October 20, 2019

3007 words 15 mins read

Paper Group ANR 99

Anomaly Detection for Industrial Big Data. CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web. Location Augmentation for CNN. Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising. Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System. Generative Des …

Anomaly Detection for Industrial Big Data


Title	Anomaly Detection for Industrial Big Data
Authors	Neil Caithness, David Wallom
Abstract	As the Industrial Internet of Things (IIoT) grows, systems are increasingly being monitored by arrays of sensors returning time-series data at ever-increasing ‘volume, velocity and variety’ (i.e. Industrial Big Data). An obvious use for these data is real-time systems condition monitoring and prognostic time to failure analysis (remaining useful life, RUL). (e.g. See white papers by Senseye.io, and output of the NASA Prognostics Center of Excellence (PCoE).) However, as noted by Agrawal and Choudhary ‘Our ability to collect “big data” has greatly surpassed our capability to analyze it, underscoring the emergence of the fourth paradigm of science, which is data-driven discovery.’ In order to fully utilize the potential of Industrial Big Data we need data-driven techniques that operate at scales that process models cannot. Here we present a prototype technique for data-driven anomaly detection to operate at industrial scale. The method generalizes to application with almost any multivariate dataset based on independent ordinations of repeated (bootstrapped) partitions of the dataset and inspection of the joint distribution of ordinal distances.
Tasks	Anomaly Detection, Time Series
Published	2018-04-09
URL	http://arxiv.org/abs/1804.02998v1
PDF	http://arxiv.org/pdf/1804.02998v1.pdf
PWC	https://paperswithcode.com/paper/anomaly-detection-for-industrial-big-data
Repo
Framework

CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web


Title	CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web
Authors	Colin Lockard, Xin Luna Dong, Arash Einolghozati, Prashant Shiralkar
Abstract	The web contains countless semi-structured websites, which can be a rich source of information for populating knowledge bases. Existing methods for extracting relations from the DOM trees of semi-structured webpages can achieve high precision and recall only when manual annotations for each website are available. Although there have been efforts to learn extractors from automatically-generated labels, these methods are not sufficiently robust to succeed in settings with complex schemas and information-rich websites. In this paper we present a new method for automatic extraction from semi-structured websites based on distant supervision. We automatically generate training labels by aligning an existing knowledge base with a web page and leveraging the unique structural characteristics of semi-structured websites. We then train a classifier based on the potentially noisy and incomplete labels to predict new relation instances. Our method can compete with annotation-based techniques in the literature in terms of extraction quality. A large-scale experiment on over 400,000 pages from dozens of multi-lingual long-tail websites harvested 1.25 million facts at a precision of 90%.
Tasks	Relation Extraction
Published	2018-04-12
URL	http://arxiv.org/abs/1804.04635v1
PDF	http://arxiv.org/pdf/1804.04635v1.pdf
PWC	https://paperswithcode.com/paper/ceres-distantly-supervised-relation
Repo
Framework

Location Augmentation for CNN


Title	Location Augmentation for CNN
Authors	Zhenyi Wang, Olga Veksler
Abstract	CNNs have made a tremendous impact on the field of computer vision in the last several years. The main component of any CNN architecture is the convolution operation, which is translation invariant by design. However, location in itself can be an important cue. For example, a salient object is more likely to be closer to the center of the image, the sky in the top part of an image, etc. To include the location cue for feature learning, we propose to augment the color image, the usual input to CNNs, with one or more channels that carry location information. We test two approaches for adding location information. In the first approach, we incorporate location directly, by including the row and column indexes as two additional channels to the input image. In the second approach, we add location less directly by adding distance transform from the center pixel as an additional channel to the input image. We perform experiments with both direct and indirect ways to encode location. We show the advantage of augmenting the standard color input with location related channels on the tasks of salient object segmentation, semantic segmentation, and scene parsing.
Tasks	Scene Parsing, Semantic Segmentation
Published	2018-07-18
URL	http://arxiv.org/abs/1807.07044v3
PDF	http://arxiv.org/pdf/1807.07044v3.pdf
PWC	https://paperswithcode.com/paper/location-augmentation-for-cnn
Repo
Framework

Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising


Title	Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising
Authors	Junwei Pan, Jian Xu, Alfonso Lobos Ruiz, Wenliang Zhao, Shengjun Pan, Yu Sun, Quan Lu
Abstract	Click-through rate (CTR) prediction is a critical task in online display advertising. The data involved in CTR prediction are typically multi-field categorical data, i.e., every feature is categorical and belongs to one and only one field. One of the interesting characteristics of such data is that features from one field often interact differently with features from different other fields. Recently, Field-aware Factorization Machines (FFMs) have been among the best performing models for CTR prediction by explicitly modeling such difference. However, the number of parameters in FFMs is in the order of feature number times field number, which is unacceptable in the real-world production systems. In this paper, we propose Field-weighted Factorization Machines (FwFMs) to model the different feature interactions between different fields in a much more memory-efficient way. Our experimental evaluations show that FwFMs can achieve competitive prediction performance with only as few as 4% parameters of FFMs. When using the same number of parameters, FwFMs can bring 0.92% and 0.47% AUC lift over FFMs on two real CTR prediction data sets.
Tasks	Click-Through Rate Prediction
Published	2018-06-09
URL	https://arxiv.org/abs/1806.03514v2
PDF	https://arxiv.org/pdf/1806.03514v2.pdf
PWC	https://paperswithcode.com/paper/field-weighted-factorization-machines-for
Repo
Framework

Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System


Title	Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System
Authors	Hong Wen, Jing Zhang, Quan Lin, Keping Yang, Pipei Huang
Abstract	Developing effective and efficient recommendation methods is very challenging for modern e-commerce platforms. Generally speaking, two essential modules named “Click-Through Rate Prediction” (\textit{CTR}) and “Conversion Rate Prediction” (\textit{CVR}) are included, where \textit{CVR} module is a crucial factor that affects the final purchasing volume directly. However, it is indeed very challenging due to its sparseness nature. In this paper, we tackle this problem by proposing multi-Level Deep Cascade Trees (\textit{ldcTree}), which is a novel decision tree ensemble approach. It leverages deep cascade structures by stacking Gradient Boosting Decision Trees (\textit{GBDT}) to effectively learn feature representation. In addition, we propose to utilize the cross-entropy in each tree of the preceding \textit{GBDT} as the input feature representation for next level \textit{GBDT}, which has a clear explanation, i.e., a traversal from root to leaf nodes in the next level \textit{GBDT} corresponds to the combination of certain traversals in the preceding \textit{GBDT}. The deep cascade structure and the combination rule enable the proposed \textit{ldcTree} to have a stronger distributed feature representation ability. Moreover, inspired by ensemble learning, we propose an Ensemble \textit{ldcTree} (\textit{E-ldcTree}) to encourage the model’s diversity and enhance the representation ability further. Finally, we propose an improved Feature learning method based on \textit{EldcTree} (\textit{F-EldcTree}) for taking adequate use of weak and strong correlation features identified by pre-trained \textit{GBDT} models. Experimental results on off-line data set and online deployment demonstrate the effectiveness of the proposed methods.
Tasks	Click-Through Rate Prediction
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09484v3
PDF	http://arxiv.org/pdf/1805.09484v3.pdf
PWC	https://paperswithcode.com/paper/multi-level-deep-cascade-trees-for-conversion
Repo
Framework

Generative Design in Minecraft (GDMC), Settlement Generation Competition


Title	Generative Design in Minecraft (GDMC), Settlement Generation Competition
Authors	Christoph Salge, Michael Cerny Green, Rodrigo Canaan, Julian Togelius
Abstract	This paper introduces the settlement generation competition for Minecraft, the first part of the Generative Design in Minecraft challenge. The settlement generation competition is about creating Artificial Intelligence (AI) agents that can produce functional, aesthetically appealing and believable settlements adapted to a given Minecraft map - ideally at a level that can compete with human created designs. The aim of the competition is to advance procedural content generation for games, especially in overcoming the challenges of adaptive and holistic PCG. The paper introduces the technical details of the challenge, but mostly focuses on what challenges this competition provides and why they are scientifically relevant.
Tasks
Published	2018-03-27
URL	http://arxiv.org/abs/1803.09853v2
PDF	http://arxiv.org/pdf/1803.09853v2.pdf
PWC	https://paperswithcode.com/paper/generative-design-in-minecraft-gdmc
Repo
Framework

