January 31, 2020

3033 words 15 mins read

Paper Group ANR 144

GraphSAC: Detecting anomalies in large-scale graphs. Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks. Heuristic Black-box Adversarial Attacks on Video Recognition Models. Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints. SMART: Skeletal Motion …

GraphSAC: Detecting anomalies in large-scale graphs


Title	GraphSAC: Detecting anomalies in large-scale graphs
Authors	Vassilis N. Ioannidis, Dimitris Berberidis, Georgios B. Giannakis
Abstract	A graph-based sampling and consensus (GraphSAC) approach is introduced to effectively detect anomalous nodes in large-scale graphs. Existing approaches rely on connectivity and attributes of all nodes to assign an anomaly score per node. However, nodal attributes and network links might be compromised by adversaries, rendering these holistic approaches vulnerable. Alleviating this limitation, GraphSAC randomly draws subsets of nodes, and relies on graph-aware criteria to judiciously filter out sets contaminated by anomalous nodes, before employing a semi-supervised learning (SSL) module to estimate nominal label distributions per node. These learned nominal distributions are minimally affected by the anomalous nodes, and hence can be directly adopted for anomaly detection. Rigorous analysis provides performance guarantees for GraphSAC, by bounding the required number of draws. The per-draw complexity grows linearly with the number of edges, which implies efficient SSL, while draws can be run in parallel, thereby ensuring scalability to large graphs. GraphSAC is tested under different anomaly generation models based on random walks, clustered anomalies, as well as contemporary adversarial attacks for graph data. Experiments with real-world graphs showcase the advantage of GraphSAC relative to state-of-the-art alternatives.
Tasks	Anomaly Detection
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09589v1
PDF	https://arxiv.org/pdf/1910.09589v1.pdf
PWC	https://paperswithcode.com/paper/graphsac-detecting-anomalies-in-large-scale
Repo
Framework

Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks


Title	Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
Authors	Yaqin Zhou, Shangqing Liu, Jingkai Siow, Xiaoning Du, Yang Liu
Abstract	Vulnerability identification is crucial to protect the software systems from attacks for cyber security. It is especially important to localize the vulnerable functions among the source code to facilitate the fix. However, it is a challenging and tedious process, and also requires specialized security expertise. Inspired by the work on manually-defined patterns of vulnerabilities from various code representation graphs and the recent advance on graph neural networks, we propose Devign, a general graph neural network based model for graph-level classification through learning on a rich set of code semantic representations. It includes a novel Conv module to efficiently extract useful features in the learned rich node representations for graph-level classification. The model is trained over manually labeled datasets built on 4 diversified large-scale open-source C projects that incorporate high complexity and variety of real source code instead of synthesis code used in previous works. The results of the extensive evaluation on the datasets demonstrate that Devign outperforms the state of the arts significantly with an average of 10.51% higher accuracy and 8.68% F1 score, increases averagely 4.66% accuracy and 6.37% F1 by the Conv module.
Tasks
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03496v1
PDF	https://arxiv.org/pdf/1909.03496v1.pdf
PWC	https://paperswithcode.com/paper/devign-effective-vulnerability-identification
Repo
Framework

