January 25, 2020

3083 words 15 mins read

Paper Group ANR 1684

Unsupervised Method to Localize Masses in Mammograms. Aligning Biomedical Metadata with Ontologies Using Clustering and Embeddings. Interpretable Text Classification Using CNN and Max-pooling. Time Series Imputation. Predicting Specificity in Classroom Discussion. Information Bottleneck and its Applications in Deep Learning. Segmentation is All You …

Unsupervised Method to Localize Masses in Mammograms


Title	Unsupervised Method to Localize Masses in Mammograms
Authors	Bilal Ahmed Lodhi
Abstract	Breast cancer is one of the most common and prevalent type of cancer that mainly affects the women population. chances of effective treatment increases with early diagnosis. Mammography is considered one of the effective and proven techniques for early diagnosis of breast cancer. Tissues around masses look identical in mammogram, which makes automatic detection process a very challenging task. They are indistinguishable from the surrounding parenchyma. In this paper, we present an efficient and automated approach to segment masses in mammograms. The proposed method uses hierarchical clustering to isolate the salient area, and then features are extracted to reject false detection. We applied our method on two popular publicly available datasets (mini-MIAS and DDSM). A total of 56 images from mini-mias database, and 76 images from DDSM were randomly selected. Results are explained in-terms of ROC (Receiver Operating Characteristics) curves and compared with the other techniques. Experimental results demonstrate the efficiency and advantages of the proposed system in automatic mass identification in mammograms.
Tasks
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06044v1
PDF	http://arxiv.org/pdf/1904.06044v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-method-to-localize-masses-in
Repo
Framework

Aligning Biomedical Metadata with Ontologies Using Clustering and Embeddings


Title	Aligning Biomedical Metadata with Ontologies Using Clustering and Embeddings
Authors	Rafael S. Gonçalves, Maulik R. Kamdar, Mark A. Musen
Abstract	The metadata about scientific experiments published in online repositories have been shown to suffer from a high degree of representational heterogeneity—there are often many ways to represent the same type of information, such as a geographical location via its latitude and longitude. To harness the potential that metadata have for discovering scientific data, it is crucial that they be represented in a uniform way that can be queried effectively. One step toward uniformly-represented metadata is to normalize the multiple, distinct field names used in metadata (e.g., lat lon, lat and long) to describe the same type of value. To that end, we present a new method based on clustering and embeddings (i.e., vector representations of words) to align metadata field names with ontology terms. We apply our method to biomedical metadata by generating embeddings for terms in biomedical ontologies from the BioPortal repository. We carried out a comparative study between our method and the NCBO Annotator, which revealed that our method yields more and substantially better alignments between metadata and ontology terms.
Tasks
Published	2019-03-19
URL	https://arxiv.org/abs/1903.08206v2
PDF	https://arxiv.org/pdf/1903.08206v2.pdf
PWC	https://paperswithcode.com/paper/aligning-biomedical-metadata-with-ontologies
Repo
Framework

Interpretable Text Classification Using CNN and Max-pooling


Title	Interpretable Text Classification Using CNN and Max-pooling
Authors	Hao Cheng, Xiaoqing Yang, Zang Li, Yanghua Xiao, Yucheng Lin
Abstract	Deep neural networks have been widely used in text classification. However, it is hard to interpret the neural models due to the complicate mechanisms. In this work, we study the interpretability of a variant of the typical text classification model which is based on convolutional operation and max-pooling layer. Two mechanisms: convolution attribution and n-gram feature analysis are proposed to analyse the process procedure for the CNN model. The interpretability of the model is reflected by providing posterior interpretation for neural network predictions. Besides, a multi-sentence strategy is proposed to enable the model to beused in multi-sentence situation without loss of performance and interpret ability. We evaluate the performance of the model on several classification tasks and justify the interpretable performance with some case studies.
Tasks	Text Classification
Published	2019-10-14
URL	https://arxiv.org/abs/1910.11236v1
PDF	https://arxiv.org/pdf/1910.11236v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-text-classification-using-cnn
Repo
Framework

