January 26, 2020

3354 words 16 mins read

Paper Group ANR 1499

Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks. Functional Generative Design of Mechanisms with Recurrent Neural Networks and Novelty Search. Leveraging Human Guidance for Deep Reinforcement Learning Tasks. Accelerating Goal-Directed Reinforcement Learning by Model Characterization. High Accuracy an …

Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks


Title	Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks
Authors	Davood Karimi, Septimiu E. Salcudean
Abstract	The Hausdorff Distance (HD) is widely used in evaluating medical image segmentation methods. However, existing segmentation methods do not attempt to reduce HD directly. In this paper, we present novel loss functions for training convolutional neural network (CNN)-based segmentation methods with the goal of reducing HD directly. We propose three methods to estimate HD from the segmentation probability map produced by a CNN. One method makes use of the distance transform of the segmentation boundary. Another method is based on applying morphological erosion on the difference between the true and estimated segmentation maps. The third method works by applying circular/spherical convolution kernels of different radii on the segmentation probability maps. Based on these three methods for estimating HD, we suggest three loss functions that can be used for training to reduce HD. We use these loss functions to train CNNs for segmentation of the prostate, liver, and pancreas in ultrasound, magnetic resonance, and computed tomography images and compare the results with commonly-used loss functions. Our results show that the proposed loss functions can lead to approximately 18-45 % reduction in HD without degrading other segmentation performance criteria such as the Dice similarity coefficient. The proposed loss functions can be used for training medical image segmentation methods in order to reduce the large segmentation errors.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2019-04-22
URL	http://arxiv.org/abs/1904.10030v1
PDF	http://arxiv.org/pdf/1904.10030v1.pdf
PWC	https://paperswithcode.com/paper/reducing-the-hausdorff-distance-in-medical
Repo
Framework

Functional Generative Design of Mechanisms with Recurrent Neural Networks and Novelty Search


Title	Functional Generative Design of Mechanisms with Recurrent Neural Networks and Novelty Search
Authors	Cameron R. Wolfe, Cem C. Tutum, Risto Miikkulainen
Abstract	Consumer-grade 3D printers have made it easier to fabricate aesthetic objects and static assemblies, opening the door to automated design of such objects. However, while static designs are easily produced with 3D printing, functional designs with moving parts are more difficult to generate: The search space is too high-dimensional, the resolution of the 3D-printed parts is not adequate, and it is difficult to predict the physical behavior of imperfect 3D-printed mechanisms. An example challenge is to produce a diverse set of reliable and effective gear mechanisms that could be used after production without extensive post-processing. To meet this challenge, an indirect encoding based on a Recurrent Neural Network (RNN) is created and evolved using novelty search. The elite solutions of each generation are 3D printed to evaluate their functional performance on a physical test platform. The system is able to discover sequential design rules that are difficult to discover with other methods. Compared to direct encoding evolved with Genetic Algorithms (GAs), its designs are geometrically more diverse and functionally more effective. It therefore forms a promising foundation for the generative design of 3D-printed, functional mechanisms.
Tasks
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10103v1
PDF	http://arxiv.org/pdf/1903.10103v1.pdf
PWC	https://paperswithcode.com/paper/functional-generative-design-of-mechanisms
Repo
Framework

Leveraging Human Guidance for Deep Reinforcement Learning Tasks


Title	Leveraging Human Guidance for Deep Reinforcement Learning Tasks
Authors	Ruohan Zhang, Faraz Torabi, Lin Guan, Dana H. Ballard, Peter Stone
Abstract	Reinforcement learning agents can learn to solve sequential decision tasks by interacting with the environment. Human knowledge of how to solve these tasks can be incorporated using imitation learning, where the agent learns to imitate human demonstrated decisions. However, human guidance is not limited to the demonstrations. Other types of guidance could be more suitable for certain tasks and require less human effort. This survey provides a high-level overview of five recent learning frameworks that primarily rely on human guidance other than conventional, step-by-step action demonstrations. We review the motivation, assumption, and implementation of each framework. We then discuss possible future research directions.
Tasks	Imitation Learning
Published	2019-09-21
URL	https://arxiv.org/abs/1909.09906v1
PDF	https://arxiv.org/pdf/1909.09906v1.pdf
PWC	https://paperswithcode.com/paper/190909906
Repo
Framework