A Sauer-Shelah-Perles Lemma for Sumsets


Title	A Sauer-Shelah-Perles Lemma for Sumsets
Authors	Zeev Dvir, Shay Moran
Abstract	We show that any family of subsets $A\subseteq 2^{[n]}$ satisfies $\lvert A\rvert \leq O\bigl(n^{\lceil{d}/{2}\rceil}\bigr)$, where $d$ is the VC dimension of ${S\triangle T ,\vert, S,T\in A}$, and $\triangle$ is the symmetric difference operator. We also observe that replacing $\triangle$ by either $\cup$ or $\cap$ fails to satisfy an analogous statement. Our proof is based on the polynomial method; specifically, on an argument due to [Croot, Lev, Pach ‘17].
Tasks
Published	2018-06-14
URL	http://arxiv.org/abs/1806.05737v2
PDF	http://arxiv.org/pdf/1806.05737v2.pdf
PWC	https://paperswithcode.com/paper/a-sauer-shelah-perles-lemma-for-sumsets
Repo
Framework

Modeling, comprehending and summarizing textual content by graphs


Title	Modeling, comprehending and summarizing textual content by graphs
Authors	Vinicius Woloszyn, Guilherme Medeiros Machado, Leandro Krug Wives, José Palazzo Moreira de Oliveira
Abstract	Automatic Text Summarization strategies have been successfully employed to digest text collections and extract its essential content. Usually, summaries are generated using textual corpora that belongs to the same domain area where the summary will be used. Nonetheless, there are special cases where it is not found enough textual sources, and one possible alternative is to generate a summary from a different domain. One manner to summarize texts consists of using a graph model. This model allows giving more importance to words corresponding to the main concepts from the target domain found in the summarized text. This gives the reader an overview of the main text concepts as well as their relationships. However, this kind of summarization presents a significant number of repeated terms when compared to human-generated summaries. In this paper, we present an approach to produce graph-model extractive summaries of texts, meeting the target domain exigences and treating the terms repetition problem. To evaluate the proposition, we performed a series of experiments showing that the proposed approach statistically improves the performance of a model based on Graph Centrality, achieving better coverage, accuracy, and recall.
Tasks	Text Summarization
Published	2018-07-01
URL	http://arxiv.org/abs/1807.00303v1
PDF	http://arxiv.org/pdf/1807.00303v1.pdf
PWC	https://paperswithcode.com/paper/modeling-comprehending-and-summarizing
Repo
Framework

Reliability Map Estimation For CNN-Based Camera Model Attribution


Title	Reliability Map Estimation For CNN-Based Camera Model Attribution
Authors	David Güera, Sri Kalyan Yarlagadda, Paolo Bestagini, Fengqing Zhu, Stefano Tubaro, Edward J. Delp
Abstract	Among the image forensic issues investigated in the last few years, great attention has been devoted to blind camera model attribution. This refers to the problem of detecting which camera model has been used to acquire an image by only exploiting pixel information. Solving this problem has great impact on image integrity assessment as well as on authenticity verification. Recent advancements that use convolutional neural networks (CNNs) in the media forensic field have enabled camera model attribution methods to work well even on small image patches. These improvements are also important for determining forgery localization. Some patches of an image may not contain enough information related to the camera model (e.g., saturated patches). In this paper, we propose a CNN-based solution to estimate the camera model attribution reliability of a given image patch. We show that we can estimate a reliability-map indicating which portions of the image contain reliable camera traces. Testing using a well known dataset confirms that by using this information, it is possible to increase small patch camera model attribution accuracy by more than 8% on a single patch.
Tasks
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01946v1
PDF	http://arxiv.org/pdf/1805.01946v1.pdf
PWC	https://paperswithcode.com/paper/reliability-map-estimation-for-cnn-based
Repo
Framework

