January 30, 2020

3342 words 16 mins read

Paper Group ANR 284

Architectural Tricks for Deep Learning in Remote Photoplethysmography. Semantically Driven Auto-completion. Infant Mortality Prediction using Birth Certificate Data. Pre-train, Interact, Fine-tune: A Novel Interaction Representation for Text Classification. Deep Plug-and-Play Prior for Parallel MRI Reconstruction. Improved Reinforcement Learning th …

Architectural Tricks for Deep Learning in Remote Photoplethysmography


Title	Architectural Tricks for Deep Learning in Remote Photoplethysmography
Authors	Mikhail Kopeliovich, Yuriy Mironenko, Mikhail Petrushan
Abstract	Architectural improvements are studied for convolutional network performing estimation of heart rate (HR) values on color signal patches. Color signals are time series of color components averaged over facial regions recorded by webcams in two scenarios: Stationary (without motion of a person) and Mixed Motion (different motion patterns of a person). HR estimation problem is addressed as a classification task, where classes correspond to different heart rate values within the admissible range of [40; 125] bpm. Both adding convolutional filtering layers after fully connected layers and involving combined loss function where first component is a cross entropy and second is a squared error between the network output and smoothed one-hot vector, lead to better performance of HR estimation model in Stationary and Mixed Motion scenarios.
Tasks	Time Series
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02202v1
PDF	https://arxiv.org/pdf/1911.02202v1.pdf
PWC	https://paperswithcode.com/paper/architectural-tricks-for-deep-learning-in
Repo
Framework

Semantically Driven Auto-completion


Title	Semantically Driven Auto-completion
Authors	Konstantine Arkoudas, Mohamed Yahya
Abstract	The Bloomberg Terminal has been a leading source of financial data and analytics for over 30 years. Through its thousands of functions, the Terminal allows its users to query and run analytics over a large array of data sources, including structured, semi-structured, and unstructured data; as well as plot charts, set up event-driven alerts and triggers, create interactive maps, exchange information via instant and email-style messages, and so on. To improve user experience, we have been building question answering systems that can understand a wide range of natural language constructions for various domains that are of fundamental interest to our users. Such natural language interfaces, while exceedingly helpful to users, introduce a number of usability challenges of their own. We tackle some of these challenges through auto-completion for query formulation. A distinguishing mark of our auto-complete systems is that they are based on and guided by corresponding semantic parsing systems. We describe the auto-complete problem as it arises in this setting, the novel algorithms that we use to solve it, and report on the quality of the results and the efficiency of our approach.
Tasks	Question Answering, Semantic Parsing
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09450v1
PDF	https://arxiv.org/pdf/1906.09450v1.pdf
PWC	https://paperswithcode.com/paper/semantically-driven-auto-completion
Repo
Framework

Infant Mortality Prediction using Birth Certificate Data


Title	Infant Mortality Prediction using Birth Certificate Data
Authors	Antonia Saravanou, Clemens Noelke, Nicholas Huntington, Dolores Acevedo-Garcia, Dimitrios Gunopulos
Abstract	The Infant Mortality Rate (IMR) is the number of infants per 1000 that do not survive until their first birthday. It is an important metric providing information about infant health but it also measures the society’s general health status. Despite the high level of prosperity in the U.S.A., the country’s IMR is higher than that of many other developed countries. Additionally, the U.S.A. exhibits persistent inequalities in the IMR across different racial and ethnic groups. In this paper, we study the infant mortality prediction using features extracted from birth certificates. We are interested in training classification models to decide whether an infant will survive or not. We focus on exploring and understanding the importance of features in subsets of the population; we compare models trained for individual races to general models. Our evaluation shows that our methodology outperforms standard classification methods used by epidemiology researchers.
Tasks	Epidemiology, Mortality Prediction
Published	2019-07-21
URL	https://arxiv.org/abs/1907.08968v2
PDF	https://arxiv.org/pdf/1907.08968v2.pdf
PWC	https://paperswithcode.com/paper/infant-mortality-prediction-using-birth
Repo
Framework

Pre-train, Interact, Fine-tune: A Novel Interaction Representation for Text Classification


