October 19, 2019

3117 words 15 mins read

Paper Group ANR 186

Bias Amplification in Artificial Intelligence Systems. Machine learning for prediction of extreme statistics in modulation instability. Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource. Gaussian Process Subset Scanning for Anomalous Pattern Detection in Non-iid Data. Learning Robust Heterogeneous Signal Features f …

Bias Amplification in Artificial Intelligence Systems


Title	Bias Amplification in Artificial Intelligence Systems
Authors	Kirsten Lloyd
Abstract	As Artificial Intelligence (AI) technologies proliferate, concern has centered around the long-term dangers of job loss or threats of machines causing harm to humans. All of this concern, however, detracts from the more pertinent and already existing threats posed by AI today: its ability to amplify bias found in training datasets, and swiftly impact marginalized populations at scale. Government and public sector institutions have a responsibility to citizens to establish a dialogue with technology developers and release thoughtful policy around data standards to ensure diverse representation in datasets to prevent bias amplification and ensure that AI systems are built with inclusion in mind.
Tasks
Published	2018-09-20
URL	http://arxiv.org/abs/1809.07842v1
PDF	http://arxiv.org/pdf/1809.07842v1.pdf
PWC	https://paperswithcode.com/paper/bias-amplification-in-artificial-intelligence
Repo
Framework

Machine learning for prediction of extreme statistics in modulation instability


Title	Machine learning for prediction of extreme statistics in modulation instability
Authors	Mikko Närhi, Lauri Salmela, Juha Toivonen, Cyril Billet, John M. Dudley, Goëry Genty
Abstract	A central area of research in nonlinear science is the study of instabilities that drive the emergence of extreme events. Unfortunately, experimental techniques for measuring such phenomena often provide only partial characterization. For example, real-time studies of instabilities in nonlinear fibre optics frequently use only spectral data, precluding detailed predictions about the associated temporal properties. Here, we show how Machine Learning can overcome this limitation by predicting statistics for the maximum intensity of temporal peaks in modulation instability based only on spectral measurements. Specifically, we train a neural network based Machine Learning model to correlate spectral and temporal properties of optical fibre modulation instability using data from numerical simulations, and we then use this model to predict the temporal probability distribution based on high-dynamic range spectral data from experiments. These results open novel perspectives in all systems exhibiting chaos and instability where direct time-domain observations are difficult.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1806.06121v1
PDF	http://arxiv.org/pdf/1806.06121v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-prediction-of-extreme
Repo
Framework

Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource


Title	Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource
Authors	Antonis Anastasopoulos, Marika Lekakou, Josep Quer, Eleni Zimianiti, Justin DeBenedetto, David Chiang
Abstract	Most work on part-of-speech (POS) tagging is focused on high resource languages, or examines low-resource and active learning settings through simulated studies. We evaluate POS tagging techniques on an actual endangered language, Griko. We present a resource that contains 114 narratives in Griko, along with sentence-level translations in Italian, and provides gold annotations for the test set. Based on a previously collected small corpus, we investigate several traditional methods, as well as methods that take advantage of monolingual data or project cross-lingual POS tags. We show that the combination of a semi-supervised method with cross-lingual transfer is more appropriate for this extremely challenging setting, with the best tagger achieving an accuracy of 72.9%. With an applied active learning scheme, which we use to collect sentence-level annotations over the test set, we achieve improvements of more than 21 percentage points.
Tasks	Active Learning, Cross-Lingual Transfer, Part-Of-Speech Tagging
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03757v1
PDF	http://arxiv.org/pdf/1806.03757v1.pdf
PWC	https://paperswithcode.com/paper/part-of-speech-tagging-on-an-endangered
Repo
Framework