Information-Theoretic Scoring Rules to Learn Additive Bayesian Network Applied to Epidemiology


Title	Information-Theoretic Scoring Rules to Learn Additive Bayesian Network Applied to Epidemiology
Authors	Gilles Kratzer, Reinhard Furrer
Abstract	Bayesian network modelling is a well adapted approach to study messy and highly correlated datasets which are very common in, e.g., systems epidemiology. A popular approach to learn a Bayesian network from an observational datasets is to identify the maximum a posteriori network in a search-and-score approach. Many scores have been proposed both Bayesian or frequentist based. In an applied perspective, a suitable approach would allow multiple distributions for the data and is robust enough to run autonomously. A promising framework to compute scores are generalized linear models. Indeed, there exists fast algorithms for estimation and many tailored solutions to common epidemiological issues. The purpose of this paper is to present an R package abn that has an implementation of multiple frequentist scores and some realistic simulations that show its usability and performance. It includes features to deal efficiently with data separation and adjustment which are very common in systems epidemiology.
Tasks	Epidemiology
Published	2018-08-03
URL	http://arxiv.org/abs/1808.01126v1
PDF	http://arxiv.org/pdf/1808.01126v1.pdf
PWC	https://paperswithcode.com/paper/information-theoretic-scoring-rules-to-learn
Repo
Framework

A Function Fitting Method


Title	A Function Fitting Method
Authors	Rajesh Dachiraju
Abstract	In this article, we describe a function fitting method that has potential applications in machine learning and also prove relevant theorems. The described function fitting method is a convex minimization problem and can be solved using a gradient descent algorithm. We also provide qualitative analysis on fitness to data of this function fitting method. The function fitting problem is also shown to be a solution of a linear, weak partial differential equation(PDE). We describe a way to fit a Sobolev function by giving a method to choose the optimal $\lambda$ parameter. We describe a closed-form solution to the derived PDE, which enables the parametrization of the solution function. We describe a simple numerical solution using a gradient descent algorithm, that converges uniformly to the actual solution. As the functional of the minimization problem is a quadratic form, there also exists a numerical method using linear algebra. Lastly, we give some numerical examples and also numerically demonstrate its application to a binary classification problem.
Tasks
Published	2018-11-04
URL	https://arxiv.org/abs/1811.01336v5
PDF	https://arxiv.org/pdf/1811.01336v5.pdf
PWC	https://paperswithcode.com/paper/a-function-fitting-method
Repo
Framework

ConvCSNet: A Convolutional Compressive Sensing Framework Based on Deep Learning


Title	ConvCSNet: A Convolutional Compressive Sensing Framework Based on Deep Learning
Authors	Xiaotong Lu, Weisheng Dong, Peiyao Wang, Guangming Shi, Xuemei Xie
Abstract	Compressive sensing (CS), aiming to reconstruct an image/signal from a small set of random measurements has attracted considerable attentions in recent years. Due to the high dimensionality of images, previous CS methods mainly work on image blocks to avoid the huge requirements of memory and computation, i.e., image blocks are measured with Gaussian random matrices, and the whole images are recovered from the reconstructed image blocks. Though efficient, such methods suffer from serious blocking artifacts. In this paper, we propose a convolutional CS framework that senses the whole image using a set of convolutional filters. Instead of reconstructing individual blocks, the whole image is reconstructed from the linear convolutional measurements. Specifically, the convolutional CS is implemented based on a convolutional neural network (CNN), which performs both the convolutional CS and nonlinear reconstruction. Through end-to-end training, the sensing filters and the reconstruction network can be jointly optimized. To facilitate the design of the CS reconstruction network, a novel two-branch CNN inspired from a sparsity-based CS reconstruction model is developed. Experimental results show that the proposed method substantially outperforms previous state-of-the-art CS methods in term of both PSNR and visual quality.
Tasks	Compressive Sensing
Published	2018-01-31
URL	http://arxiv.org/abs/1801.10342v1
PDF	http://arxiv.org/pdf/1801.10342v1.pdf
PWC	https://paperswithcode.com/paper/convcsnet-a-convolutional-compressive-sensing
Repo
Framework