Time Series Imputation


Title	Time Series Imputation
Authors	Samuel Arcadinho, Paulo Mateus
Abstract	Multivariate time series is a very active topic in the research community and many machine learning tasks are being used in order to extract information from this type of data. However, in real-world problems data has missing values, which may difficult the application of machine learning techniques to extract information. In this paper we focus on the task of imputation of time series. Many imputation methods for time series are based on regression methods. Unfortunately, these methods perform poorly when the variables are categorical. To address this case, we propose a new imputation method based on Expectation Maximization over dynamic Bayesian networks. The approach is assessed with synthetic and real data, and it outperforms several state-of-the art methods.
Tasks	Imputation, Time Series
Published	2019-03-22
URL	http://arxiv.org/abs/1903.09732v1
PDF	http://arxiv.org/pdf/1903.09732v1.pdf
PWC	https://paperswithcode.com/paper/time-series-imputation
Repo
Framework

Predicting Specificity in Classroom Discussion


Title	Predicting Specificity in Classroom Discussion
Authors	Luca Lugini, Diane Litman
Abstract	High quality classroom discussion is important to student development, enhancing abilities to express claims, reason about other students’ claims, and retain information for longer periods of time. Previous small-scale studies have shown that one indicator of classroom discussion quality is specificity. In this paper we tackle the problem of predicting specificity for classroom discussions. We propose several methods and feature sets capable of outperforming the state of the art in specificity prediction. Additionally, we provide a set of meaningful, interpretable features that can be used to analyze classroom discussions at a pedagogical level.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01462v1
PDF	https://arxiv.org/pdf/1909.01462v1.pdf
PWC	https://paperswithcode.com/paper/predicting-specificity-in-classroom-1
Repo
Framework

Information Bottleneck and its Applications in Deep Learning


Title	Information Bottleneck and its Applications in Deep Learning
Authors	Hassan Hafez-Kolahi, Shohreh Kasaei
Abstract	Information Theory (IT) has been used in Machine Learning (ML) from early days of this field. In the last decade, advances in Deep Neural Networks (DNNs) have led to surprising improvements in many applications of ML. The result has been a paradigm shift in the community toward revisiting previous ideas and applications in this new framework. Ideas from IT are no exception. One of the ideas which is being revisited by many researchers in this new era, is Information Bottleneck (IB); a formulation of information extraction based on IT. The IB is promising in both analyzing and improving DNNs. The goal of this survey is to review the IB concept and demonstrate its applications in deep learning. The information theoretic nature of IB, makes it also a good candidate in showing the more general concept of how IT can be used in ML. Two important concepts are highlighted in this narrative on the subject, i) the concise and universal view that IT provides on seemingly unrelated methods of ML, demonstrated by explaining how IB relates to minimal sufficient statistics, stochastic gradient descent, and variational auto-encoders, and ii) the common technical mistakes and problems caused by applying ideas from IT, which is discussed by a careful study of some recent methods suffering from them.
Tasks
Published	2019-04-07
URL	http://arxiv.org/abs/1904.03743v1
PDF	http://arxiv.org/pdf/1904.03743v1.pdf
PWC	https://paperswithcode.com/paper/information-bottleneck-and-its-applications
Repo
Framework

