In the past few years, neural abstractive text summarization with sequence-to-sequence (seq2seq) models have gained a lot of popularity. Many interesting techniques have been proposed to improve the seq2seq models, making them capable of handling different challenges, such as saliency, fluency and human readability, and generate high-quality summaries. Generally speaking, most of these techniques differ in one of these three categories: network structure, parameter inference, and decoding/generation. There are also other concerns, such as efficiency and parallelism for training a model. In this paper, we provide a comprehensive literature and technical survey on different seq2seq models for abstractive text summarization from viewpoint of network structures, training strategies, and summary generation algorithms. Many models were first proposed for language modeling and generation tasks, such as machine translation, and later applied to abstractive text summarization. Therefore, we also provide a brief review of these models. As part of this survey, we also develop an open source library, namely Neural Abstractive Text Summarizer (NATS) toolkit, for the abstractive text summarization. An extensive set of experiments have been conducted on the widely used CNN/Daily Mail dataset to examine the effectiveness of several different neural network components. Finally, we benchmark two models implemented in NATS on two recently released datasets, i.e., Newsroom and Bytecup.

Network representation learning in low dimensional vector space has attracted considerable attention in both academic and industrial domains. Most real-world networks are dynamic with addition/deletion of nodes and edges. The existing graph embedding methods are designed for static networks and they cannot capture evolving patterns in a large dynamic network. In this paper, we propose a dynamic embedding method, dynnode2vec, based on the well-known graph embedding method node2vec. Node2vec is a random walk based embedding method for static networks. Applying static network embedding in dynamic settings has two crucial problems: 1) Generating random walks for every time step is time consuming 2) Embedding vector spaces in each timestamp are different. In order to tackle these challenges, dynnode2vec uses evolving random walks and initializes the current graph embedding with previous embedding vectors. We demonstrate the advantages of the proposed dynamic network embedding by conducting empirical evaluations on several large dynamic network datasets.

Dimensionality reduction (DR) methods have attracted extensive attention to provide discriminative information and reduce the computational burden of the hyperspectral image (HSI) classification. However, the DR methods face many challenges due to limited training samples with high dimensional spectra. To address this issue, a graph-based spatial and spectral regularized local scaling cut (SSRLSC) for DR of HSI data is proposed. The underlying idea of the proposed method is to utilize the information from both the spectral and spatial domains to achieve better classification accuracy than its spectral domain counterpart. In SSRLSC, a guided filter is initially used to smoothen and homogenize the pixels of the HSI data in order to preserve the pixel consistency. This is followed by generation of between-class and within-class dissimilarity matrices in both spectral and spatial domains by regularized local scaling cut (RLSC) and neighboring pixel local scaling cut (NPLSC) respectively. Finally, we obtain the projection matrix by optimizing the updated spatial-spectral between-class and total-class dissimilarity. The effectiveness of the proposed DR algorithm is illustrated with two popular real-world HSI datasets.

In contrast to traditional server-side training whereuser data is aggregated on centralized servers for training, FL instead trains models on end user devices while aggregating only ephemeral parameter updates on a centralized server.This is particularly advantageous for environments whereprivacy is paramount. The Google Keyboard (Gboard) is a virtual keyboard for mobile devices with over 1 billion installs in 2018. Gboard includes both typing features like text autocorrection, nextword predictionand word completions as well as expression features like emoji, GIFs and Stickers (curated, expressive illustrations andanimations). As both a mobile application and keyboard, Gboard has unique constraints which lends itself well to both on-device inference and training. First, as a keyboard applicationwith access to much of what a user types into their mobile device, Gboard must respect the user's privacy.

Nonlinear conjugate gradient (NLCG) based optimizers have shown superior loss convergence properties compared to gradient descent based optimizers for traditional optimization problems. However, in Deep Neural Network (DNN) training, the dominant optimization algorithm of choice is still Stochastic Gradient Descent (SGD) and its variants. In this work, we propose and evaluate the stochastic preconditioned nonlinear conjugate gradient algorithm for large scale DNN training tasks. We show that a nonlinear conjugate gradient algorithm improves the convergence speed of DNN training, especially in the large mini-batch scenario, which is essential for scaling synchronous distributed DNN training to large number of workers. We show how to efficiently use second order information in the NLCG pre-conditioner for improving DNN training convergence. For the ImageNet classification task, at extremely large mini-batch sizes of greater than 65k, NLCG optimizer is able to improve top-1 accuracy by more than 10 percentage points for standard training of the Resnet-50 model for 90 epochs. For the CIFAR-100 classification task, at extremely large mini-batch sizes of greater than 16k, NLCG optimizer is able to improve top-1 accuracy by more than 15 percentage points for standard training of the Resnet-32 model for 200 epochs.

