January 30, 2020

3475 words 17 mins read

Paper Group ANR 340

Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution. Free resolutions of function classes via order complexes. A Semi-Automated Approach for Information Extraction, Classification and Analysis of Unstructured Data. Autonomous Voltage Control for Grid Operation Using Deep Reinforcement Learning. Artificial Intelligence and Machin …

Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution


Title	Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution
Authors	Lei Zhang, Zhiqiang Lang, Peng Wang, Wei Wei, Shengcai Liao, Ling Shao, Yanning Zhang
Abstract	Spectral super-resolution (SSR) aims at generating a hyperspectral image (HSI) from a given RGB image. Recently, a promising direction for SSR is to learn a complicated mapping function from the RGB image to the HSI counterpart using a deep convolutional neural network. This essentially involves mapping the RGB context within a size-specific receptive field centered at each pixel to its spectrum in the HSI. The focus thereon is to appropriately determine the receptive field size and establish the mapping function from RGB context to the corresponding spectrum. Due to their differences in category or spatial position, pixels in HSIs often require different-sized receptive fields and distinct mapping functions. However, few efforts have been invested to explicitly exploit this prior. To address this problem, we propose a pixel-aware deep function-mixture network for SSR, which is composed of a new class of modules, termed function-mixture (FM) blocks. Each FM block is equipped with some basis functions, i.e., parallel subnets of different-sized receptive fields. Besides, it incorporates an extra subnet as a mixing function to generate pixel-wise weights, and then linearly mixes the outputs of all basis functions with those generated weights. This enables us to pixel-wisely determine the receptive field size and the mapping function. Moreover, we stack several such FM blocks to further increase the flexibility of the network in learning the pixel-wise mapping. To encourage feature reuse, intermediate features generated by the FM blocks are fused in late stage, which proves to be effective for boosting the SSR performance. Experimental results on three benchmark HSI datasets demonstrate the superiority of the proposed method.
Tasks	Super-Resolution
Published	2019-03-24
URL	http://arxiv.org/abs/1903.10501v1
PDF	http://arxiv.org/pdf/1903.10501v1.pdf
PWC	https://paperswithcode.com/paper/pixel-aware-deep-function-mixture-network-for
Repo
Framework

Free resolutions of function classes via order complexes


Title	Free resolutions of function classes via order complexes
Authors	Justin Chen, Christopher Eur, Greg Yang, Mengyuan Zhang
Abstract	Function classes are collections of Boolean functions on a finite set, which are fundamental objects of study in theoretical computer science. We study algebraic properties of ideals associated to function classes previously defined by the third author. We consider the broad family of intersection-closed function classes, and describe cellular free resolutions of their ideals by order complexes of the associated posets. For function classes arising from matroids, polyhedral cell complexes, and more generally interval Cohen-Macaulay posets, we show that the multigraded Betti numbers are pure, and are given combinatorially by the M"obius functions. We then apply our methods to derive bounds on the VC dimension of some important families of function classes in learning theory.
Tasks
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02159v1
PDF	https://arxiv.org/pdf/1909.02159v1.pdf
PWC	https://paperswithcode.com/paper/free-resolutions-of-function-classes-via
Repo
Framework

A Semi-Automated Approach for Information Extraction, Classification and Analysis of Unstructured Data


Title	A Semi-Automated Approach for Information Extraction, Classification and Analysis of Unstructured Data
Authors	Alberto Purpura, Marco Calaresu
Abstract	In this paper, we show how Quantitative Narrative Analysis and simple Natural Language Processing techniques apply to the extraction and categorization of data in a sample case study of the Diary of the former President of the Italian Republic (PoR), Giorgio Napolitano. The Diary contains a record of all his institutional meetings. This information, if properly handled, allows for an analysis of how the PoR used his so-called soft-powers to influence the Italian political system during his first mandate. In this paper, we propose a way to use simple, yet very effective, Natural Language Processing techniques - such as Regular Expressions and Named Entity Recognition - to extract information from the Diary. Then, we propose an innovative way to organize the extracted data relying on the methodological framework of Quantitative Narrative Analysis. Finally, we show how to analyze the structured data under different levels of detail using PC-ACE (Program for Computer-Assisted Coding of Events), a software developed specifically for this task and for data visualization.
Tasks	Named Entity Recognition
Published	2019-10-20
URL	https://arxiv.org/abs/1910.12734v1
PDF	https://arxiv.org/pdf/1910.12734v1.pdf
PWC	https://paperswithcode.com/paper/a-semi-automated-approach-for-information
Repo
Framework

