July 27, 2019

3101 words 15 mins read

Paper Group ANR 541

PixelNN: Example-based Image Synthesis. Efficient Online Linear Optimization with Approximation Algorithms. Cooperative Hierarchical Dirichlet Processes: Superposition vs. Maximization. Modeling Events as Machines. Identifying Consistent Statements about Numerical Data with Dispersion-Corrected Subgroup Discovery. DeepAPT: Nation-State APT Attribut …

PixelNN: Example-based Image Synthesis


Title	PixelNN: Example-based Image Synthesis
Authors	Aayush Bansal, Yaser Sheikh, Deva Ramanan
Abstract	We present a simple nearest-neighbor (NN) approach that synthesizes high-frequency photorealistic images from an “incomplete” signal such as a low-resolution image, a surface normal map, or edges. Current state-of-the-art deep generative models designed for such conditional image synthesis lack two important things: (1) they are unable to generate a large set of diverse outputs, due to the mode collapse problem. (2) they are not interpretable, making it difficult to control the synthesized output. We demonstrate that NN approaches potentially address such limitations, but suffer in accuracy on small datasets. We design a simple pipeline that combines the best of both worlds: the first stage uses a convolutional neural network (CNN) to maps the input to a (overly-smoothed) image, and the second stage uses a pixel-wise nearest neighbor method to map the smoothed output to multiple high-quality, high-frequency outputs in a controllable manner. We demonstrate our approach for various input modalities, and for various domains ranging from human faces to cats-and-dogs to shoes and handbags.
Tasks	Image Generation
Published	2017-08-17
URL	http://arxiv.org/abs/1708.05349v1
PDF	http://arxiv.org/pdf/1708.05349v1.pdf
PWC	https://paperswithcode.com/paper/pixelnn-example-based-image-synthesis
Repo
Framework

Efficient Online Linear Optimization with Approximation Algorithms


Title	Efficient Online Linear Optimization with Approximation Algorithms
Authors	Dan Garber
Abstract	We revisit the problem of \textit{online linear optimization} in case the set of feasible actions is accessible through an approximated linear optimization oracle with a factor $\alpha$ multiplicative approximation guarantee. This setting is in particular interesting since it captures natural online extensions of well-studied \textit{offline} linear optimization problems which are NP-hard, yet admit efficient approximation algorithms. The goal here is to minimize the $\alpha$\textit{-regret} which is the natural extension of the standard \textit{regret} in \textit{online learning} to this setting. We present new algorithms with significantly improved oracle complexity for both the full information and bandit variants of the problem. Mainly, for both variants, we present $\alpha$-regret bounds of $O(T^{-1/3})$, were $T$ is the number of prediction rounds, using only $O(\log{T})$ calls to the approximation oracle per iteration, on average. These are the first results to obtain both average oracle complexity of $O(\log{T})$ (or even poly-logarithmic in $T$) and $\alpha$-regret bound $O(T^{-c})$ for a constant $c>0$, for both variants.
Tasks
Published	2017-09-10
URL	http://arxiv.org/abs/1709.03093v1
PDF	http://arxiv.org/pdf/1709.03093v1.pdf
PWC	https://paperswithcode.com/paper/efficient-online-linear-optimization-with
Repo
Framework