Purpose: Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting algorithms and hyper-parameter values requires advanced machine learning knowledge and many labor-intensive manual iterations. To lower the bar to machine learning, miscellaneous automatic selection methods for algorithms and/or hyper-parameter values have been proposed. Existing automatic selection methods are inefficient on large data sets. This poses a challenge for using machine learning in the clinical big data era. Methods: To address the challenge, this paper presents progressive sampling-based Bayesian optimization, an efficient and automatic selection method for both algorithms and hyper-parameter values. Results: We report an implementation of the method. We show that compared to a state of the art automatic selection method, our method can significantly reduce search time, classification error rate, and standard deviation of error rate due to randomization. Conclusions: This is major progress towards enabling fast turnaround in identifying high-quality solutions required by many machine learning-based clinical data analysis tasks.

In statistical connectomics, the quantitative study of brain networks, estimating the mean of a population of graphs based on a sample is a core problem. Often, this problem is especially difficult because the sample or cohort size is relatively small, sometimes even a single subject. While using the element-wise sample mean of the adjacency matrices is a common approach, this method does not exploit any underlying structural properties of the graphs. We propose using a low-rank method which incorporates tools for dimension selection and diagonal augmentation to smooth the estimates and improve performance over the naive methodology for small sample sizes. Theoretical results for the stochastic blockmodel show that this method offers major improvements when there are many vertices. Similarly, we demonstrate that the low-rank methods outperform the standard sample mean for a variety of independent edge distributions as well as human connectome data derived from magnetic resonance imaging, especially when sample sizes are small. Moreover, the low-rank methods yield "eigen-connectomes", which correlate with the lobe-structure of the human brain and superstructures of the mouse brain. These results indicate that low-rank methods are an important part of the tool box for researchers studying populations of graphs in general, and statistical connectomics in particular.

Despite their impressive performance on various learning tasks, neural networks have been shown to be vulnerable. An otherwise highly accurate network can be completely fooled by an artificially constructed perturbationimperceptible to human perception, known as the adversarial attack (Szegedy et al., 2013; Biggio et al., 2013). Not surprisingly, numerous algorithms in defending adversarial attacks have already been proposed in the literature which, arguably, can be interpreted as different ways in increasing the margins, i.e. the smallest distance from the sample point to the decision boundary induced by the network. Obviously, adversarial robustness is equivalent to large margins. Onetype of the algorithms is to use regularization in the learning to enforce the Lipschitz constant of the network (Cisse et al., 2017; Ross and Doshi-Velez, 2017; Hein and Andriushchenko, 2017; Tsuzuku et al., 2018), thus a small loss sample point would have a large margin since the loss cannot increase too fast. If the Lipschitz constant is regularized on data points, it is usually too local and not accurate in a neighborhood; if it is controlled globally, the constraint on the model is often too strong that it harms accuracy. So far, such methods seem not able to achieve very robust models. There are also efforts using first-order approximation to estimate and maximize input space margin (Elsayed et al., 2018; Sokolic et al., 2017; Matyasko and Chau, 2017). Similarly tolocal Lipschitz regularization, the reliance on local information might not provide accurate margin estimation and efficient maximization.

This paper proposes a method for modeling event sequences with ambiguous timestamps, a time-discounting convolution. Unlike in ordinary time series, time intervals are not constant, small time-shifts have no significant effect, and inputting timestamps or time durations into a model is not effective. The criteria that we require for the modeling are providing robustness against time-shifts or timestamps uncertainty as well as maintaining the essential capabilities of time-series models, i.e., forgetting meaningless past information and handling infinite sequences. The proposed method handles them with a convolutional mechanism across time with specific parameterizations, which efficiently represents the event dependencies in a time-shift invariant manner while discounting the effect of past events, and a dynamic pooling mechanism, which provides robustness against the uncertainty in timestamps and enhances the time-discounting capability by dynamically changing the pooling window size. In our learning algorithm, the decaying and dynamic pooling mechanisms play critical roles in handling infinite and variable length sequences. Numerical experiments on real-world event sequences with ambiguous timestamps and ordinary time series demonstrated the advantages of our method.

Label noise may handicap the generalization of classifiers, and the effective learning of the main pattern from samples with noisy labels is an important issue. Recent studies have shown that deep neural networks tend to prioritize the learning of simple patterns over the memorization of noise patterns. This suggests the need for a method to search for the best generalization that learns the main pattern until noise begins to be memorized. An intuitive idea is to use a supervised approach to find the stop timing of learning by, for example, employing a clean verification set. In practice, however, a clean verification set is sometimes difficult to obtain. To solve this problem, we propose an unsupervised method called limited gradient descent to estimate the best stop timing. We modified the labels of a few samples in a noisy dataset to be almost false labels, creating a reverse pattern. By monitoring the learning progresses of the noisy samples and the reverse samples, we could determine the stop timing of learning. In this paper, we also provide some sufficient conditions on learning with noisy labels. Experimental results on CIFAR-10 demonstrate that our approach has a similar generalization performance to supervised methods. For uncomplicated datasets, such as MNIST, we add a relabeling strategy to further improve generalization and achieve state-of-the-art performance.