Accelerating Goal-Directed Reinforcement Learning by Model Characterization


Title	Accelerating Goal-Directed Reinforcement Learning by Model Characterization
Authors	Shoubhik Debnath, Gaurav Sukhatme, Lantao Liu
Abstract	We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where firstly, we approximate a model from Model-Free reinforcement learning. Then, we leverage this approximate model along with a notion of reachability using Mean First Passage Times to perform Model-Based reinforcement learning. Built on such a novel observation, we design two new algorithms - Mean First Passage Time based Q-Learning (MFPT-Q) and Mean First Passage Time based DYNA (MFPT-DYNA), that have been fundamentally modified from the state-of-the-art reinforcement learning techniques. Preliminary results have shown that our hybrid approaches converge with much fewer iterations than their corresponding state-of-the-art counterparts and therefore requiring much fewer samples and much fewer training trials to converge.
Tasks	Q-Learning
Published	2019-01-04
URL	http://arxiv.org/abs/1901.01977v1
PDF	http://arxiv.org/pdf/1901.01977v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-goal-directed-reinforcement
Repo
Framework

High Accuracy and High Fidelity Extraction of Neural Networks


Title	High Accuracy and High Fidelity Extraction of Neural Networks
Authors	Matthew Jagielski, Nicholas Carlini, David Berthelot, Alex Kurakin, Nicolas Papernot
Abstract	In a model extraction attack, an adversary steals a copy of a remotely deployed machine learning model, given oracle prediction access. We taxonomize model extraction attacks around two objectives: accuracy, i.e., performing well on the underlying learning task, and fidelity, i.e., matching the predictions of the remote victim classifier on any input. To extract a high-accuracy model, we develop a learning-based attack exploiting the victim to supervise the training of an extracted model. Through analytical and empirical arguments, we then explain the inherent limitations that prevent any learning-based strategy from extracting a truly high-fidelity model—i.e., extracting a functionally-equivalent model whose predictions are identical to those of the victim model on all possible inputs. Addressing these limitations, we expand on prior work to develop the first practical functionally-equivalent extraction attack for direct extraction (i.e., without training) of a model’s weights. We perform experiments both on academic datasets and a state-of-the-art image classifier trained with 1 billion proprietary images. In addition to broadening the scope of model extraction research, our work demonstrates the practicality of model extraction attacks against production-grade systems.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01838v2
PDF	https://arxiv.org/pdf/1909.01838v2.pdf
PWC	https://paperswithcode.com/paper/high-fidelity-extraction-of-neural-network
Repo
Framework

From Non-Paying to Premium: Predicting User Conversion in Video Games with Ensemble Learning


Title	From Non-Paying to Premium: Predicting User Conversion in Video Games with Ensemble Learning
Authors	Anna Guitart, Shi Hui Tan, Ana Fernández del Río, Pei Pei Chen, África Periáñez
Abstract	Retaining premium players is key to the success of free-to-play games, but most of them do not start purchasing right after joining the game. By exploiting the exceptionally rich datasets recorded by modern video games–which provide information on the individual behavior of each and every player–survival analysis techniques can be used to predict what players are more likely to become paying (or even premium) users and when, both in terms of time and game level, the conversion will take place. Here we show that a traditional semi-parametric model (Cox regression), a random survival forest (RSF) technique and a method based on conditional inference survival ensembles all yield very promising results. However, the last approach has the advantage of being able to correct the inherent bias in RSF models by dividing the procedure into two steps: first selecting the best predictor to perform the splitting and then the best split point for that covariate. The proposed conditional inference survival ensembles method could be readily used in operational environments for early identification of premium players and the parts of the game that may prompt them to become paying users. Such knowledge would allow developers to induce their conversion and, more generally, to better understand the needs of their players and provide them with a personalized experience, thereby increasing their engagement and paving the way to higher monetization.
Tasks	Survival Analysis
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10320v2
PDF	https://arxiv.org/pdf/1906.10320v2.pdf
PWC	https://paperswithcode.com/paper/from-non-paying-to-premium-predicting-user
Repo
Framework

A unified construction for series representations and finite approximations of completely random measures