Heuristic Black-box Adversarial Attacks on Video Recognition Models


Title	Heuristic Black-box Adversarial Attacks on Video Recognition Models
Authors	Zhipeng Wei, Jingjing Chen, Xingxing Wei, Linxi Jiang, Tat-Seng Chua, Fengfeng Zhou, Yu-Gang Jiang
Abstract	We study the problem of attacking video recognition models in the black-box setting, where the model information is unknown and the adversary can only make queries to detect the predicted top-1 class and its probability. Compared with the black-box attack on images, attacking videos is more challenging as the computation cost for searching the adversarial perturbations on a video is much higher due to its high dimensionality. To overcome this challenge, we propose a heuristic black-box attack model that generates adversarial perturbations only on the selected frames and regions. More specifically, a heuristic-based algorithm is proposed to measure the importance of each frame in the video towards generating the adversarial examples. Based on the frames’ importance, the proposed algorithm heuristically searches a subset of frames where the generated adversarial example has strong adversarial attack ability while keeps the perturbations lower than the given bound. Besides, to further boost the attack efficiency, we propose to generate the perturbations only on the salient regions of the selected frames. In this way, the generated perturbations are sparse in both temporal and spatial domains. Experimental results of attacking two mainstream video recognition methods on the UCF-101 dataset and the HMDB-51 dataset demonstrate that the proposed heuristic black-box adversarial attack method can significantly reduce the computation cost and lead to more than 28% reduction in query numbers for the untargeted attack on both datasets.
Tasks	Adversarial Attack, Video Recognition
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09449v1
PDF	https://arxiv.org/pdf/1911.09449v1.pdf
PWC	https://paperswithcode.com/paper/heuristic-black-box-adversarial-attacks-on
Repo
Framework

Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints


Title	Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints
Authors	Kuan Huang, Yingtao Zhang, H. D. Cheng, Ping Xing, Boyu Zhang
Abstract	Breast cancer is one of the most serious disease affecting women’s health. Due to low cost, portable, no radiation, and high efficiency, breast ultrasound (BUS) imaging is the most popular approach for diagnosing early breast cancer. However, ultrasound images are low resolution and poor quality. Thus, developing accurate detection system is a challenging task. In this paper, we propose a fully automatic segmentation algorithm consisting of two parts: fuzzy fully convolutional network and accurately fine-tuning post-processing based on breast anatomy constraints. In the first part, the image is preprocessed by contrast enhancement, and wavelet features are employed for image augmentation. A fuzzy membership function transforms the augmented BUS images into fuzzy domain. The features from convolutional layers are processed using fuzzy logic as well. The conditional random fields (CRFs) post-process the segmentation result. The location relation among the breast anatomy layers is utilized to improve the performance. The proposed method is applied to the dataset with 325 BUS images, and achieves state-of-art performance compared with that of existing methods with true positive rate 90.33%, false positive rate 9.00%, and intersection over union (IoU) 81.29% on tumor category, and overall intersection over union (mIoU) 80.47% over five categories: fat layer, mammary layer, muscle layer, background, and tumor.
Tasks	Image Augmentation, Semantic Segmentation
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06645v3
PDF	https://arxiv.org/pdf/1909.06645v3.pdf
PWC	https://paperswithcode.com/paper/fuzzy-semantic-segmentation-of-breast
Repo
Framework

SMART: Skeletal Motion Action Recognition aTtack


Title	SMART: Skeletal Motion Action Recognition aTtack
Authors	He Wang, Feixiang He, Zhexi Peng, Yongliang Yang, Tianjia Shao, Kun Zhou, David Hogg
Abstract	Adversarial attack has inspired great interest in computer vision, by showing that classification-based solutions are prone to imperceptible attack in many tasks. In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions. Our method involves an innovative perceptual loss which ensures the imperceptibility of the attack. Empirical studies demonstrate that SMART is effective in both white-box and black-box scenarios. Its generalizability is evidenced on a variety of action recognizers and datasets. Its versatility is shown in different attacking strategies. Its deceitfulness is proven in extensive perceptual studies. Finally, SMART shows that adversarial attack on 3D skeletal motion, one type of time-series data, is significantly different from traditional adversarial attack problems.
Tasks	Adversarial Attack, Time Series
Published	2019-11-16
URL	https://arxiv.org/abs/1911.07107v3
PDF	https://arxiv.org/pdf/1911.07107v3.pdf
PWC	https://paperswithcode.com/paper/smart-skeletal-motion-action-recognition
Repo
Framework