Gaussian Process Subset Scanning for Anomalous Pattern Detection in Non-iid Data


Title	Gaussian Process Subset Scanning for Anomalous Pattern Detection in Non-iid Data
Authors	William Herlands, Edward McFowland III, Andrew Gordon Wilson, Daniel B. Neill
Abstract	Identifying anomalous patterns in real-world data is essential for understanding where, when, and how systems deviate from their expected dynamics. Yet methods that separately consider the anomalousness of each individual data point have low detection power for subtle, emerging irregularities. Additionally, recent detection techniques based on subset scanning make strong independence assumptions and suffer degraded performance in correlated data. We introduce methods for identifying anomalous patterns in non-iid data by combining Gaussian processes with novel log-likelihood ratio statistic and subset scanning techniques. Our approaches are powerful, interpretable, and can integrate information across multiple data streams. We illustrate their performance on numeric simulations and three open source spatiotemporal datasets of opioid overdose deaths, 311 calls, and storm reports.
Tasks	Gaussian Processes
Published	2018-04-04
URL	http://arxiv.org/abs/1804.01466v1
PDF	http://arxiv.org/pdf/1804.01466v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-subset-scanning-for
Repo
Framework

Learning Robust Heterogeneous Signal Features from Parallel Neural Network for Audio Sentiment Analysis


Title	Learning Robust Heterogeneous Signal Features from Parallel Neural Network for Audio Sentiment Analysis
Authors	Feiyang Chen, Ziqian Luo
Abstract	Audio Sentiment Analysis is a popular research area which extends the conventional text-based sentiment analysis to depend on the effectiveness of acoustic features extracted from speech. However, current progress on audio sentiment analysis mainly focuses on extracting homogeneous acoustic features or doesn’t fuse heterogeneous features effectively. In this paper, we propose an utterance-based deep neural network model, which has a parallel combination of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) based network, to obtain representative features termed Audio Sentiment Vector (ASV), that can maximally reflect sentiment information in an audio. Specifically, our model is trained by utterance-level labels and ASV can be extracted and fused creatively from two branches. In the CNN model branch, spectrum graphs produced by signals are fed as inputs while in the LSTM model branch, inputs include spectral features and cepstrum coefficient extracted from dependent utterances in audio. Besides, Bidirectional Long Short-Term Memory (BiLSTM) with attention mechanism is used for feature fusion. Extensive experiments have been conducted to show our model can recognize audio sentiment precisely and quickly, and demonstrate our ASV is better than traditional acoustic features or vectors extracted from other deep learning models. Furthermore, experimental results indicate that the proposed model outperforms the state-of-the-art approach by 9.33% on Multimodal Opinion-level Sentiment Intensity dataset (MOSI) dataset.
Tasks	Sentiment Analysis
Published	2018-11-20
URL	https://arxiv.org/abs/1811.08065v2
PDF	https://arxiv.org/pdf/1811.08065v2.pdf
PWC	https://paperswithcode.com/paper/utterance-based-audio-sentiment-analysis
Repo
Framework

Robust GANs against Dishonest Adversaries


Title	Robust GANs against Dishonest Adversaries
Authors	Zhi Xu, Chengtao Li, Stefanie Jegelka
Abstract	Robustness of deep learning models is a property that has recently gained increasing attention. We explore a notion of robustness for generative adversarial models that is pertinent to their internal interactive structure, and show that, perhaps surprisingly, the GAN in its original form is not robust. Our notion of robustness relies on a perturbed discriminator, or noisy, adversarial interference with its feedback. We explore, theoretically and empirically, the effect of model and training properties on this robustness. In particular, we show theoretical conditions for robustness that are supported by empirical evidence. We also test the effect of regularization. Our results suggest variations of GANs that are indeed more robust to noisy attacks and have more stable training behavior, requiring less regularization in general. Inspired by our theoretical results, we further extend our framework to obtain a class of models related to WGAN, with good empirical performance. Overall, our results suggest a new perspective on understanding and designing GAN models from the viewpoint of their internal robustness.
Tasks
Published	2018-02-27
URL	https://arxiv.org/abs/1802.09700v3
PDF	https://arxiv.org/pdf/1802.09700v3.pdf
PWC	https://paperswithcode.com/paper/robust-gans-against-dishonest-adversaries
Repo
Framework