Segmentation is All You Need


Title	Segmentation is All You Need
Authors	Zehua Cheng, Yuxiang Wu, Zhenghua Xu, Thomas Lukasiewicz, Weiyang Wang
Abstract	Region proposal mechanisms are essential for existing deep learning approaches to object detection in images. Although they can generally achieve a good detection performance under normal circumstances, their recall in a scene with extreme cases is unacceptably low. This is mainly because bounding box annotations contain much environment noise information, and non-maximum suppression (NMS) is required to select target boxes. Therefore, in this paper, we propose the first anchor-free and NMS-free object detection model called weakly supervised multimodal annotation segmentation (WSMA-Seg), which utilizes segmentation models to achieve an accurate and robust object detection without NMS. In WSMA-Seg, multimodal annotations are proposed to achieve an instance-aware segmentation using weakly supervised bounding boxes; we also develop a run-data-based following algorithm to trace contours of objects. In addition, we propose a multi-scale pooling segmentation (MSP-Seg) as the underlying segmentation model of WSMA-Seg to achieve a more accurate segmentation and to enhance the detection accuracy of WSMA-Seg. Experimental results on multiple datasets show that the proposed WSMA-Seg approach outperforms the state-of-the-art detectors.
Tasks	Face Detection, Head Detection, Object Detection, Robust Object Detection
Published	2019-04-30
URL	https://arxiv.org/abs/1904.13300v3
PDF	https://arxiv.org/pdf/1904.13300v3.pdf
PWC	https://paperswithcode.com/paper/segmentation-is-all-you-need
Repo
Framework

Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data


Title	Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data
Authors	Onorina Kovalenko, Vladislav Golyanik, Jameel Malik, Ahmed Elhayek, Didier Stricker
Abstract	Recovery of articulated 3D structure from 2D observations is a challenging computer vision problem with many applications. Current learning-based approaches achieve state-of-the-art accuracy on public benchmarks but are restricted to specific types of objects and motions covered by the training datasets. Model-based approaches do not rely on training data but show lower accuracy on these datasets. In this paper, we introduce a model-based method called Structure from Articulated Motion (SfAM), which can recover multiple object and motion types without training on extensive data collections. At the same time, it performs on par with learning-based state-of-the-art approaches on public benchmarks and outperforms previous non-rigid structure from motion (NRSfM) methods. SfAM is built upon a general-purpose NRSfM technique while integrating a soft spatio-temporal constraint on the bone lengths. We use alternating optimization strategy to recover optimal geometry (i.e., bone proportions) together with 3D joint positions by enforcing the bone lengths consistency over a series of frames. SfAM is highly robust to noisy 2D annotations, generalizes to arbitrary objects and does not rely on training data, which is shown in extensive experiments on public benchmarks and real video sequences. We believe that it brings a new perspective on the domain of monocular 3D recovery of articulated structures, including human motion capture.
Tasks	3D Reconstruction, Motion Capture
Published	2019-05-12
URL	https://arxiv.org/abs/1905.04789v2
PDF	https://arxiv.org/pdf/1905.04789v2.pdf
PWC	https://paperswithcode.com/paper/structure-from-articulated-motion-an-accurate
Repo
Framework

The Bitwise Hashing Trick for Personalized Search


Title	The Bitwise Hashing Trick for Personalized Search
Authors	Braddock Gaskill
Abstract	Many real world problems require fast and efficient lexical comparison of large numbers of short text strings. Search personalization is one such domain. We introduce the use of feature bit vectors using the hashing trick for improving relevance in personalized search and other personalization applications. We present results of several lexical hashing and comparison methods. These methods are applied to a user’s historical behavior and are used to predict future behavior. Using a single bit per dimension instead of floating point results in an order of magnitude decrease in data structure size, while preserving or even improving quality. We use real data to simulate a search personalization task. A simple method for combining bit vectors demonstrates an order of magnitude improvement in compute time on the task with only a small decrease in accuracy.
Tasks
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08646v1
PDF	https://arxiv.org/pdf/1910.08646v1.pdf
PWC	https://paperswithcode.com/paper/the-bitwise-hashing-trick-for-personalized
Repo
Framework

Towards a Robust Classifier: An MDL-Based Method for Generating Adversarial Examples