A Conditional Adversarial Network for Scene Flow Estimation


Title	A Conditional Adversarial Network for Scene Flow Estimation
Authors	Ravi Kumar Thakur, Snehasis Mukherjee
Abstract	The problem of Scene flow estimation in depth videos has been attracting attention of researchers of robot vision, due to its potential application in various areas of robotics. The conventional scene flow methods are difficult to use in reallife applications due to their long computational overhead. We propose a conditional adversarial network SceneFlowGAN for scene flow estimation. The proposed SceneFlowGAN uses loss function at two ends: both generator and descriptor ends. The proposed network is the first attempt to estimate scene flow using generative adversarial networks, and is able to estimate both the optical flow and disparity from the input stereo images simultaneously. The proposed method is experimented on a large RGB-D benchmark sceneflow dataset.
Tasks	Optical Flow Estimation, Scene Flow Estimation
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11163v1
PDF	http://arxiv.org/pdf/1904.11163v1.pdf
PWC	https://paperswithcode.com/paper/a-conditional-adversarial-network-for-scene
Repo
Framework

A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI


Title	A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
Authors	Erico Tjoa, Cuntai Guan
Abstract	Recently, artificial intelligence, especially machine learning has demonstrated remarkable performances in many tasks, from image processing to natural language processing, especially with the advent of deep learning. Along with research progress, machine learning has encroached into many different fields and disciplines. Some of them, such as the medical field, require high level of accountability, and thus transparency, which means we need to be able to explain machine decisions, predictions and justify their reliability. This requires greater interpretability, which often means we need to understand the mechanism underlying the algorithms. Unfortunately, the black-box nature of the deep learning is still unresolved, and many machine decisions are still poorly understood. We provide a review on interpretabilities suggested by different research works and categorize them. Also, within an exhaustive list of papers, we find that interpretability is often algorithm-centric, with few human-subject tests to verify whether proposed methods indeed enhance human interpretability. We explore further into interpretability in the medical field, illustrating the complexity of interpretability issue.
Tasks
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07374v3
PDF	https://arxiv.org/pdf/1907.07374v3.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-explainable-artificial
Repo
Framework

Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis of Expressive Speech


Title	Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis of Expressive Speech
Authors	Vatsal Aggarwal, Marius Cotescu, Nishant Prateek, Jaime Lorenzo-Trueba, Roberto Barra-Chicote
Abstract	We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art sequence-to-sequence based system with a Variational AutoEncoder (VAE) and a Householder Flow. The proposed system provides a 22% KL-divergence reduction while jointly improving perceptual metrics over state-of-the-art. At synthesis time we use one example of expressive style as a reference input to the encoder for generating any text in the desired style. Perceptual MUSHRA evaluations show that we can create a voice with a 9% relative naturalness improvement over standard Neural Text-to-Speech, while also improving the perceived emotional intensity (59 compared to the 55 of neutral speech).
Tasks	Speech Synthesis, Text-To-Speech Synthesis
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12760v2
PDF	https://arxiv.org/pdf/1911.12760v2.pdf
PWC	https://paperswithcode.com/paper/using-vaes-and-normalizing-flows-for-one-shot
Repo
Framework

Investigating bankruptcy prediction models in the presence of extreme class imbalance and multiple stages of economy


Title	Investigating bankruptcy prediction models in the presence of extreme class imbalance and multiple stages of economy
Authors	Sheikh Rabiul Islam, William Eberle, Sheikh K. Ghafoor, Sid C. Bundy, Douglas A. Talbert, Ambareen Siraj
Abstract	In the area of credit risk analytics, current Bankruptcy Prediction Models (BPMs) struggle with (a) the availability of comprehensive and real-world data sets and (b) the presence of extreme class imbalance in the data (i.e., very few samples for the minority class) that degrades the performance of the prediction model. Moreover, little research has compared the relative performance of well-known BPM’s on public datasets addressing the class imbalance problem. In this work, we apply eight classes of well-known BPMs, as suggested by a review of decades of literature, on a new public dataset named Freddie Mac Single-Family Loan-Level Dataset with resampling (i.e., adding synthetic minority samples) of the minority class to tackle class imbalance. Additionally, we apply some recent AI techniques (e.g., tree-based ensemble techniques) that demonstrate potentially better results on models trained with resampled data. In addition, from the analysis of 19 years (1999-2017) of data, we discover that models behave differently when presented with sudden changes in the economy (e.g., a global financial crisis) resulting in abrupt fluctuations in the national default rate. In summary, this study should aid practitioners/researchers in determining the appropriate model with respect to data that contains a class imbalance and various economic stages.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09858v1
PDF	https://arxiv.org/pdf/1911.09858v1.pdf
PWC	https://paperswithcode.com/paper/investigating-bankruptcy-prediction-models-in
Repo
Framework