Autonomous Voltage Control for Grid Operation Using Deep Reinforcement Learning


Title	Autonomous Voltage Control for Grid Operation Using Deep Reinforcement Learning
Authors	Ruisheng Diao, Zhiwei Wang, Di Shi, Qianyun Chang, Jiajun Duan, Xiaohu Zhang
Abstract	Modern power grids are experiencing grand challenges caused by the stochastic and dynamic nature of growing renewable energy and demand response. Traditional theoretical assumptions and operational rules may be violated, which are difficult to be adapted by existing control systems due to the lack of computational power and accurate grid models for use in real time, leading to growing concerns in the secure and economic operation of the power grid. Existing operational control actions are typically determined offline, which are less optimized. This paper presents a novel paradigm, Grid Mind, for autonomous grid operational controls using deep reinforcement learning. The proposed AI agent for voltage control can learn its control policy through interactions with massive offline simulations, and adapts its behavior to new changes including not only load/generation variations but also topological changes. A properly trained agent is tested on the IEEE 14-bus system with tens of thousands of scenarios, and promising performance is demonstrated in applying autonomous voltage controls for secure grid operation.
Tasks
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10597v1
PDF	http://arxiv.org/pdf/1904.10597v1.pdf
PWC	https://paperswithcode.com/paper/autonomous-voltage-control-for-grid-operation
Repo
Framework

Artificial Intelligence and Machine Learning to Predict and Improve Efficiency in Manufacturing Industry


Title	Artificial Intelligence and Machine Learning to Predict and Improve Efficiency in Manufacturing Industry
Authors	Ibtissam El Hassani, Choumicha El Mazgualdi, Tawfik Masrour
Abstract	The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the necessary decisions in order to improve the situation. However, this calculation is done a-posterior which is often too late. In the present research, we implemented different Machine Learning algorithms namely; Support vector machine, Optimized Support vector Machine (using Genetic Algorithm), Random Forest, XGBoost and Deep Learning to predict the estimate OEE value. The data used to train our models was provided by an automotive cable production industry. The results show that the Deep Learning and Random Forest are more accurate and present better performance for the prediction of the overall equipment effectiveness in our case study.
Tasks
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02256v2
PDF	http://arxiv.org/pdf/1901.02256v2.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-and-machine-learning
Repo
Framework

An Efficient Framework for Visible-Infrared Cross Modality Person Re-Identification


Title	An Efficient Framework for Visible-Infrared Cross Modality Person Re-Identification
Authors	Emrah Basaran, Muhittin Gokmen, Mustafa E. Kamasak
Abstract	Visible-infrared cross modality person re-identification (VI-ReId) is an important task for video surveillance in poorly illuminated or dark environments. Despite many recent studies on person re-identification in visible domain (ReId), there are few studies dealing with VI-ReId. Besides challenges that are common for both ReId and VI-ReId such as pose/illumination variations, background clutter and occlusion, VI-ReId has additional challenges as color information is not available in infrared images. As a result, the performance of VI-ReId systems is typically lower than ReId systems. In this work, we propose a 4-stream framework to improve VI-ReId performance. We train a separate deep convolutional neural network in each stream using different representations of input images. We expect that different and complementary features can be learned from each stream. In our framework, grayscale and infrared input images are used to train the ResNet in the first stream. In the second stream, RGB and 3-channel infrared images (created by repeating infrared channel) are used. In the remaining two streams, we use local pattern maps as input images. These maps are generated utilizing local Zernike moments transformation. Local pattern maps are obtained from grayscale and infrared images in the 3rd stream and from RGB and 3-channel infrared images in the last stream. We improve the performance of the proposed framework by employing a re-ranking algorithm for post processing. Our results indicate that the proposed framework outperforms current state-of-the-art on SYSU-MM01 dataset with large margin by improving Rank-1/mAP by 34.2%/37.9% and 37.4%/34.8% under all-search and indoor-search modes, respectively.
Tasks	Person Re-Identification
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06498v1
PDF	https://arxiv.org/pdf/1907.06498v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-framework-for-visible-infrared
Repo
Framework