Title	A unified construction for series representations and finite approximations of completely random measures
Authors	Juho Lee, Xenia Miscouridou, François Caron
Abstract	Infinite-activity completely random measures (CRMs) have become important building blocks of complex Bayesian nonparametric models. They have been successfully used in various applications such as clustering, density estimation, latent feature models, survival analysis or network science. Popular infinite-activity CRMs include the (generalized) gamma process and the (stable) beta process. However, except in some specific cases, exact simulation or scalable inference with these models is challenging and finite-dimensional approximations are often considered. In this work, we propose a general and unified framework to derive both series representations and finite-dimensional approximations of CRMs. Our framework can be seen as an extension of constructions based on size-biased sampling of Poisson point process [Perman1992]. It includes as special cases several known series representations as well as novel ones. In particular, we show that one can get novel series representations for the generalized gamma process and the stable beta process. We also provide some analysis of the truncation error.
Tasks	Density Estimation, Survival Analysis
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10733v1
PDF	https://arxiv.org/pdf/1905.10733v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-construction-for-series
Repo
Framework

Relational Generalized Few-Shot Learning


Title	Relational Generalized Few-Shot Learning
Authors	Xiahan Shi, Leonard Salewski, Martin Schiegg, Zeynep Akata, Max Welling
Abstract	Transferring learned models to novel tasks is a challenging problem, particularly if only very few labeled examples are available. Although this few-shot learning setup has received a lot of attention recently, most proposed methods focus on discriminating novel classes only. Instead, we consider the extended setup of generalized few-shot learning (GFSL), where the model is required to perform classification on the joint label space consisting of both previously seen and novel classes. We propose a graph-based framework that explicitly models relationships between all seen and novel classes in the joint label space. Our model Graph-convolutional Global Prototypical Networks (GcGPN) incorporates these inter-class relations using graph-convolution in order to embed novel class representations into the existing space of previously seen classes in a globally consistent manner. Our approach ensures both fast adaptation and global discrimination, which is the major challenge in GFSL. We demonstrate the benefits of our model on two challenging benchmark datasets.
Tasks	Few-Shot Learning
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09557v1
PDF	https://arxiv.org/pdf/1907.09557v1.pdf
PWC	https://paperswithcode.com/paper/relational-generalized-few-shot-learning
Repo
Framework

Unsupervised Machine Learning for the Discovery of Latent Disease Clusters and Patient Subgroups Using Electronic Health Records


Title	Unsupervised Machine Learning for the Discovery of Latent Disease Clusters and Patient Subgroups Using Electronic Health Records
Authors	Yanshan Wang, Yiqing Zhao, Terry M. Therneau, Elizabeth J. Atkinson, Ahmad P. Tafti, Nan Zhang, Shreyasee Amin, Andrew H. Limper, Hongfang Liu
Abstract	Machine learning has become ubiquitous and a key technology on mining electronic health records (EHRs) for facilitating clinical research and practice. Unsupervised machine learning, as opposed to supervised learning, has shown promise in identifying novel patterns and relations from EHRs without using human created labels. In this paper, we investigate the application of unsupervised machine learning models in discovering latent disease clusters and patient subgroups based on EHRs. We utilized Latent Dirichlet Allocation (LDA), a generative probabilistic model, and proposed a novel model named Poisson Dirichlet Model (PDM), which extends the LDA approach using a Poisson distribution to model patients’ disease diagnoses and to alleviate age and sex factors by considering both observed and expected observations. In the empirical experiments, we evaluated LDA and PDM on three patient cohorts with EHR data retrieved from the Rochester Epidemiology Project (REP), for the discovery of latent disease clusters and patient subgroups. We compared the effectiveness of LDA and PDM in identifying latent disease clusters through the visualization of disease representations learned by two approaches. We also tested the performance of LDA and PDM in differentiating patient subgroups through survival analysis, as well as statistical analysis. The experimental results show that the proposed PDM could effectively identify distinguished disease clusters by alleviating the impact of age and sex, and that LDA could stratify patients into more differentiable subgroups than PDM in terms of p-values. However, the subgroups discovered by PDM might imply the underlying patterns of diseases of greater interest in epidemiology research due to the alleviation of age and sex. Both unsupervised machine learning approaches could be leveraged to discover patient subgroups using EHRs but with different foci.
Tasks	Epidemiology, Survival Analysis
Published	2019-05-17
URL	https://arxiv.org/abs/1905.10309v1
PDF	https://arxiv.org/pdf/1905.10309v1.pdf
PWC	https://paperswithcode.com/paper/190510309
Repo
Framework