Title	Pre-train, Interact, Fine-tune: A Novel Interaction Representation for Text Classification
Authors	Jianming Zheng, Fei Cai, Honghui Chen, Maarten de Rijke
Abstract	Text representation can aid machines in understanding text. Previous work on text representation often focuses on the so-called forward implication, i.e., preceding words are taken as the context of later words for creating representations, thus ignoring the fact that the semantics of a text segment is a product of the mutual implication of words in the text: later words contribute to the meaning of preceding words. We introduce the concept of interaction and propose a two-perspective interaction representation, that encapsulates a local and a global interaction representation. Here, a local interaction representation is one that interacts among words with parent-children relationships on the syntactic trees and a global interaction interpretation is one that interacts among all the words in a sentence. We combine the two interaction representations to develop a Hybrid Interaction Representation (HIR). Inspired by existing feature-based and fine-tuning-based pretrain-finetuning approaches to language models, we integrate the advantages of feature-based and fine-tuning-based methods to propose the Pre-train, Interact, Fine-tune (PIF) architecture. We evaluate our proposed models on five widely-used datasets for text classification tasks. Our ensemble method, outperforms state-of-the-art baselines with improvements ranging from 2.03% to 3.15% in terms of error rate. In addition, we find that, the improvements of PIF against most state-of-the-art methods is not affected by increasing of the length of the text.
Tasks	Text Classification
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11824v1
PDF	https://arxiv.org/pdf/1909.11824v1.pdf
PWC	https://paperswithcode.com/paper/pre-train-interact-fine-tune-a-novel
Repo
Framework

Deep Plug-and-Play Prior for Parallel MRI Reconstruction


Title	Deep Plug-and-Play Prior for Parallel MRI Reconstruction
Authors	Ali Pour Yazdanpanah, Onur Afacan, Simon K. Warfield
Abstract	Fast data acquisition in Magnetic Resonance Imaging (MRI) is vastly in demand and scan time directly depends on the number of acquired k-space samples. Conventional MRI reconstruction methods for fast MRI acquisition mostly relied on different regularizers which represent analytical models of sparsity. However, recent data-driven methods based on deep learning has resulted in promising improvements in image reconstruction algorithms. In this paper, we propose a deep plug-and-play prior framework for parallel MRI reconstruction problems which utilize a deep neural network (DNN) as an advanced denoiser within an iterative method. This, in turn, enables rapid acquisition of MR images with improved image quality. The proposed method was compared with the reconstructions using the clinical gold standard GRAPPA method. Our results with undersampled data demonstrate that our method can deliver considerably higher quality images at high acceleration factors in comparison to clinical gold standard method for MRI reconstructions. Our proposed reconstruction enables an increase in acceleration factor, and a reduction in acquisition time while maintaining high image quality.
Tasks	Image Reconstruction
Published	2019-08-30
URL	https://arxiv.org/abs/1909.00089v2
PDF	https://arxiv.org/pdf/1909.00089v2.pdf
PWC	https://paperswithcode.com/paper/deep-plug-and-play-prior-for-parallel-mri
Repo
Framework

Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving


Title	Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving
Authors	Tianqi Wang, Dong Eui Chang
Abstract	We present a training pipeline for the autonomous driving task given the current camera image and vehicle speed as the input to produce the throttle, brake, and steering control output. The simulator Airsim’s convenient weather and lighting API provides a sufficient diversity during training which can be very helpful to increase the trained policy’s robustness. In order to not limit the possible policy’s performance, we use a continuous and deterministic control policy setting. We utilize ResNet-34 as our actor and critic networks with some slight changes in the fully connected layers. Considering human’s mastery of this task and the high-complexity nature of this task, we first use imitation learning to mimic the given human policy and leverage the trained policy and its weights to the reinforcement learning phase for which we use DDPG. This combination shows a considerable performance boost comparing to both pure imitation learning and pure DDPG for the autonomous driving task.
Tasks	Autonomous Driving, Imitation Learning, Steering Control
Published	2019-07-16
URL	https://arxiv.org/abs/1907.06838v1
PDF	https://arxiv.org/pdf/1907.06838v1.pdf
PWC	https://paperswithcode.com/paper/improved-reinforcement-learning-through
Repo
Framework