ACE – An Anomaly Contribution Explainer for Cyber-Security Applications


Title	ACE – An Anomaly Contribution Explainer for Cyber-Security Applications
Authors	Xiao Zhang, Manish Marwah, I-ta Lee, Martin Arlitt, Dan Goldwasser
Abstract	In this paper, we introduce Anomaly Contribution Explainer or ACE, a tool to explain security anomaly detection models in terms of the model features through a regression framework, and its variant, ACE-KL, which highlights the important anomaly contributors. ACE and ACE-KL provide insights in diagnosing which attributes significantly contribute to an anomaly by building a specialized linear model to locally approximate the anomaly score that a black-box model generates. We conducted experiments with these anomaly detection models to detect security anomalies on both synthetic data and real data. In particular, we evaluate performance on three public data sets: CERT insider threat, netflow logs, and Android malware. The experimental results are encouraging: our methods consistently identify the correct contributing feature in the synthetic data where ground truth is available; similarly, for real data sets, our methods point a security analyst in the direction of the underlying causes of an anomaly, including in one case leading to the discovery of previously overlooked network scanning activity. We have made our source code publicly available.
Tasks	Anomaly Detection
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00314v2
PDF	https://arxiv.org/pdf/1912.00314v2.pdf
PWC	https://paperswithcode.com/paper/an-anomaly-contribution-explainer-for-cyber
Repo
Framework

A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification


Title	A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification
Authors	Jiaxuan Zhuo, Jianhuang Lai, Peijia Chen
Abstract	Person re-identification (re-id) has made great progress in recent years, but occlusion is still a challenging problem which significantly degenerates the identification performance. In this paper, we design a teacher-student learning framework to learn an occlusion-robust model from the full-body person domain to the occluded person domain. Notably, the teacher network only uses large-scale full-body person data to simulate the learning process of occluded person re-id. Based on the teacher network, the student network then trains a better model by using inadequate real-world occluded person data. In order to transfer more knowledge from the teacher network to the student network, we equip the proposed framework with a co-saliency network and a cross-domain simulator. The co-saliency network extracts the backbone features, and two separated collaborative branches are followed by the backbone. One branch is a classification branch for identity recognition and the other is a co-saliency branch for guiding the network to highlight meaningful parts without any manual annotation. The cross-domain simulator generates artificial occlusions on full-body person data under a growing probability so that the teacher network could train a cross-domain model by observing more and more occluded cases. Experiments on four occluded person re-id benchmarks show that our method outperforms other state-of-the-art methods.
Tasks	Person Re-Identification
Published	2019-07-07
URL	https://arxiv.org/abs/1907.03253v1
PDF	https://arxiv.org/pdf/1907.03253v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-teacher-student-learning-framework
Repo
Framework

Host-based anomaly detection using Eigentraces feature extraction and one-class classification on system call trace data


Title	Host-based anomaly detection using Eigentraces feature extraction and one-class classification on system call trace data
Authors	Ehsan Aghaei, Gursel Serpen
Abstract	This paper proposes a methodology for host-based anomaly detection using a semi-supervised algorithm namely one-class classifier combined with a PCA-based feature extraction technique called Eigentraces on system call trace data. The one-class classification is based on generating a set of artificial data using a reference distribution and combining the target class probability function with artificial class density function to estimate the target class density function through the Bayes formulation. The benchmark dataset, ADFA-LD, is employed for the simulation study. ADFA-LD dataset contains thousands of system call traces collected during various normal and attack processes for the Linux operating system environment. In order to pre-process and to extract features, windowing on the system call trace data followed by the principal component analysis which is named as Eigentraces is implemented. The target class probability function is modeled separately by Radial Basis Function neural network and Random Forest machine learners for performance comparison purposes. The simulation study showed that the proposed intrusion detection system offers high performance for detecting anomalies and normal activities with respect to a set of well-accepted metrics including detection rate, accuracy, and missed and false alarm rates.
Tasks	Anomaly Detection, Intrusion Detection, One-class classifier
Published	2019-11-25
URL	https://arxiv.org/abs/1911.11284v1
PDF	https://arxiv.org/pdf/1911.11284v1.pdf
PWC	https://paperswithcode.com/paper/host-based-anomaly-detection-using
Repo
Framework

AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces


Title	AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces
Authors	Manpreet Singh Minhas, John Zelek
Abstract	Humans can easily detect a defect (anomaly) because it is different or salient when compared to the surface it resides on. Today, manual human visual inspection is still the norm because it is difficult to automate anomaly detection. Neural networks are a useful tool that can teach a machine to find defects. However, they require a lot of training examples to learn what a defect is and it is tedious and expensive to get these samples. We tackle the problem of teaching a network with a low number of training samples with a system we call AnoNet. AnoNet’s architecture is similar to CompactCNN with the exceptions that (1) it is a fully convolutional network and does not use strided convolution; (2) it is shallow and compact which minimizes over-fitting by design; (3) the compact design constrains the size of intermediate features which allows training to be done without image downsizing; (4) the model footprint is low making it suitable for edge computation; and (5) the anomaly can be detected and localized despite the weak labelling. AnoNet learns to detect the underlying shape of the anomalies despite the weak annotation as well as preserves the spatial localization of the anomaly. Pre-seeding AnoNet with an engineered filter bank initialization technique reduces the total samples required for training and also achieves state-of-the-art performance. Compared to the CompactCNN, AnoNet achieved a massive 94% reduction of network parameters from 1.13 million to 64 thousand parameters. Experiments were conducted on four data-sets and results were compared against CompactCNN and DeepLabv3. AnoNet improved the performance on an average across all data-sets by 106% to an F1 score of 0.98 and by 13% to an AUROC value of 0.942. AnoNet can learn from a limited number of images. For one of the data-sets, AnoNet learnt to detect anomalies after a single pass through just 53 training images.
Tasks	Anomaly Detection
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10608v1
PDF	https://arxiv.org/pdf/1911.10608v1.pdf
PWC	https://paperswithcode.com/paper/anonet-weakly-supervised-anomaly-detection-in
Repo
Framework

A Multi-level Neural Network for Implicit Causality Detection in Web Texts


Title	A Multi-level Neural Network for Implicit Causality Detection in Web Texts
Authors	Shining Liang, Wanli Zuo, Zhenkun Shi, Sen Wang
Abstract	Mining causality from text is a complex and crucial natural language understanding task. Most of the early attempts at its solution can group into two categories: 1) utilizing co-occurrence frequency and world knowledge for causality detection; 2) extracting cause-effect pairs by using connectives and syntax patterns directly. However, because causality has various linguistic expressions, the noisy data and ignoring implicit expressions problems induced by these methods cannot be avoided. In this paper, we present a neural causality detection model, namely Multi-level Causality Detection Network (MCDN), to address this problem. Specifically, we adopt multi-head self-attention to acquire semantic feature at word level and integrate a novel Relation Network to infer causality at segment level. To the best of our knowledge, in touch with the causality tasks, this is the first time that the Relation Network is applied. The experimental results on the AltLex dataset, demonstrate that: a) MCDN is highly effective for the ambiguous and implicit causality inference; b) comparing with the regular text classification task, causality detection requires stronger inference capability; c) the proposed approach achieved state-of-the-art performance.
Tasks	Text Classification
Published	2019-08-18
URL	https://arxiv.org/abs/1908.07822v2
PDF	https://arxiv.org/pdf/1908.07822v2.pdf
PWC	https://paperswithcode.com/paper/190807822
Repo
Framework

Distributed Training of Embeddings using Graph Analytics


Title	Distributed Training of Embeddings using Graph Analytics
Authors	Gurbinder Gill, Roshan Dathathri, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Olli Saarikivi
Abstract	Many applications today, such as NLP, network analysis, and code analysis, rely on semantically embedding objects into low-dimensional fixed-length vectors. Such embeddings naturally provide a way to perform useful downstream tasks, such as identifying relations among objects or predicting objects for a given context, etc. Unfortunately, the training necessary for accurate embeddings is usually computationally intensive and requires processing large amounts of data. Furthermore, distributing this training is challenging. Most embedding training uses stochastic gradient descent (SGD), an “inherently” sequential algorithm. Prior approaches to parallelizing SGD do not honor these dependencies and thus potentially suffer poor convergence. This paper presents a distributed training framework for a class of applications that use Skip-gram-like models to generate embeddings. We call this class Any2Vec and it includes Word2Vec, DeepWalk, and Node2Vec among others. We first formulate Any2Vec training algorithm as a graph application and leverage the state-of-the-art distributed graph analytics framework, D-Galois. We adapt D-Galois to support dynamic graph generation and repartitioning, and incorporate novel communication optimizations. Finally, we introduce a novel way to combine gradients during distributed training to prevent accuracy loss. We show that our framework, called GraphAny2Vec, matches on a cluster of 32 hosts the accuracy of the state-of-the-art shared-memory implementations of Word2Vec and Vertex2Vec on 1 host, and gives a geo-mean speedup of 12x and 5x respectively. Furthermore, GraphAny2Vec is on average 2x faster than the state-of-the-art distributed Word2Vec implementation, DMTK, on 32 hosts. We also show the superiority of our Gradient Combiner independent of GraphAny2Vec by incorporating it in DMTK, which raises its accuracy by > 30%.
Tasks	Graph Generation, Word Embeddings
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03359v2
PDF	https://arxiv.org/pdf/1909.03359v2.pdf
PWC	https://paperswithcode.com/paper/distributed-word2vec-using-graph-analytics
Repo
Framework