Cooperative Hierarchical Dirichlet Processes: Superposition vs. Maximization


Title	Cooperative Hierarchical Dirichlet Processes: Superposition vs. Maximization
Authors	Junyu Xuan, Jie Lu, Guangquan Zhang, Richard Yi Da Xu
Abstract	The cooperative hierarchical structure is a common and significant data structure observed in, or adopted by, many research areas, such as: text mining (author-paper-word) and multi-label classification (label-instance-feature). Renowned Bayesian approaches for cooperative hierarchical structure modeling are mostly based on topic models. However, these approaches suffer from a serious issue in that the number of hidden topics/factors needs to be fixed in advance and an inappropriate number may lead to overfitting or underfitting. One elegant way to resolve this issue is Bayesian nonparametric learning, but existing work in this area still cannot be applied to cooperative hierarchical structure modeling. In this paper, we propose a cooperative hierarchical Dirichlet process (CHDP) to fill this gap. Each node in a cooperative hierarchical structure is assigned a Dirichlet process to model its weights on the infinite hidden factors/topics. Together with measure inheritance from hierarchical Dirichlet process, two kinds of measure cooperation, i.e., superposition and maximization, are defined to capture the many-to-many relationships in the cooperative hierarchical structure. Furthermore, two constructive representations for CHDP, i.e., stick-breaking and international restaurant process, are designed to facilitate the model inference. Experiments on synthetic and real-world data with cooperative hierarchical structures demonstrate the properties and the ability of CHDP for cooperative hierarchical structure modeling and its potential for practical application scenarios.
Tasks	Multi-Label Classification, Topic Models
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05420v1
PDF	http://arxiv.org/pdf/1707.05420v1.pdf
PWC	https://paperswithcode.com/paper/cooperative-hierarchical-dirichlet-processes
Repo
Framework

Modeling Events as Machines


Title	Modeling Events as Machines
Authors	Sabah Al-Fedaghi
Abstract	The notion of events has occupied a central role in modeling and has an influence in computer science and philosophy. Recent developments in diagrammatic modeling have made it possible to examine conceptual representation of events. This paper explores some aspects of the notion of events that are produced by applying a new diagrammatic methodology with a focus on the interaction of events with such concepts as time and space, objects. The proposed description applies to abstract machines where events form the dynamic phases of a system. The results of this nontechnical research can be utilized in many fields where the notion of an event is typically used in interdisciplinary application.
Tasks
Published	2017-04-26
URL	http://arxiv.org/abs/1704.08588v1
PDF	http://arxiv.org/pdf/1704.08588v1.pdf
PWC	https://paperswithcode.com/paper/modeling-events-as-machines
Repo
Framework

Identifying Consistent Statements about Numerical Data with Dispersion-Corrected Subgroup Discovery


Title	Identifying Consistent Statements about Numerical Data with Dispersion-Corrected Subgroup Discovery
Authors	Mario Boley, Bryan R. Goldsmith, Luca M. Ghiringhelli, Jilles Vreeken
Abstract	Existing algorithms for subgroup discovery with numerical targets do not optimize the error or target variable dispersion of the groups they find. This often leads to unreliable or inconsistent statements about the data, rendering practical applications, especially in scientific domains, futile. Therefore, we here extend the optimistic estimator framework for optimal subgroup discovery to a new class of objective functions: we show how tight estimators can be computed efficiently for all functions that are determined by subgroup size (non-decreasing dependence), the subgroup median value, and a dispersion measure around the median (non-increasing dependence). In the important special case when dispersion is measured using the average absolute deviation from the median, this novel approach yields a linear time algorithm. Empirical evaluation on a wide range of datasets shows that, when used within branch-and-bound search, this approach is highly efficient and indeed discovers subgroups with much smaller errors.
Tasks
Published	2017-01-26
URL	http://arxiv.org/abs/1701.07696v2
PDF	http://arxiv.org/pdf/1701.07696v2.pdf
PWC	https://paperswithcode.com/paper/identifying-consistent-statements-about
Repo
Framework

DeepAPT: Nation-State APT Attribution Using End-to-End Deep Neural Networks


Title	DeepAPT: Nation-State APT Attribution Using End-to-End Deep Neural Networks
Authors	Ishai Rosenberg, Guillaume Sicard, Eli David
Abstract	In recent years numerous advanced malware, aka advanced persistent threats (APT) are allegedly developed by nation-states. The task of attributing an APT to a specific nation-state is extremely challenging for several reasons. Each nation-state has usually more than a single cyber unit that develops such advanced malware, rendering traditional authorship attribution algorithms useless. Furthermore, those APTs use state-of-the-art evasion techniques, making feature extraction challenging. Finally, the dataset of such available APTs is extremely small. In this paper we describe how deep neural networks (DNN) could be successfully employed for nation-state APT attribution. We use sandbox reports (recording the behavior of the APT when run dynamically) as raw input for the neural network, allowing the DNN to learn high level feature abstractions of the APTs itself. Using a test set of 1,000 Chinese and Russian developed APTs, we achieved an accuracy rate of 94.6%.
Tasks
Published	2017-11-27
URL	http://arxiv.org/abs/1711.09666v1
PDF	http://arxiv.org/pdf/1711.09666v1.pdf
PWC	https://paperswithcode.com/paper/deepapt-nation-state-apt-attribution-using
Repo
Framework