Convolutional Neural Network on Semi-Regular Triangulated Meshes and its Application to Brain Image Data


Title	Convolutional Neural Network on Semi-Regular Triangulated Meshes and its Application to Brain Image Data
Authors	Caoqiang Liu, Hui Ji, Anqi Qiu
Abstract	We developed a convolution neural network (CNN) on semi-regular triangulated meshes whose vertices have 6 neighbours. The key blocks of the proposed CNN, including convolution and down-sampling, are directly defined in a vertex domain. By exploiting the ordering property of semi-regular meshes, the convolution is defined on a vertex domain with strong motivation from the spatial definition of classic convolution. Moreover, the down-sampling of a semi-regular mesh embedded in a 3D Euclidean space can achieve a down-sampling rate of 4, 16, 64, etc. We demonstrated the use of this vertex-based graph CNN for the classification of mild cognitive impairment (MCI) and Alzheimer’s disease (AD) based on 3169 MRI scans of the Alzheimer’s Disease Neuroimaging Initiative (ADNI). We compared the performance of the vertex-based graph CNN with that of the spectral graph CNN.
Tasks
Published	2019-03-21
URL	http://arxiv.org/abs/1903.08828v3
PDF	http://arxiv.org/pdf/1903.08828v3.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-network-on-semi-regular
Repo
Framework

Doubly-Robust Lasso Bandit


Title	Doubly-Robust Lasso Bandit
Authors	Gi-Soo Kim, Myunghee Cho Paik
Abstract	Contextual multi-armed bandit algorithms are widely used in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health. Most of the existing algorithms have regret proportional to a polynomial function of the context dimension, $d$. In many applications however, it is often the case that contexts are high-dimensional with only a sparse subset of size $s_0 (\ll d)$ being correlated with the reward. We consider the stochastic linear contextual bandit problem and propose a novel algorithm, namely the Doubly-Robust Lasso Bandit algorithm, which exploits the sparse structure of the regression parameter as in Lasso, while blending the doubly-robust technique used in missing data literature. The high-probability upper bound of the regret incurred by the proposed algorithm does not depend on the number of arms and scales with $\mathrm{log}(d)$ instead of a polynomial function of $d$. The proposed algorithm shows good performance when contexts of different arms are correlated and requires less tuning parameters than existing methods.
Tasks	Recommendation Systems
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11362v2
PDF	https://arxiv.org/pdf/1907.11362v2.pdf
PWC	https://paperswithcode.com/paper/doubly-robust-lasso-bandit
Repo
Framework