Sequential anatomy localization in fetal echocardiography videos


Title	Sequential anatomy localization in fetal echocardiography videos
Authors	Arijit Patra, J. A. Noble
Abstract	Fetal heart motion is an important diagnostic indicator for structural detection and functional assessment of congenital heart disease. We propose an approach towards integrating deep convolutional and recurrent architectures that utilize localized spatial and temporal features of different anatomical substructures within a global spatiotemporal context for interpretation of fetal echocardiography videos. We formulate our task as a cardiac structure localization problem with convolutional architectures for aggregating global spatial context and detecting anatomical structures on spatial region proposals. This information is aggregated temporally by recurrent architectures to quantify the progressive motion patterns. We experimentally show that the resulting architecture combines anatomical landmark detection at the frame-level over multiple video sequences-with temporal progress of the associated anatomical motions to encode local spatiotemporal fetal heart dynamics and is validated on a real-world clinical dataset.
Tasks
Published	2018-10-28
URL	http://arxiv.org/abs/1810.11868v2
PDF	http://arxiv.org/pdf/1810.11868v2.pdf
PWC	https://paperswithcode.com/paper/sequential-anatomy-localization-in-fetal
Repo
Framework

Simultaneous Tensor Completion and Denoising by Noise Inequality Constrained Convex Optimization


Title	Simultaneous Tensor Completion and Denoising by Noise Inequality Constrained Convex Optimization
Authors	Tatsuya Yokota, Hidekata Hontani
Abstract	Tensor completion is a technique of filling missing elements of the incomplete data tensors. It being actively studied based on the convex optimization scheme such as nuclear-norm minimization. When given data tensors include some noises, the nuclear-norm minimization problem is usually converted to the nuclear-norm `regularization' problem which simultaneously minimize penalty and error terms with some trade-off parameter. However, the good value of trade-off is not easily determined because of the difference of two units and the data dependence. In the sense of trade-off tuning, the noisy tensor completion problem with the` noise inequality constraint’ is better choice than the `regularization’ because the good noise threshold can be easily bounded with noise standard deviation. In this study, we tackle to solve the convex tensor completion problems with two types of noise inequality constraints: Gaussian and Laplace distributions. The contributions of this study are follows: (1) New tensor completion and denoising models using tensor total variation and nuclear-norm are proposed which can be characterized as a generalization/extension of many past matrix and tensor completion models, (2) proximal mappings for noise inequalities are derived which are analytically computable with low computational complexity, (3) convex optimization algorithm is proposed based on primal-dual splitting framework, (4) new step-size adaptation method is proposed to accelerate the optimization, and (5) extensive experiments demonstrated the advantages of the proposed method for visual data retrieval such as for color images, movies, and 3D-volumetric data. \|
Tasks	Denoising
Published	2018-01-10
URL	http://arxiv.org/abs/1801.03299v1
PDF	http://arxiv.org/pdf/1801.03299v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-tensor-completion-and-denoising
Repo
Framework

PeerReview4All: Fair and Accurate Reviewer Assignment in Peer Review


Title	PeerReview4All: Fair and Accurate Reviewer Assignment in Peer Review
Authors	Ivan Stelmakh, Nihar B. Shah, Aarti Singh
Abstract	We consider the problem of automated assignment of papers to reviewers in conference peer review, with a focus on fairness and statistical accuracy. Our fairness objective is to maximize the review quality of the most disadvantaged paper, in contrast to the commonly used objective of maximizing the total quality over all papers. We design an assignment algorithm based on an incremental max-flow procedure that we prove is near-optimally fair. Our statistical accuracy objective is to ensure correct recovery of the papers that should be accepted. We provide a sharp minimax analysis of the accuracy of the peer-review process for a popular objective-score model as well as for a novel subjective-score model that we propose in the paper. Our analysis proves that our proposed assignment algorithm also leads to a near-optimal statistical accuracy. Finally, we design a novel experiment that allows for an objective comparison of various assignment algorithms, and overcomes the inherent difficulty posed by the absence of a ground truth in experiments on peer-review. The results of this experiment as well as of other experiments on synthetic and real data corroborate the theoretical guarantees of our algorithm.
Tasks
Published	2018-06-16
URL	https://arxiv.org/abs/1806.06237v2
PDF	https://arxiv.org/pdf/1806.06237v2.pdf
PWC	https://paperswithcode.com/paper/peerreview4all-fair-and-accurate-reviewer
Repo
Framework