Understanding the Limitations of Conditional Generative Models


Title	Understanding the Limitations of Conditional Generative Models
Authors	Ethan Fetaya, Jörn-Henrik Jacobsen, Will Grathwohl, Richard Zemel
Abstract	Class-conditional generative models hold promise to overcome the shortcomings of their discriminative counterparts. They are a natural choice to solve discriminative tasks in a robust manner as they jointly optimize for predictive performance and accurate modeling of the input distribution. In this work, we investigate robust classification with likelihood-based generative models from a theoretical and practical perspective to investigate if they can deliver on their promises. Our analysis focuses on a spectrum of robustness properties: (1) Detection of worst-case outliers in the form of adversarial examples; (2) Detection of average-case outliers in the form of ambiguous inputs and (3) Detection of incorrectly labeled in-distribution inputs. Our theoretical result reveals that it is impossible to guarantee detectability of adversarially-perturbed inputs even for near-optimal generative classifiers. Experimentally, we find that while we are able to train robust models for MNIST, robustness completely breaks down on CIFAR10. We relate this failure to various undesirable model properties that can be traced to the maximum likelihood training objective. Despite being a common choice in the literature, our results indicate that likelihood-based conditional generative models may are surprisingly ineffective for robust classification.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01171v2
PDF	https://arxiv.org/pdf/1906.01171v2.pdf
PWC	https://paperswithcode.com/paper/conditional-generative-models-are-not-robust
Repo
Framework

Multi-Task Kernel Null-Space for One-Class Classification


Title	Multi-Task Kernel Null-Space for One-Class Classification
Authors	Shervin Rahimzadeh Arashloo, Josef Kittler
Abstract	The one-class kernel spectral regression (OC-KSR), the regression-based formulation of the kernel null-space approach has been found to be an effective Fisher criterion-based methodology for one-class classification (OCC), achieving state-of-the-art performance in one-class classification while providing relatively high robustness against data corruption. This work extends the OC-KSR methodology to a multi-task setting where multiple one-class problems share information for improved performance. By viewing the multi-task structure learning problem as one of compositional function learning, first, the OC-KSR method is extended to learn multiple tasks’ structure \textit{linearly} by posing it as an instantiation of the separable kernel learning problem in a vector-valued reproducing kernel Hilbert space where an output kernel encodes tasks’ structure while another kernel captures input similarities. Next, a non-linear structure learning mechanism is proposed which captures multiple tasks’ relationships \textit{non-linearly} via an output kernel. The non-linear structure learning method is then extended to a sparse setting where different tasks compete in an output composition mechanism, leading to a sparse non-linear structure among multiple problems. Through extensive experiments on different data sets, the merits of the proposed multi-task kernel null-space techniques are verified against the baseline as well as other existing multi-task one-class learning techniques.
Tasks
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09173v1
PDF	https://arxiv.org/pdf/1905.09173v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-kernel-null-space-for-one-class
Repo
Framework

One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them


Title	One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them
Authors	Saber Salehkaleybar, Arsalan Sharifnassab, S. Jamaloddin Golestani
Abstract	We consider distributed statistical optimization in one-shot setting, where there are $m$ machines each observing $n$ i.i.d. samples. Based on its observed samples, each machine sends a $B$-bit-long message to a server. The server then collects messages from all machines, and estimates a parameter that minimizes an expected convex loss function. We investigate the impact of communication constraint, $B$, on the expected error and derive a tight lower bound on the error achievable by any algorithm. We then propose an estimator, which we call Multi-Resolution Estimator (MRE), whose expected error (when $B\ge\log mn$) meets the aforementioned lower bound up to poly-logarithmic factors, and is thereby order optimal. We also address the problem of learning under tiny communication budget, and present lower and upper error bounds when $B$ is a constant. The expected error of MRE, unlike existing algorithms, tends to zero as the number of machines ($m$) goes to infinity, even when the number of samples per machine ($n$) remains upper bounded by a constant. This property of the MRE algorithm makes it applicable in new machine learning paradigms where $m$ is much larger than $n$.
Tasks
Published	2019-05-12
URL	https://arxiv.org/abs/1905.04634v5
PDF	https://arxiv.org/pdf/1905.04634v5.pdf
PWC	https://paperswithcode.com/paper/theoretical-limits-of-one-shot-distributed
Repo
Framework

