Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box models, (b) lack of robustness to noise in labeling, (c) lack of transparency. In response, we propose a transparent batch active sampling framework by estimating the error decay curves of multiple feature-defined subsets of the data. Experiments on four named entity recognition (NER) tasks demonstrate that the proposed methods significantly outperform diversification-based methods for black-box NER taggers and can make the sampling process more robust to labeling noise when combined with uncertainty-based methods. Furthermore, the analysis of experimental results sheds light on the weaknesses of different active sampling strategies, and when traditional uncertainty-based or diversification-based methods can be expected to work well.

A new algorithm is developed to tackle the issue of sampling non-Gaussian model parameter posterior probability distributions that arise from solutions to Bayesian inverse problems. The algorithm aims to mitigate some of the hurdles faced by traditional Markov Chain Monte Carlo (MCMC) samplers, through constructing proposal probability densities that are both, easy to sample and that provide a better approximation to the target density than a simple Gaussian proposal distribution would. To achieve that, a Gaussian proposal distribution is augmented with a Gaussian Process (GP) surface that helps capture non-linearities in the log-likelihood function. In order to train the GP surface, an iterative approach is adopted for the optimal selection of points in parameter space. Optimality is sought by maximizing the information gain of the GP surface using a minimum number of forward model simulation runs. The accuracy of the GP-augmented surface approximation is assessed in two ways. The first consists of comparing predictions obtained from the approximate surface with those obtained through running the actual simulation model at hold-out points in parameter space. The second consists of a measure based on the relative variance of sample weights obtained from sampling the approximate posterior probability distribution of the model parameters. The efficacy of this new algorithm is tested on inferring reaction rate parameters in a 3-node and 6-node network toy problems, which imitate idealized reaction networks in combustion applications.

We propose to address multi-label learning by jointly estimating the distribution of positive and negative instances for all labels. By a shared mapping function, each label's positive and negative instances are mapped into a new space forming a mixture distribution of two components (positive and negative). Due to the dependency among labels, positive instances are mapped close if they share common labels, while positive and negative embeddings of the same label are pushed away. The distribution is learned in the new space, and thus well presents both the distance between instances in their original feature space and their common membership w.r.t. different categories. By measuring the density function values, new instances mapped to the new space can easily identify their membership to possible multiple categories. We use neural networks for learning the mapping function and use the expectations of the positive and negative embedding as prototypes of the positive and negative components for each label, respectively. Therefore, we name our proposed method PNML (prototypical networks for multi-label learning). Extensive experiments verify that PNML significantly outperforms the state-of-the-arts.

--In various web applications like targeted advertising and recommender systems, the available categorical features (e.g., product type) are often of great importance but sparse. As a widely adopted solution, models based on Factorization Machines (FMs) are capable of modelling high-order interactions among features for effective sparse predictive analytics. As the volume of web-scale data grows exponentially over time, sparse predictive analytics inevitably involves dynamic and sequential features. However, existing FMbased models assume no temporal orders in the data, and are unable to capture the sequential dependencies or patterns within the dynamic features, impeding the performance and adaptivity of these methods. Hence, in this paper, we propose a novel Sequence-A ware Factorization Machine (SeqFM) for temporal predictive analytics, which models feature interactions by fully investigating the effect of sequential dependencies. As static features (e.g., user gender) and dynamic features (e.g., user interacted items) express different semantics, we innovatively devise a multi-view self-attention scheme that separately models the effect of static features, dynamic features and the mutual interactions between static and dynamic features in three different views. In SeqFM, we further map the learned representations of feature interactions to the desired output with a shared residual network. T o showcase the versatility and generalizability of SeqFM, we test SeqFM in three popular application scenarios for FMbased models, namely ranking, classification and regression tasks. Extensive experimental results on six large-scale datasets demonstrate the superior effectiveness and efficiency of SeqFM. As an important supervised learning scheme, predictive analytics play a pivotal role in various applications, ranging from recommender systems [1], [2] to financial analysis [3] and online advertising [4], [5]. In practice, the goal of predictive analytics is to learn a mapping function from the observed variables (i.e., features) to the desired output. When dealing with categorical features in predictive analytics, a common approach is to convert such features into one-hot encodings [6]-[8] so that standard regressors like logistic regression [9] and support vector machines [10] can be directly applied. Due to the large number of possible category variables, the converted one-hot features are usually of high dimensionality but sparse [11], and simply using raw features rarely provides optimal results. The interactions among multiple raw features are usually termed as cross features [7] (a.k.a.

In this article I will show you how to create your own stock prediction Python program using a machine learning algorithm called Support Vector Regression (SVR). The program will read in Facebook (FB) stock data and make a prediction of the open price based on the day. A Support Vector Regression (SVR) is a type of Support Vector Machine,and is a type of supervised learning algorithm that analyzes data for regression analysis. In 1996, this version of SVM for regression was proposed by Christopher J. C. Burges, Vladimir N. Vapnik, Harris Drucker, Alexander J. Smola and Linda Kaufman. The model produced by SVR depends only on a subset of the training data, because the cost function for building the model ignores any training data close to the model prediction.