TherML: Thermodynamics of Machine Learning


Title	TherML: Thermodynamics of Machine Learning
Authors	Alexander A. Alemi, Ian Fischer
Abstract	In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning. We develop a formal correspondence between this work and thermodynamics and discuss its implications.
Tasks
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04162v3
PDF	http://arxiv.org/pdf/1807.04162v3.pdf
PWC	https://paperswithcode.com/paper/therml-thermodynamics-of-machine-learning
Repo
Framework

High-throughput, high-resolution registration-free generated adversarial network microscopy


Title	High-throughput, high-resolution registration-free generated adversarial network microscopy
Authors	Hao Zhang, Xinlin Xie, Chunyu Fang, Yicong Yang, Di Jin, Peng Fei
Abstract	We combine generative adversarial network (GAN) with light microscopy to achieve deep learning super-resolution under a large field of view (FOV). By appropriately adopting prior microscopy data in an adversarial training, the neural network can recover a high-resolution, accurate image of new specimen from its single low-resolution measurement. Its capacity has been broadly demonstrated via imaging various types of samples, such as USAF resolution target, human pathological slides, fluorescence-labelled fibroblast cells, and deep tissues in transgenic mouse brain, by both wide-field and light-sheet microscopes. The gigapixel, multi-color reconstruction of these samples verifies a successful GAN-based single image super-resolution procedure. We also propose an image degrading model to generate low resolution images for training, making our approach free from the complex image registration during training dataset preparation. After a welltrained network being created, this deep learning-based imaging approach is capable of recovering a large FOV (~95 mm2), high-resolution (~1.7 {\mu}m) image at high speed (within 1 second), while not necessarily introducing any changes to the setup of existing microscopes.
Tasks	Image Registration, Image Super-Resolution, Super-Resolution
Published	2018-01-07
URL	http://arxiv.org/abs/1801.07330v2
PDF	http://arxiv.org/pdf/1801.07330v2.pdf
PWC	https://paperswithcode.com/paper/high-throughput-high-resolution-registration
Repo
Framework

Patient Subtyping with Disease Progression and Irregular Observation Trajectories


Title	Patient Subtyping with Disease Progression and Irregular Observation Trajectories
Authors	Nikhil Galagali, Minnan Xu-Wilson
Abstract	Patient subtyping based on temporal observations can lead to significantly nuanced subtyping that acknowledges the dynamic characteristics of diseases. Existing methods for subtyping trajectories treat the evolution of clinical observations as a homogeneous process or employ data available at regular intervals. In reality, diseases may have transient underlying states and a state-dependent observation pattern. In our paper, we present an approach to subtype irregular patient data while acknowledging the underlying progression of disease states. Our approach consists of two components: a probabilistic model to determine the likelihood of a patient’s observation trajectory and a mixture model to measure similarity between asynchronous patient trajectories. We demonstrate our model by discovering subtypes of progression to hemodynamic instability (requiring cardiovascular intervention) in a patient cohort from a multi-institution ICU dataset. We find three primary patterns: two of which show classic signs of decompensation (rising heart rate with dropping blood pressure), with one of these showing a faster course of decompensation than the other. The third pattern has transient period of low heart rate and blood pressure. We also show that our model results in a 13% reduction in average cross-entropy error compared to a model with no state progression when forecasting vital signs.
Tasks
Published	2018-10-21
URL	http://arxiv.org/abs/1810.09043v4
PDF	http://arxiv.org/pdf/1810.09043v4.pdf
PWC	https://paperswithcode.com/paper/patient-subtyping-with-disease-progression
Repo
Framework