A Simple Approach to Learn Polysemous Word Embeddings


Title	A Simple Approach to Learn Polysemous Word Embeddings
Authors	Yifan Sun, Nikhil Rao, Weicong Ding
Abstract	Many NLP applications require disambiguating polysemous words. Existing methods that learn polysemous word vector representations involve first detecting various senses and optimizing the sense-specific embeddings separately, which are invariably more involved than single sense learning methods such as word2vec. Evaluating these methods is also problematic, as rigorous quantitative evaluations in this space is limited, especially when compared with single-sense embeddings. In this paper, we propose a simple method to learn a word representation, given any context. Our method only requires learning the usual single sense representation, and coefficients that can be learnt via a single pass over the data. We propose several new test sets for evaluating word sense induction, relevance detection, and contextual word similarity, significantly supplementing the currently available tests. Results on these and other tests show that while our method is embarrassingly simple, it achieves excellent results when compared to the state of the art models for unsupervised polysemous word representation learning.
Tasks	Representation Learning, Word Embeddings, Word Sense Induction
Published	2017-07-06
URL	http://arxiv.org/abs/1707.01793v2
PDF	http://arxiv.org/pdf/1707.01793v2.pdf
PWC	https://paperswithcode.com/paper/a-simple-approach-to-learn-polysemous-word
Repo
Framework

Neural Question Answering at BioASQ 5B


Title	Neural Question Answering at BioASQ 5B
Authors	Georg Wiese, Dirk Weissenborn, Mariana Neves
Abstract	This paper describes our submission to the 2017 BioASQ challenge. We participated in Task B, Phase B which is concerned with biomedical question answering (QA). We focus on factoid and list question, using an extractive QA model, that is, we restrict our system to output substrings of the provided text snippets. At the core of our system, we use FastQA, a state-of-the-art neural QA system. We extended it with biomedical word embeddings and changed its answer layer to be able to answer list questions in addition to factoid questions. We pre-trained the model on a large-scale open-domain QA dataset, SQuAD, and then fine-tuned the parameters on the BioASQ training set. With our approach, we achieve state-of-the-art results on factoid questions and competitive results on list questions.
Tasks	Question Answering, Word Embeddings
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08568v1
PDF	http://arxiv.org/pdf/1706.08568v1.pdf
PWC	https://paperswithcode.com/paper/neural-question-answering-at-bioasq-5b
Repo
Framework

An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection


Title	An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection
Authors	Joseph Futoma, Sanjay Hariharan, Mark Sendak, Nathan Brajer, Meredith Clement, Armando Bedoya, Cara O’Brien, Katherine Heller
Abstract	Sepsis is a poorly understood and potentially life-threatening complication that can occur as a result of infection. Early detection and treatment improves patient outcomes, and as such it poses an important challenge in medicine. In this work, we develop a flexible classifier that leverages streaming lab results, vitals, and medications to predict sepsis before it occurs. We model patient clinical time series with multi-output Gaussian processes, maintaining uncertainty about the physiological state of a patient while also imputing missing values. The mean function takes into account the effects of medications administered on the trajectories of the physiological variables. Latent function values from the Gaussian process are then fed into a deep recurrent neural network to classify patient encounters as septic or not, and the overall model is trained end-to-end using back-propagation. We train and validate our model on a large dataset of 18 months of heterogeneous inpatient stays from the Duke University Health System, and develop a new “real-time” validation scheme for simulating the performance of our model as it will actually be used. Our proposed method substantially outperforms clinical baselines, and improves on a previous related model for detecting sepsis. Our model’s predictions will be displayed in a real-time analytics dashboard to be used by a sepsis rapid response team to help detect and improve treatment of sepsis.
Tasks	Gaussian Processes, Time Series
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05894v1
PDF	http://arxiv.org/pdf/1708.05894v1.pdf
PWC	https://paperswithcode.com/paper/an-improved-multi-output-gaussian-process-rnn
Repo
Framework