Title	Towards a Robust Classifier: An MDL-Based Method for Generating Adversarial Examples
Authors	Behzad Asadi, Vijay Varadharajan
Abstract	We address the problem of adversarial examples in machine learning where an adversary tries to misguide a classifier by making functionality-preserving modifications to original samples. We assume a black-box scenario where the adversary has access to only the feature set, and the final hard-decision output of the classifier. We propose a method to generate adversarial examples using the minimum description length (MDL) principle. Our final aim is to improve the robustness of the classifier by considering generated examples in rebuilding the classifier. We evaluate our method for the application of static malware detection in portable executable (PE) files. We consider API calls of PE files as their distinguishing features where the feature vector is a binary vector representing the presence-absence of API calls. In our method, we first create a dataset of benign samples by querying the target classifier. We next construct a code table of frequent patterns for the compression of this dataset using the MDL principle. We finally generate an adversarial example corresponding to a malware sample by selecting and adding a pattern from the benign code table to the malware sample. The selected pattern is the one that minimizes the length of the compressed adversarial example given the code table. This modification preserves the functionalities of the original malware sample as all original API calls are kept, and only some new API calls are added. Considering a neural network, we show that the evasion rate is 78.24 percent for adversarial examples compared to 8.16 percent for original malware samples. This shows the effectiveness of our method in generating examples that need to be considered in rebuilding the classifier.
Tasks	Malware Detection
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05945v1
PDF	https://arxiv.org/pdf/1912.05945v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-robust-classifier-an-mdl-based
Repo
Framework

Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials


Title	Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials
Authors	Yabo Dan, Yong Zhao, Xiang Li, Shaobo Li, Ming Hu, Jianjun Hu
Abstract	A major challenge in materials design is how to efficiently search the vast chemical design space to find the materials with desired properties. One effective strategy is to develop sampling algorithms that can exploit both explicit chemical knowledge and implicit composition rules embodied in the large materials database. Here, we propose a generative machine learning model (MatGAN) based on a generative adversarial network (GAN) for efficient generation of new hypothetical inorganic materials. Trained with materials from the ICSD database, our GAN model can generate hypothetical materials not existing in the training dataset, reaching a novelty of 92.53% when generating 2 million samples. The percentage of chemically valid (charge neutral and electronegativity balanced) samples out of all generated ones reaches 84.5% by our GAN when trained with materials from ICSD even though no such chemical rules are explicitly enforced in our GAN model, indicating its capability to learn implicit chemical composition rules. Our algorithm could be used to speed up inverse design or computational screening of inorganic materials.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05020v1
PDF	https://arxiv.org/pdf/1911.05020v1.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-networks-gan-based
Repo
Framework

CleanML: A Benchmark for Joint Data Cleaning and Machine Learning [Experiments and Analysis]


Title	CleanML: A Benchmark for Joint Data Cleaning and Machine Learning [Experiments and Analysis]
Authors	Peng Li, Xi Rao, Jennifer Blase, Yue Zhang, Xu Chu, Ce Zhang
Abstract	It is widely recognized that the data quality affects machine learning (ML) model performances, and data scientists spend considerable amount of time on data cleaning before model training. However, to date, there does not exist a rigorous study on how exactly does cleaning affect ML — ML community usually focuses on the effects of specific types of noises of certain distributions (e.g., mislabels) on certain ML models, while database (DB) community has been mostly studying the problem of data cleaning alone without considering how data is consumed by downstream analytics. We propose the CleanML benchmark that systematically investigates the impact of data cleaning on downstream ML models. The CleanML benchmark currently includes 13 real-world datasets with real errors, five common error types, and seven different ML models. To ensure that our findings are statistically significant, CleanML carefully controls the randomness in ML experiments using statistical hypothesis testing, and also uses the Benjamini-Yekutieli (BY) procedure to control potential false discoveries due to many hypotheses in the benchmark. We obtain many interesting and non-trivial insights, and identify multiple open research directions. We also release the benchmark and hope to invite future studies on the important problems of joint data cleaning and ML.
Tasks
Published	2019-04-20
URL	http://arxiv.org/abs/1904.09483v2
PDF	http://arxiv.org/pdf/1904.09483v2.pdf
PWC	https://paperswithcode.com/paper/cleanml-a-benchmark-for-joint-data-cleaning
Repo
Framework

