with each other. In thi s paper, we propose the M ulti - R ange A ttentive B icomponent GCN (MRA - BGCN), a novel deep learning model for traffic forecasting. We first build the node - wise graph according to the road network distance and the edge - wise graph according to various edge inter action patterns . Then, we implement the interactions of both nodes and edges using bicom-ponent graph convolution. T he multi - range attention mechanism is introduced to aggregate information in different neighbor hood range s and automatically learn the import ance of different ranges. Extensive experiments on two real - world road network traffic datasets, METR - LA and PEMS - BAY, show that our MRA - BGCN achieves the state - of - the - art results.

Variational Autoencoders (VAEs) are powerful in data representation inference, but it cannot learn relations between features with its vanilla form and common variations. The ability to capture relations within data can provide the much needed inductive bias necessary for building more robust Machine Learning algorithms with more interpretable results. In this paper, inspired by recent advances in relational learning using Graph Neural Networks, we propose the \textbf{S}elf-\textbf{A}ttention \textbf{G}raph \textbf{V}ariational \textbf{A}uto\textbf{E}ncoder (SAG-VAE) network which can simultaneously learn feature relations and data representations in an end-to-end manner. SAG-VAE is trained by jointly inferring the posterior distribution of two types of latent variables, which denote the data representation and a shared graph structure, respectively. Furthermore, we introduce a novel self-attention graph network that improves the generative capabilities of SAG-VAE by parameterizing the generative distribution allowing SAG-VAE to generate new data via graph convolution, while still trainable via backpropagation. A learnable relational graph representation enhances SAG-VAE's robustness to perturbation and noise, while also providing deeper intuition into model performance. Experiments based on graphs show that SAG-VAE is capable of approximately retrieving edges and links between nodes based entirely on feature observations. Finally, results on image data illustrate that SAG-VAE is fairly robust against perturbations in image reconstruction and sampling.

A remarkable recent discovery in machine learning has been that deep neural networks can achieve impressive performance (in terms of both lower training error and higher generalization capacity) in the regime where they are massively over-parameterized. Consequently, over the last several months, the community has devoted growing interest in analyzing optimization and generalization properties of over-parameterized networks, and several breakthrough works have led to important theoretical progress. However, the majority of existing work only applies to supervised learning scenarios and hence are limited to settings such as classification and regression. In contrast, the role of over-parameterization in the unsupervised setting has gained far less attention. In this paper, we study the gradient dynamics of two-layer over-parameterized autoencoders with ReLU activation. We make very few assumptions about the given training dataset (other than mild non-degeneracy conditions). Starting from a randomly initialized autoencoder network, we rigorously prove the linear convergence of gradient descent in two learning regimes, namely: (i) the weakly-trained regime where only the encoder is trained, and (ii) the jointly-trained regime where both the encoder and the decoder are trained. Our results indicate the considerable benefits of joint training over weak training for finding global optima, achieving a dramatic decrease in the required level of over-parameterization. We also analyze the case of weight-tied autoencoders (which is a commonly used architectural choice in practical settings) and prove that in the over-parameterized setting, training such networks from randomly initialized points leads to certain unexpected degeneracies.

Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defend against adversarial examples, a plausible idea is to obfuscate the network's gradient with respect to the input image. This general idea has inspired a long line of defense methods. Yet, almost all of them have proven vulnerable. We revisit this seemingly flawed idea from a radically different perspective. We embrace the omnipresence of adversarial examples and the numerical procedure of crafting them, and turn this harmful attacking process into a useful defense mechanism. Our defense method is conceptually simple: before feeding an input image for classification, transform it by finding an adversarial example on a pre-trained external model. We evaluate our method against a wide range of possible attacks. On both CIFAR-10 and Tiny ImageNet datasets, our method is significantly more robust than state-of-the-art methods. Particularly, in comparison to adversarial training, our method offers lower training cost as well as stronger robustness.

Although deep neural networks are highly effective, their high computational and memory costs severely challenge their applications on portable devices. As a consequence, low-bit quantization, which converts a full-precision neural network into a low-bitwidth integer version, has been an active and promising research topic. Existing methods formulate the low-bit quantization of networks as an approximation or optimization problem. Approximation-based methods confront the gradient mismatch problem, while optimization-based methods are only suitable for quantizing weights and could introduce high computational cost in the training stage. In this paper, we propose a novel perspective of interpreting and implementing neural network quantization by formulating low-bit quantization as a differentiable non-linear function (termed quantization function). The proposed quantization function can be learned in a lossless and end-to-end manner and works for any weights and activations of neural networks in a simple and uniform way. Extensive experiments on image classification and object detection tasks show that our quantization networks outperform the state-of-the-art methods. We believe that the proposed method will shed new insights on the interpretation of neural network quantization. Our code is available at https://github.com/aliyun/alibabacloud-quantization-networks.