Three-Dimensional Segmentation of Vesicular Networks of Fungal Hyphae in Macroscopic Microscopy Image Stacks


Title	Three-Dimensional Segmentation of Vesicular Networks of Fungal Hyphae in Macroscopic Microscopy Image Stacks
Authors	P. Saponaro, W. Treible, A. Kolagunda, S. Rhein, J. Caplan, C. Kambhamettu, R. Wisser
Abstract	Automating the extraction and quantification of features from three-dimensional (3-D) image stacks is a critical task for advancing computer vision research. The union of 3-D image acquisition and analysis enables the quantification of biological resistance of a plant tissue to fungal infection through the analysis of attributes such as fungal penetration depth, fungal mass, and branching of the fungal network of connected cells. From an image processing perspective, these tasks reduce to segmentation of vessel-like structures and the extraction of features from their skeletonization. In order to sample multiple infection events for analysis, we have developed an approach we refer to as macroscopic microscopy. However, macroscopic microscopy produces high-resolution image stacks that pose challenges to routine approaches and are difficult for a human to annotate to obtain ground truth data. We present a synthetic hyphal network generator, a comparison of several vessel segmentation methods, and a minimum spanning tree method for connecting small gaps resulting from imperfections in imaging or incomplete skeletonization of hyphal networks. Qualitative results are shown for real microscopic data. We believe the comparison of vessel detectors on macroscopic microscopy data, the synthetic vessel generator, and the gap closing technique are beneficial to the image processing community.
Tasks
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02356v1
PDF	http://arxiv.org/pdf/1704.02356v1.pdf
PWC	https://paperswithcode.com/paper/three-dimensional-segmentation-of-vesicular
Repo
Framework

Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection


Title	Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection
Authors	Tong Chen, Lin Wu, Xue Li, Jun Zhang, Hongzhi Yin, Yang Wang
Abstract	The proliferation of social media in communication and information dissemination has made it an ideal platform for spreading rumors. Automatically debunking rumors at their stage of diffusion is known as \textit{early rumor detection}, which refers to dealing with sequential posts regarding disputed factual claims with certain variations and highly textual duplication over time. Thus, identifying trending rumors demands an efficient yet flexible model that is able to capture long-range dependencies among postings and produce distinct representations for the accurate early detection. However, it is a challenging task to apply conventional classification algorithms to rumor detection in earliness since they rely on hand-crafted features which require intensive manual efforts in the case of large amount of posts. This paper presents a deep attention model on the basis of recurrent neural networks (RNN) to learn \textit{selectively} temporal hidden representations of sequential posts for identifying rumors. The proposed model delves soft-attention into the recurrence to simultaneously pool out distinct features with particular focus and produce hidden representations that capture contextual variations of relevant posts over time. Extensive experiments on real datasets collected from social media websites demonstrate that (1) the deep attention based RNN model outperforms state-of-the-arts that rely on hand-crafted features; (2) the introduction of soft attention mechanism can effectively distill relevant parts to rumors from original posts in advance; (3) the proposed method detects rumors more quickly and accurately than competitors.
Tasks	Deep Attention
Published	2017-04-20
URL	http://arxiv.org/abs/1704.05973v1
PDF	http://arxiv.org/pdf/1704.05973v1.pdf
PWC	https://paperswithcode.com/paper/call-attention-to-rumors-deep-attention-based
Repo
Framework