Logitron: Perceptron-augmented classification model based on an extended logistic loss function


Title	Logitron: Perceptron-augmented classification model based on an extended logistic loss function
Authors	Hyenkyun Woo
Abstract	Classification is the most important process in data analysis. However, due to the inherent non-convex and non-smooth structure of the zero-one loss function of the classification model, various convex surrogate loss functions such as hinge loss, squared hinge loss, logistic loss, and exponential loss are introduced. These loss functions have been used for decades in diverse classification models, such as SVM (support vector machine) with hinge loss, logistic regression with logistic loss, and Adaboost with exponential loss and so on. In this work, we present a Perceptron-augmented convex classification framework, {\it Logitron}. The loss function of it is a smoothly stitched function of the extended logistic loss with the famous Perceptron loss function. The extended logistic loss function is a parameterized function established based on the extended logarithmic function and the extended exponential function. The main advantage of the proposed Logitron classification model is that it shows the connection between SVM and logistic regression via polynomial parameterization of the loss function. In more details, depending on the choice of parameters, we have the Hinge-Logitron which has the generalized $k$-th order hinge-loss with an additional $k$-th root stabilization function and the Logistic-Logitron which has a logistic-like loss function with relatively large $k$. Interestingly, even $k=-1$, Hinge-Logitron satisfies the classification-calibration condition and shows reasonable classification performance with low computational cost. The numerical experiment in the linear classifier framework demonstrates that Hinge-Logitron with $k=4$ (the fourth-order SVM with the fourth root stabilization function) outperforms logistic regression, SVM, and other Logitron models in terms of classification accuracy.
Tasks	Calibration
Published	2019-04-05
URL	http://arxiv.org/abs/1904.02958v1
PDF	http://arxiv.org/pdf/1904.02958v1.pdf
PWC	https://paperswithcode.com/paper/logitron-perceptron-augmented-classification
Repo
Framework

Implicit Deep Learning


Title	Implicit Deep Learning
Authors	Laurent El Ghaoui, Fangda Gu, Bertrand Travacca, Armin Askari
Abstract	We define a new class of “implicit” deep learning prediction rules that generalize the recursive rules of feedforward neural networks. These models are based on the solution of a fixed-point equation involving a single a vector of hidden features, which is thus only implicitly defined. The new framework greatly simplifies the notation of deep learning, and opens up new possibilities, in terms of novel architectures and algorithms, robustness analysis and design, interpretability, sparsity, and network architecture optimization.
Tasks
Published	2019-08-17
URL	https://arxiv.org/abs/1908.06315v3
PDF	https://arxiv.org/pdf/1908.06315v3.pdf
PWC	https://paperswithcode.com/paper/implicit-deep-learning
Repo
Framework

Spike-and-wave epileptiform discharge pattern detection based on Kendall’s Tau-b coefficient


Title	Spike-and-wave epileptiform discharge pattern detection based on Kendall’s Tau-b coefficient
Authors	Antonio Quintero-Rincón, Catalina Carenzo, Joaquín Ems, Lourdes Hirschson, Valeria Muro, Carlos D’Giano
Abstract	Epilepsy is an important public health issue. An appropriate epileptiform discharge pattern detection of this neurological disease is a typical problem in biomedical engineering. In this paper, a new method is proposed for spike-and-wave discharge pattern detection based on Kendall’s Tau-b coefficient. The proposed approach is demonstrated on a real dataset containing spike-and-wave discharge signals, where our performance is evaluated in terms of high Specificity, rule in (SpPIn) with 94% for patient-specific spike-and-wave discharge detection and 83% for a general spike-and-wave discharge detection.
Tasks
Published	2019-11-29
URL	https://arxiv.org/abs/1911.13018v1
PDF	https://arxiv.org/pdf/1911.13018v1.pdf
PWC	https://paperswithcode.com/paper/spike-and-wave-epileptiform-discharge-pattern
Repo
Framework