Scalable Generative Models for Graphs with Graph Attention Mechanism


Title	Scalable Generative Models for Graphs with Graph Attention Mechanism
Authors	Wataru Kawai, Yusuke Mukuta, Tatsuya Harada
Abstract	Graphs are ubiquitous real-world data structures, and generative models that approximate distributions over graphs and derive new samples from them have significant importance. Among the known challenges in graph generation tasks, scalability handling of large graphs and datasets is one of the most important for practical applications. Recently, an increasing number of graph generative models have been proposed and have demonstrated impressive results. However, scalability is still an unresolved problem due to the complex generation process or difficulty in training parallelization. In this paper, we first define scalability from three different perspectives: number of nodes, data, and node/edge labels. Then, we propose GRAM, a generative model for graphs that is scalable in all three contexts, especially in training. We aim to achieve scalability by employing a novel graph attention mechanism, formulating the likelihood of graphs in a simple and general manner. Also, we apply two techniques to reduce computational complexity. Furthermore, we construct a unified and non-domain-specific evaluation metric in node/edge-labeled graph generation tasks by combining a graph kernel and Maximum Mean Discrepancy. Our experiments on synthetic and real-world graphs demonstrated the scalability of our models and their superior performance compared with baseline methods.
Tasks	Graph Generation
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01861v2
PDF	https://arxiv.org/pdf/1906.01861v2.pdf
PWC	https://paperswithcode.com/paper/gram-scalable-generative-models-for-graphs
Repo
Framework

A Graph Autoencoder Approach to Causal Structure Learning


Title	A Graph Autoencoder Approach to Causal Structure Learning
Authors	Ignavier Ng, Shengyu Zhu, Zhitang Chen, Zhuangyan Fang
Abstract	Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees. Recently, a new approach has transformed the combinatorial structure learning problem into a continuous one and then solved it using gradient-based optimization methods. Following the recent state-of-the-arts, we propose a new gradient-based method to learn causal structures from observational data. The proposed method generalizes the recent gradient-based methods to a graph autoencoder framework that allows nonlinear structural equation models and is easily applicable to vector-valued variables. We demonstrate that on synthetic datasets, our proposed method outperforms other gradient-based methods significantly, especially on large causal graphs. We further investigate the scalability and efficiency of our method, and observe a near linear training time when scaling up the graph size.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07420v1
PDF	https://arxiv.org/pdf/1911.07420v1.pdf
PWC	https://paperswithcode.com/paper/a-graph-autoencoder-approach-to-causal
Repo
Framework

Deep Q-Learning for Directed Acyclic Graph Generation


Title	Deep Q-Learning for Directed Acyclic Graph Generation
Authors	Laura D’Arcy, Padraig Corcoran, Alun Preece
Abstract	We present a method to generate directed acyclic graphs (DAGs) using deep reinforcement learning, specifically deep Q-learning. Generating graphs with specified structures is an important and challenging task in various application fields, however most current graph generation methods produce graphs with undirected edges. We demonstrate that this method is capable of generating DAGs with topology and node types satisfying specified criteria in highly sparse reward environments.
Tasks	Graph Generation, Q-Learning
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02280v1
PDF	https://arxiv.org/pdf/1906.02280v1.pdf
PWC	https://paperswithcode.com/paper/deep-q-learning-for-directed-acyclic-graph
Repo
Framework