Sequential Learning over Implicit Feedback for Robust Large-Scale Recommender Systems


Title	Sequential Learning over Implicit Feedback for Robust Large-Scale Recommender Systems
Authors	Alexandra Burashnikova, Yury Maximov, Massih-Reza Amini
Abstract	In this paper, we propose a robust sequential learning strategy for training large-scale Recommender Systems (RS) over implicit feedback mainly in the form of clicks. Our approach relies on the minimization of a pairwise ranking loss over blocks of consecutive items constituted by a sequence of non-clicked items followed by a clicked one for each user. Parameter updates are discarded if for a given user the number of sequential blocks is below or above some given thresholds estimated over the distribution of the number of blocks in the training set. This is to prevent from an abnormal number of clicks over some targeted items, mainly due to bots; or very few user interactions. Both scenarios affect the decision of RS and imply a shift over the distribution of items that are shown to the users. We provide a theoretical analysis showing that in the case where the ranking loss is convex, the deviation between the loss with respect to the sequence of weights found by the proposed algorithm and its minimum is bounded. Furthermore, experimental results on five large-scale collections demonstrate the efficiency of the proposed algorithm with respect to the state-of-the-art approaches, both regarding different ranking measures and computation time.
Tasks	Recommendation Systems
Published	2019-02-21
URL	http://arxiv.org/abs/1902.08495v1
PDF	http://arxiv.org/pdf/1902.08495v1.pdf
PWC	https://paperswithcode.com/paper/sequential-learning-over-implicit-feedback
Repo
Framework


Title	A Discussion on Influence of Newspaper Headlines on Social Media
Authors	Aneek Barman Roy, Baolei Chen, Siddharth Tiwari, Zihan Huang
Abstract	Newspaper headlines contribute severely and have an influence on the social media. This work studies the durability of impact of verbs and adjectives on headlines and determine the factors which are responsible for its nature of influence on the social media. Each headline has been categorized into positive, negative or neutral based on its sentiment score. Initial results show that intensity of a sentiment nature is positively correlated with the social media impression. Additionally, verbs and adjectives show a relation with the sentiment scores
Tasks
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02476v1
PDF	https://arxiv.org/pdf/1909.02476v1.pdf
PWC	https://paperswithcode.com/paper/a-discussion-on-influence-of-newspaper
Repo
Framework

A study of data and label shift in the LIME framework


Title	A study of data and label shift in the LIME framework
Authors	Amir Hossein Akhavan Rahnama, Henrik Boström
Abstract	LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate these instances, LIME randomly selects a subset of the non-zero features of the predicted instance. After that, the perturbed instances are fed into the black-box model to obtain labels for these, which are then used for training the interpretable model. In this study, we present a systematic evaluation of the interpretable models that are output by LIME on the two use-cases that were considered in the original paper introducing the approach; text classification and object detection. The investigation shows that the perturbation and labeling phases result in both data and label shift. In addition, we study the correlation between the shift and the fidelity of the interpretable model and show that in certain cases the shift negatively correlates with the fidelity. Based on these findings, it is argued that there is a need for a new sampling approach that mitigates the shift in the LIME’s framework.
Tasks	Object Detection, Text Classification
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14421v1
PDF	https://arxiv.org/pdf/1910.14421v1.pdf
PWC	https://paperswithcode.com/paper/a-study-of-data-and-label-shift-in-the-lime
Repo
Framework