Group-wise Deep Co-saliency Detection


Title	Group-wise Deep Co-saliency Detection
Authors	Lina Wei, Shanshan Zhao, Omar El Farouk Bourahla, Xi Li, Fei Wu
Abstract	In this paper, we propose an end-to-end group-wise deep co-saliency detection approach to address the co-salient object discovery problem based on the fully convolutional network (FCN) with group input and group output. The proposed approach captures the group-wise interaction information for group images by learning a semantics-aware image representation based on a convolutional neural network, which adaptively learns the group-wise features for co-saliency detection. Furthermore, the proposed approach discovers the collaborative and interactive relationships between group-wise feature representation and single-image individual feature representation, and model this in a collaborative learning framework. Finally, we set up a unified end-to-end deep learning scheme to jointly optimize the process of group-wise feature representation learning and the collaborative learning, leading to more reliable and robust co-saliency detection results. Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.
Tasks	Co-Saliency Detection, Representation Learning, Saliency Detection
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07381v2
PDF	http://arxiv.org/pdf/1707.07381v2.pdf
PWC	https://paperswithcode.com/paper/group-wise-deep-co-saliency-detection
Repo
Framework

Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing


Title	Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing
Authors	Minh Le, Antske Fokkens
Abstract	Error propagation is a common problem in NLP. Reinforcement learning explores erroneous states during training and can therefore be more robust when mistakes are made early in a process. In this paper, we apply reinforcement learning to greedy dependency parsing which is known to suffer from error propagation. Reinforcement learning improves accuracy of both labeled and unlabeled dependencies of the Stanford Neural Dependency Parser, a high performance greedy parser, while maintaining its efficiency. We investigate the portion of errors which are the result of error propagation and confirm that reinforcement learning reduces the occurrence of error propagation.
Tasks	Dependency Parsing
Published	2017-02-22
URL	http://arxiv.org/abs/1702.06794v1
PDF	http://arxiv.org/pdf/1702.06794v1.pdf
PWC	https://paperswithcode.com/paper/tackling-error-propagation-through
Repo
Framework

On Generalization and Regularization in Deep Learning


Title	On Generalization and Regularization in Deep Learning
Authors	Pirmin Lemberger
Abstract	Why do large neural network generalize so well on complex tasks such as image classification or speech recognition? What exactly is the role regularization for them? These are arguably among the most important open questions in machine learning today. In a recent and thought provoking paper [C. Zhang et al.] several authors performed a number of numerical experiments that hint at the need for novel theoretical concepts to account for this phenomenon. The paper stirred quit a lot of excitement among the machine learning community but at the same time it created some confusion as discussions on OpenReview.net testifies. The aim of this pedagogical paper is to make this debate accessible to a wider audience of data scientists without advanced theoretical knowledge in statistical learning. The focus here is on explicit mathematical definitions and on a discussion of relevant concepts, not on proofs for which we provide references.
Tasks	Image Classification, Speech Recognition
Published	2017-04-05
URL	http://arxiv.org/abs/1704.01312v2
PDF	http://arxiv.org/pdf/1704.01312v2.pdf
PWC	https://paperswithcode.com/paper/on-generalization-and-regularization-in-deep
Repo
Framework

Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics


Title	Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics
Authors	Matthias Kümmerer, Thomas S. A. Wallis, Matthias Bethge
Abstract	Dozens of new models on fixation prediction are published every year and compared on open benchmarks such as MIT300 and LSUN. However, progress in the field can be difficult to judge because models are compared using a variety of inconsistent metrics. Here we show that no single saliency map can perform well under all metrics. Instead, we propose a principled approach to solve the benchmarking problem by separating the notions of saliency models, maps and metrics. Inspired by Bayesian decision theory, we define a saliency model to be a probabilistic model of fixation density prediction and a saliency map to be a metric-specific prediction derived from the model density which maximizes the expected performance on that metric given the model density. We derive these optimal saliency maps for the most commonly used saliency metrics (AUC, sAUC, NSS, CC, SIM, KL-Div) and show that they can be computed analytically or approximated with high precision. We show that this leads to consistent rankings in all metrics and avoids the penalties of using one saliency map for all metrics. Our method allows researchers to have their model compete on many different metrics with state-of-the-art in those metrics: “good” models will perform well in all metrics.
Tasks
Published	2017-04-27
URL	http://arxiv.org/abs/1704.08615v2
PDF	http://arxiv.org/pdf/1704.08615v2.pdf
PWC	https://paperswithcode.com/paper/saliency-benchmarking-made-easy-separating
Repo
Framework