Multivariate Extension of Matrix-based Renyi’s α-order Entropy Functional


Title	Multivariate Extension of Matrix-based Renyi’s α-order Entropy Functional
Authors	Shujian Yu, Luis Gonzalo Sanchez Giraldo, Robert Jenssen, Jose C. Principe
Abstract	The matrix-based Renyi’s \alpha-order entropy functional was recently introduced using the normalized eigenspectrum of a Hermitian matrix of the projected data in a reproducing kernel Hilbert space (RKHS). However, the current theory in the matrix-based Renyi’s \alpha-order entropy functional only defines the entropy of a single variable or mutual information between two random variables. In information theory and machine learning communities, one is also frequently interested in multivariate information quantities, such as the multivariate joint entropy and different interactive quantities among multiple variables. In this paper, we first define the matrix-based Renyi’s \alpha-order joint entropy among multiple variables. We then show how this definition can ease the estimation of various information quantities that measure the interactions among multiple variables, such as interactive information and total correlation. We finally present an application to feature selection to show how our definition provides a simple yet powerful way to estimate a widely-acknowledged intractable quantity from data. A real example on hyperspectral image (HSI) band selection is also provided.
Tasks	Feature Selection
Published	2018-08-23
URL	https://arxiv.org/abs/1808.07912v3
PDF	https://arxiv.org/pdf/1808.07912v3.pdf
PWC	https://paperswithcode.com/paper/multivariate-extension-of-matrix-based-renyis
Repo
Framework

Reinforced Auto-Zoom Net: Towards Accurate and Fast Breast Cancer Segmentation in Whole-slide Images


Title	Reinforced Auto-Zoom Net: Towards Accurate and Fast Breast Cancer Segmentation in Whole-slide Images
Authors	Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Zeya Wang, Wei Dai, Eric P. Xing
Abstract	Convolutional neural networks have led to significant breakthroughs in the domain of medical image analysis. However, the task of breast cancer segmentation in whole-slide images (WSIs) is still underexplored. WSIs are large histopathological images with extremely high resolution. Constrained by the hardware and field of view, using high-magnification patches can slow down the inference process and using low-magnification patches can cause the loss of information. In this paper, we aim to achieve two seemingly conflicting goals for breast cancer segmentation: accurate and fast prediction. We propose a simple yet efficient framework Reinforced Auto-Zoom Net (RAZN) to tackle this task. Motivated by the zoom-in operation of a pathologist using a digital microscope, RAZN learns a policy network to decide whether zooming is required in a given region of interest. Because the zoom-in action is selective, RAZN is robust to unbalanced and noisy ground truth labels and can efficiently reduce overfitting. We evaluate our method on a public breast cancer dataset. RAZN outperforms both single-scale and multi-scale baseline approaches, achieving better accuracy at low inference cost.
Tasks
Published	2018-07-29
URL	http://arxiv.org/abs/1807.11113v1
PDF	http://arxiv.org/pdf/1807.11113v1.pdf
PWC	https://paperswithcode.com/paper/reinforced-auto-zoom-net-towards-accurate-and
Repo
Framework

Automatic Image Stylization Using Deep Fully Convolutional Networks


Title	Automatic Image Stylization Using Deep Fully Convolutional Networks
Authors	Feida Zhu, Yizhou Yu
Abstract	Color and tone stylization strives to enhance unique themes with artistic color and tone adjustments. It has a broad range of applications from professional image postprocessing to photo sharing over social networks. Mainstream photo enhancement softwares provide users with predefined styles, which are often hand-crafted through a trial-and-error process. Such photo adjustment tools lack a semantic understanding of image contents and the resulting global color transform limits the range of artistic styles it can represent. On the other hand, stylistic enhancement needs to apply distinct adjustments to various semantic regions. Such an ability enables a broader range of visual styles. In this paper, we propose a novel deep learning architecture for automatic image stylization, which learns local enhancement styles from image pairs. Our deep learning architecture is an end-to-end deep fully convolutional network performing semantics-aware feature extraction as well as automatic image adjustment prediction. Image stylization can be efficiently accomplished with a single forward pass through our deep network. Experiments on existing datasets for image stylization demonstrate the effectiveness of our deep learning architecture.
Tasks	Image Stylization
Published	2018-11-27
URL	http://arxiv.org/abs/1811.10872v1
PDF	http://arxiv.org/pdf/1811.10872v1.pdf
PWC	https://paperswithcode.com/paper/automatic-image-stylization-using-deep-fully
Repo
Framework