Multi-Instance Multi-Scale CNN for Medical Image Classification


Title	Multi-Instance Multi-Scale CNN for Medical Image Classification
Authors	Shaohua Li, Yong Liu, Xiuchao Sui, Cheng Chen, Gabriel Tjio, Daniel Shu Wei Ting, Rick Siow Mong Goh
Abstract	Deep learning for medical image classification faces three major challenges: 1) the number of annotated medical images for training are usually small; 2) regions of interest (ROIs) are relatively small with unclear boundaries in the whole medical images, and may appear in arbitrary positions across the x,y (and also z in 3D images) dimensions. However often only labels of the whole images are annotated, and localized ROIs are unavailable; and 3) ROIs in medical images often appear in varying sizes (scales). We approach these three challenges with a Multi-Instance Multi-Scale (MIMS) CNN: 1) We propose a multi-scale convolutional layer, which extracts patterns of different receptive fields with a shared set of convolutional kernels, so that scale-invariant patterns are captured by this compact set of kernels. As this layer contains only a small number of parameters, training on small datasets becomes feasible; 2) We propose a “top-k pooling” to aggregate the feature maps in varying scales from multiple spatial dimensions, allowing the model to be trained using weak annotations within the multiple instance learning (MIL) framework. Our method is shown to perform well on three classification tasks involving two 3D and two 2D medical image datasets.
Tasks	Image Classification, Multiple Instance Learning
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02413v4
PDF	https://arxiv.org/pdf/1907.02413v4.pdf
PWC	https://paperswithcode.com/paper/multi-instance-multi-scale-cnn-for-medical
Repo
Framework

Structural Analysis of Sparse Neural Networks


Title	Structural Analysis of Sparse Neural Networks
Authors	Julian Stier, Michael Granitzer
Abstract	Sparse Neural Networks regained attention due to their potential for mathematical and computational advantages. We give motivation to study Artificial Neural Networks (ANNs) from a network science perspective, provide a technique to embed arbitrary Directed Acyclic Graphs into ANNs and report study results on predicting the performance of image classifiers based on the structural properties of the networks’ underlying graph. Results could further progress neuroevolution and add explanations for the success of distinct architectures from a structural perspective.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07225v1
PDF	https://arxiv.org/pdf/1910.07225v1.pdf
PWC	https://paperswithcode.com/paper/structural-analysis-of-sparse-neural-networks
Repo
Framework

Fuzzy Inference Procedure for Intelligent and Automated Control of Refrigerant Charging


Title	Fuzzy Inference Procedure for Intelligent and Automated Control of Refrigerant Charging
Authors	Issam Damaj, Jean Saade, Hala Al-Faisal, Hassan Diab
Abstract	Fuzzy logic controllers are readily customizable in natural language terms and can effectively deal with nonlinearities and uncertainties in control systems. This paper presents an intelligent and automated fuzzy control procedure for the refrigerant charging of refrigerators. The elements that affect the experimental charging and the optimization of the performance of refrigerators are fuzzified and used in an inference model. The objective is to represent the intelligent behavior of a human tester and ultimately make the developed model available for the use in an automated data acquisition, monitoring, and decision-making system. The proposed system is capable of determining the needed amount of refrigerant in the shortest possible time. The system automates the refrigerant charging and performance testing of parallel units. The system is built using data acquisition systems from National Instruments and programmed under LabVIEW. The developed fuzzy models, and their testing results, are evaluated according to their compatibility with the principles that govern the intelligent behavior of human experts when performing the refrigerant-charging process. In addition, comparisons of the fuzzy models with classical inference models are presented. The obtained results confirm that the proposed fuzzy controllers outperform traditional crisp controllers and provide major test time and energy savings. The paper includes thorough discussions, analysis, and evaluation.
Tasks	Decision Making
Published	2019-11-02
URL	https://arxiv.org/abs/1911.02514v1
PDF	https://arxiv.org/pdf/1911.02514v1.pdf
PWC	https://paperswithcode.com/paper/fuzzy-inference-procedure-for-intelligent-and
Repo
Framework

An Online Stochastic Kernel Machine for Robust Signal Classification


Title	An Online Stochastic Kernel Machine for Robust Signal Classification
Authors	Raghu G. Raj
Abstract	We present a novel variation of online kernel machines in which we exploit a consensus based optimization mechanism to guide the evolution of decision functions drawn from a reproducing kernel Hilbert space, which efficiently models the observed stationary process.
Tasks
Published	2019-05-19
URL	https://arxiv.org/abs/1905.07686v2
PDF	https://arxiv.org/pdf/1905.07686v2.pdf
PWC	https://paperswithcode.com/paper/an-online-stochastic-kernel-machine-for
Repo
Framework