Image Quality Assessment for Rigid Motion Compensation


Title	Image Quality Assessment for Rigid Motion Compensation
Authors	Alexander Preuhs, Michael Manhart, Philipp Roser, Bernhard Stimpel, Christopher Syben, Marios Psychogios, Markus Kowarschik, Andreas Maier
Abstract	Diagnostic stroke imaging with C-arm cone-beam computed tomography (CBCT) enables reduction of time-to-therapy for endovascular procedures. However, the prolonged acquisition time compared to helical CT increases the likelihood of rigid patient motion. Rigid motion corrupts the geometry alignment assumed during reconstruction, resulting in image blurring or streaking artifacts. To reestablish the geometry, we estimate the motion trajectory by an autofocus method guided by a neural network, which was trained to regress the reprojection error, based on the image information of a reconstructed slice. The network was trained with CBCT scans from 19 patients and evaluated using an additional test patient. It adapts well to unseen motion amplitudes and achieves superior results in a motion estimation benchmark compared to the commonly used entropy-based method.
Tasks	Image Quality Assessment, Motion Compensation, Motion Estimation
Published	2019-10-09
URL	https://arxiv.org/abs/1910.04254v2
PDF	https://arxiv.org/pdf/1910.04254v2.pdf
PWC	https://paperswithcode.com/paper/image-quality-assessment-for-rigid-motion
Repo
Framework

Unsupervised Task Design to Meta-Train Medical Image Classifiers


Title	Unsupervised Task Design to Meta-Train Medical Image Classifiers
Authors	Gabriel Maicas, Cuong Nguyen, Farbod Motlagh, Jacinto C. Nascimento, Gustavo Carneiro
Abstract	Meta-training has been empirically demonstrated to be the most effective pre-training method for few-shot learning of medical image classifiers (i.e., classifiers modeled with small training sets). However, the effectiveness of meta-training relies on the availability of a reasonable number of hand-designed classification tasks, which are costly to obtain, and consequently rarely available. In this paper, we propose a new method to unsupervisedly design a large number of classification tasks to meta-train medical image classifiers. We evaluate our method on a breast dynamically contrast enhanced magnetic resonance imaging (DCE-MRI) data set that has been used to benchmark few-shot training methods of medical image classifiers. Our results show that the proposed unsupervised task design to meta-train medical image classifiers builds a pre-trained model that, after fine-tuning, produces better classification results than other unsupervised and supervised pre-training methods, and competitive results with respect to meta-training that relies on hand-designed classification tasks.
Tasks	Few-Shot Learning
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07816v1
PDF	https://arxiv.org/pdf/1907.07816v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-task-design-to-meta-train
Repo
Framework


Title	On Social Machines for Algorithmic Regulation
Authors	Nello Cristianini, Teresa Scantamburlo
Abstract	Autonomous mechanisms have been proposed to regulate certain aspects of society and are already being used to regulate business organisations. We take seriously recent proposals for algorithmic regulation of society, and we identify the existing technologies that can be used to implement them, most of them originally introduced in business contexts. We build on the notion of ‘social machine’ and we connect it to various ongoing trends and ideas, including crowdsourced task-work, social compiler, mechanism design, reputation management systems, and social scoring. After showing how all the building blocks of algorithmic regulation are already well in place, we discuss possible implications for human autonomy and social order. The main contribution of this paper is to identify convergent social and technical trends that are leading towards social regulation by algorithms, and to discuss the possible social, political, and ethical consequences of taking this path.
Tasks
Published	2019-04-30
URL	http://arxiv.org/abs/1904.13316v1
PDF	http://arxiv.org/pdf/1904.13316v1.pdf
PWC	https://paperswithcode.com/paper/on-social-machines-for-algorithmic-regulation
Repo
Framework

Kernel Mean Embedding Based Hypothesis Tests for Comparing Spatial Point Patterns