Multi-scale Neural Networks for Retinal Blood Vessels Segmentation


Title	Multi-scale Neural Networks for Retinal Blood Vessels Segmentation
Authors	Boheng Zhang, Shenglei Huang, Shaohan Hu
Abstract	Existing supervised approaches didn’t make use of the low-level features which are actually effective to this task. And another deficiency is that they didn’t consider the relation between pixels, which means effective features are not extracted. In this paper, we proposed a novel convolutional neural network which make sufficient use of low-level features together with high-level features and involves atrous convolution to get multi-scale features which should be considered as effective features. Our model is tested on three standard benchmarks - DRIVE, STARE, and CHASE databases. The results presents that our model significantly outperforms existing approaches in terms of accuracy, sensitivity, specificity, the area under the ROC curve and the highest prediction speed. Our work provides evidence of the power of wide and deep neural networks in retinal blood vessels segmentation task which could be applied on other medical images tasks.
Tasks
Published	2018-04-11
URL	http://arxiv.org/abs/1804.04206v1
PDF	http://arxiv.org/pdf/1804.04206v1.pdf
PWC	https://paperswithcode.com/paper/multi-scale-neural-networks-for-retinal-blood
Repo
Framework

A New COLD Feature based Handwriting Analysis for Ethnicity/Nationality Identification


Title	A New COLD Feature based Handwriting Analysis for Ethnicity/Nationality Identification
Authors	Sauradip Nag, Palaiahnakote Shivakumara, Wu Yirui, Umapada Pal, Tong Lu
Abstract	Identifying crime for forensic investigating teams when crimes involve people of different nationals is challenging. This paper proposes a new method for ethnicity (nationality) identification based on Cloud of Line Distribution (COLD) features of handwriting components. The proposed method, at first, explores tangent angle for the contour pixels in each row and the mean of intensity values of each row in an image for segmenting text lines. For segmented text lines, we use tangent angle and direction of base lines to remove rule lines in the image. We use polygonal approximation for finding dominant points for contours of edge components. Then the proposed method connects the nearest dominant points of every dominant point, which results in line segments of dominant point pairs. For each line segment, the proposed method estimates angle and length, which gives a point in polar domain. For all the line segments, the proposed method generates dense points in polar domain, which results in COLD distribution. As character component shapes change, according to nationals, the shape of the distribution changes. This observation is extracted based on distance from pixels of distribution to Principal Axis of the distribution. Then the features are subjected to an SVM classifier for identifying nationals. Experiments are conducted on a complex dataset, which show the proposed method is effective and outperforms the existing method
Tasks
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07072v1
PDF	http://arxiv.org/pdf/1806.07072v1.pdf
PWC	https://paperswithcode.com/paper/a-new-cold-feature-based-handwriting-analysis
Repo
Framework

Lightly-supervised Representation Learning with Global Interpretability


Title	Lightly-supervised Representation Learning with Global Interpretability
Authors	Marco A. Valenzuela-Escárcega, Ajay Nagesh, Mihai Surdeanu
Abstract	We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction patterns, with the robust learning approaches proposed in representation learning. Our algorithm iteratively learns custom embeddings for both the multi-word entities to be extracted and the patterns that match them from a few example entities per category. We demonstrate that this representation-based approach outperforms three other state-of-the-art bootstrapping approaches on two datasets: CoNLL-2003 and OntoNotes. Additionally, using these embeddings, our approach outputs a globally-interpretable model consisting of a decision list, by ranking patterns based on their proximity to the average entity embedding in a given class. We show that this interpretable model performs close to our complete bootstrapping model, proving that representation learning can be used to produce interpretable models with small loss in performance.
Tasks	Representation Learning
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11545v1
PDF	http://arxiv.org/pdf/1805.11545v1.pdf
PWC	https://paperswithcode.com/paper/lightly-supervised-representation-learning
Repo
Framework