Local Bures-Wasserstein Transport: A Practical and Fast Mapping Approximation


Title	Local Bures-Wasserstein Transport: A Practical and Fast Mapping Approximation
Authors	Andrés Hoyos-Idrobo
Abstract	Optimal transport (OT)-based methods have a wide range of applications and have attracted a tremendous amount of attention in recent years. However, most of the computational approaches of OT do not learn the underlying transport map. Although some algorithms have been proposed to learn this map, they rely on kernel-based methods, which makes them prohibitively slow when the number of samples increases. Here, we propose a way to learn an approximate transport map and a parametric approximation of the Wasserstein barycenter. We build an approximated transport mapping by leveraging the closed-form of Gaussian (Bures-Wasserstein) transport; we compute local transport plans between matched pairs of the Gaussian components of each density. The learned map generalizes to out-of-sample examples. We provide experimental results on simulated and real data, comparing our proposed method with other mapping estimation algorithms. Preliminary experiments suggest that our proposed method is not only faster, with a factor 80 overall running time, but it also requires fewer components than state-of-the-art methods to recover the support of the barycenter. From a practical standpoint, it is straightforward to implement and can be used with a conventional machine learning pipeline.
Tasks
Published	2019-06-19
URL	https://arxiv.org/abs/1906.08227v1
PDF	https://arxiv.org/pdf/1906.08227v1.pdf
PWC	https://paperswithcode.com/paper/local-bures-wasserstein-transport-a-practical
Repo
Framework

Multisource Region Attention Network for Fine-Grained Object Recognition in Remote Sensing Imagery


Title	Multisource Region Attention Network for Fine-Grained Object Recognition in Remote Sensing Imagery
Authors	Gencer Sumbul, Ramazan Gokberk Cinbis, Selim Aksoy
Abstract	Fine-grained object recognition concerns the identification of the type of an object among a large number of closely related sub-categories. Multisource data analysis, that aims to leverage the complementary spectral, spatial, and structural information embedded in different sources, is a promising direction towards solving the fine-grained recognition problem that involves low between-class variance, small training set sizes for rare classes, and class imbalance. However, the common assumption of co-registered sources may not hold at the pixel level for small objects of interest. We present a novel methodology that aims to simultaneously learn the alignment of multisource data and the classification model in a unified framework. The proposed method involves a multisource region attention network that computes per-source feature representations, assigns attention scores to candidate regions sampled around the expected object locations by using these representations, and classifies the objects by using an attention-driven multisource representation that combines the feature representations and the attention scores from all sources. All components of the model are realized using deep neural networks and are learned in an end-to-end fashion. Experiments using RGB, multispectral, and LiDAR elevation data for classification of street trees showed that our approach achieved 64.2% and 47.3% accuracies for the 18-class and 40-class settings, respectively, which correspond to 13% and 14.3% improvement relative to the commonly used feature concatenation approach from multiple sources.
Tasks	Object Recognition
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06403v1
PDF	http://arxiv.org/pdf/1901.06403v1.pdf
PWC	https://paperswithcode.com/paper/multisource-region-attention-network-for-fine
Repo
Framework

Breast Tumor Classification and Segmentation using Convolutional Neural Networks


Title	Breast Tumor Classification and Segmentation using Convolutional Neural Networks
Authors	Parvin Yousefikamal
Abstract	Breast cancer is considered as the most fatal type of cancer among women worldwide and it is crucially important to be diagnosed at its early stages. In the current study, we aim to represent a fast and efficient framework which consists of two main parts:1- image classification, and 2- tumor region segmentation. At the initial stage, the images are classified into the two categories of normal and abnormal. Since the Deep Neural Networks have performed successfully in machine vision task, we would employ the convolutional neural networks for the classification of images. In the second stage, the suggested framework is to diagnose and segment the tumor in the mammography images. First, the mammography images are pre-processed by removing noise and artifacts, and then, segment the image using the level-set algorithm based on the spatial fuzzy c-means clustering. The proper initialization and optimal configuration have strong effects on the performance of the level-set segmentation. Thus, in our suggested framework, we have improved the level-set algorithm by utilizing the spatial fuzzy c-means clustering which ultimately results in a more precise segmentation. In order to evaluate the proposed approach, we conducted experiments using the Mammographic Image Analysis (MIAS) dataset. The tests have shown that the convolutional neural networks could achieve high accuracy in classification of images. Moreover, the improved level-set segmentation method, along with the fuzzy c-means clustering, could perfectly do the segmentation on the tumor area. The suggested method has classified the images with the accuracy of 78% and the AUC of 69%, which, as compared to the previous methods, is 2% more accurate and 6% better AUC; and has been able to extract the tumor area in a more precise way.
Tasks	Image Classification
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04247v1
PDF	https://arxiv.org/pdf/1905.04247v1.pdf
PWC	https://paperswithcode.com/paper/breast-tumor-classification-and-segmentation
Repo
Framework