Title	Kernel Mean Embedding Based Hypothesis Tests for Comparing Spatial Point Patterns
Authors	Raif M. Rustamov, James T. Klosowski
Abstract	This paper introduces an approach for detecting differences in the first-order structures of spatial point patterns. The proposed approach leverages the kernel mean embedding in a novel way by introducing its approximate version tailored to spatial point processes. While the original embedding is infinite-dimensional and implicit, our approximate embedding is finite-dimensional and comes with explicit closed-form formulas. With its help we reduce the pattern comparison problem to the comparison of means in the Euclidean space. Hypothesis testing is based on conducting t-tests on each dimension of the embedding and combining the resulting p-values using one of the recently introduced p-value combination techniques. The main advantages of the proposed approach are that it can be applied to both single and replicated pattern comparisons, and that neither bootstrap nor permutation procedures are needed to obtain or calibrate the p-values. Our experiments show that the resulting tests are powerful and the p-values are well-calibrated; two applications to real world data are presented.
Tasks	Point Processes
Published	2019-05-31
URL	https://arxiv.org/abs/1906.00116v2
PDF	https://arxiv.org/pdf/1906.00116v2.pdf
PWC	https://paperswithcode.com/paper/kernel-mean-embedding-based-hypothesis-tests
Repo
Framework

Predicting Urban Dispersal Events: A Two-Stage Framework through Deep Survival Analysis on Mobility Data


Title	Predicting Urban Dispersal Events: A Two-Stage Framework through Deep Survival Analysis on Mobility Data
Authors	Amin Vahedian, Xun Zhou, Ling Tong, W. Nick Street, Yanhua Li
Abstract	Urban dispersal events are processes where an unusually large number of people leave the same area in a short period. Early prediction of dispersal events is important in mitigating congestion and safety risks and making better dispatching decisions for taxi and ride-sharing fleets. Existing work mostly focuses on predicting taxi demand in the near future by learning patterns from historical data. However, they fail in case of abnormality because dispersal events with abnormally high demand are non-repetitive and violate common assumptions such as smoothness in demand change over time. Instead, in this paper we argue that dispersal events follow a complex pattern of trips and other related features in the past, which can be used to predict such events. Therefore, we formulate the dispersal event prediction problem as a survival analysis problem. We propose a two-stage framework (DILSA), where a deep learning model combined with survival analysis is developed to predict the probability of a dispersal event and its demand volume. We conduct extensive case studies and experiments on the NYC Yellow taxi dataset from 2014-2016. Results show that DILSA can predict events in the next 5 hours with F1-score of 0.7 and with average time error of 18 minutes. It is orders of magnitude better than the state-ofthe-art deep learning approaches for taxi demand prediction.
Tasks	Survival Analysis
Published	2019-05-03
URL	https://arxiv.org/abs/1905.01281v2
PDF	https://arxiv.org/pdf/1905.01281v2.pdf
PWC	https://paperswithcode.com/paper/predicting-urban-dispersal-events-a-two-stage
Repo
Framework

Deep Learning for CSI Feedback Based on Superimposed Coding


Title	Deep Learning for CSI Feedback Based on Superimposed Coding
Authors	Chaojin Qing, Bin Cai, Qingyao Yang, Jiafan Wang, Chuan Huang
Abstract	Massive multiple-input multiple-output (MIMO) with frequency division duplex (FDD) mode is a promising approach to increasing system capacity and link robustness for the fifth generation (5G) wireless cellular systems. The premise of these advantages is the accurate downlink channel state information (CSI) fed back from user equipment. However, conventional feedback methods have difficulties in reducing feedback overhead due to significant amount of base station (BS) antennas in massive MIMO systems. Recently, deep learning (DL)-based CSI feedback conquers many difficulties, yet still shows insufficiency to decrease the occupation of uplink bandwidth resources. In this paper, to solve this issue, we combine DL and superimposed coding (SC) for CSI feedback, in which the downlink CSI is spread and then superimposed on uplink user data sequences (UL-US) toward the BS. Then, a multi-task neural network (NN) architecture is proposed at BS to recover the downlink CSI and UL-US by unfolding two iterations of the minimum mean-squared error (MMSE) criterion-based interference reduction. In addition, for a network training, a subnet-by-subnet approach is exploited to facilitate the parameter tuning and expedite the convergence rate. Compared with standalone SC-based CSI scheme, our multi-task NN, trained in a specific signal-to-noise ratio (SNR) and power proportional coefficient (PPC), consistently improves the estimation of downlink CSI with similar or better UL-US detection under SNR and PPC varying.
Tasks
Published	2019-07-27
URL	https://arxiv.org/abs/1907.11836v1
PDF	https://arxiv.org/pdf/1907.11836v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-csi-feedback-based-on
Repo
Framework