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a low-dimensional embedding using a pretrained model, and then performs efficient search within the embedding space to attack an unknown target network. The method produces adversarial perturbations with high level semantic patterns that are easily transferable. We show that this approach can greatly improve the query efficiency of black-box adversarial attack across different target network architectures. We evaluate our approach on MNIST, ImageNet and Google Cloud Vision API, resulting in a significant reduction on the number of queries. We also attack adversarially defended networks on CIFAR10 and ImageNet, where our method not only reduces the number of queries, but also improves the attack success rate.

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction by~\citet{fredrikson2014privacy}, such attacks have raised serious concerns given that training data usually contain privacy sensitive information. Thus far, successful model-inversion attacks have only been demonstrated on simple models, such as linear regression and logistic regression. Previous attempts to invert neural networks, even the ones with simple architectures, have failed to produce convincing results. Here we present a novel attack method, termed the \emph{generative model-inversion attack}, which can invert deep neural networks with high success rates. Rather than reconstructing private training data from scratch, we leverage partial public information, which can be very generic, to learn a distributional prior via generative adversarial networks (GANs) and use it to guide the inversion process. Moreover, we theoretically prove that a model's predictive power and its vulnerability to inversion attacks are indeed two sides of the same coin---highly predictive models are able to establish a strong correlation between features and labels, which coincides exactly with what an adversary exploits to mount the attacks. Our extensive experiments demonstrate that the proposed attack improves identification accuracy over the existing work by about $75\%$ for reconstructing face images from a state-of-the-art face recognition classifier. We also show that differential privacy, in its canonical form, is of little avail to defend against our attacks.

Knowledge graph (KG) embedding is a fundamental problem in mining relational patterns. It aims to encode the entities and relations in KG into low dimensional vector space that can be used for subsequent algorithms. Lots of KG embedding models have been proposed to learn the interactions between entities and relations, which contain meaningful semantic information. However, structural information, which encodes local topology among entities, is also important to KG. In this work, we propose S2E to distill structural information and combine it with semantic information for different KGs as a neural architecture search (NAS) problem. First, we analyze the difficulty of using a unified model to solve the distillation problem. Based on it, we define the path distiller to recurrently combine structural and semantic information along relational paths, which are sampled to preserve both local topologies and semantics. Then, inspired by the recent success of NAS, we design a recurrent network-based search space for specific KG tasks and propose a natural gradient (NG) based search algorithm to update architectures. Experimental results demonstrate that the searched models by our proposed S2E outperform human-designed ones, and the NG based search algorithm is efficient compared with other NAS methods. Besides, our work is the first NAS method for RNN that can search architectures with better performance than human-designed models.

This paper focuses on valuating training data for supervised learning tasks and studies the Shapley value, a data value notion originated in cooperative game theory. The Shapley value defines a unique value distribution scheme that satisfies a set of appealing properties desired by a data value notion. However, the Shapley value requires exponential complexity to calculate exactly. Existing approximation algorithms, although achieving great improvement over the exact algorithm, relies on retraining models for multiple times, thus remaining limited when applied to larger-scale learning tasks and real-world datasets. In this work, we develop a simple and efficient heuristic for data valuation based on the Shapley value with complexity independent with the model size. The key idea is to approximate the model via a $K$-nearest neighbor ($K$NN) classifier, which has a locality structure that can lead to efficient Shapley value calculation. We evaluate the utility of the values produced by the $K$NN proxies in various settings, including label noise correction, watermark detection, data summarization, active data acquisition, and domain adaption. Extensive experiments demonstrate that our algorithm achieves at least comparable utility to the values produced by existing algorithms while significant efficiency improvement. Moreover, we theoretically analyze the Shapley value and justify its advantage over the leave-one-out error as a data value measure.

Graph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linkage patterns across graphs in various applications. As real-world graphs are often incomplete and noisy, treating them as ground-truth information, which is a common practice in most GCNs, unavoidably leads to sub-optimal solutions. Existing efforts for addressing this problem either involve an over-parameterized model which is difficult to scale, or simply re-weight observed edges without dealing with the missing-edge issue. This paper proposes a novel framework called Graph-Revised Convolutional Network (GRCN), which avoids both extremes. Specifically, a GCN-based graph revision module is introduced for predicting missing edges and revising edge weights w.r.t. downstream tasks via joint optimization. A theoretical analysis reveals the connection between GRCN and previous work on multigraph belief propagation. Experiments on six benchmark datasets show that GRCN consistently outperforms strong baseline methods by a large margin, especially when the original graphs are severely incomplete or the labeled instances for model training are highly sparse.