April 2, 2020

3680 words 18 mins read

Paper Group ANR 227

Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification. Interpretability of machine learning based prediction models in healthcare. DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction. Multiple Imputation with Denoising Autoencoder using Metamorphic Truth and Imputation Feedback. Thompson …

Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification


Title	Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
Authors	Changxing Ding, Kan Wang, Pengfei Wang, Dacheng Tao
Abstract	Part-level representations are important for robust person re-identification (ReID), but in practice feature quality suffers due to the body part misalignment problem. In this paper, we present a robust, compact, and easy-to-use method called the Multi-task Part-aware Network (MPN), which is designed to extract semantically aligned part-level features from pedestrian images. MPN solves the body part misalignment problem via multi-task learning (MTL) in the training stage. More specifically, it builds one main task (MT) and one auxiliary task (AT) for each body part on the top of the same backbone model. The ATs are equipped with a coarse prior of the body part locations for training images. ATs then transfer the concept of the body parts to the MTs via optimizing the MT parameters to identify part-relevant channels from the backbone model. Concept transfer is accomplished by means of two novel alignment strategies: namely, parameter space alignment via hard parameter sharing and feature space alignment in a class-wise manner. With the aid of the learned high-quality parameters, MTs can independently extract semantically aligned part-level features from relevant channels in the testing stage. MPN has three key advantages: 1) it does not need to conduct body part detection in the inference stage; 2) its model is very compact and efficient for both training and testing; 3) in the training stage, it requires only coarse priors of body part locations, which are easy to obtain. Systematic experiments on four large-scale ReID databases demonstrate that MPN consistently outperforms state-of-the-art approaches by significant margins.
Tasks	Multi-Task Learning, Person Re-Identification
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08069v1
PDF	https://arxiv.org/pdf/2003.08069v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-learning-with-coarse-priors-for
Repo
Framework

Interpretability of machine learning based prediction models in healthcare


Title	Interpretability of machine learning based prediction models in healthcare
Authors	Gregor Stiglic, Primoz Kocbek, Nino Fijacko, Marinka Zitnik, Katrien Verbert, Leona Cilar
Abstract	There is a need of ensuring machine learning models that are interpretable. Higher interpretability of the model means easier comprehension and explanation of future predictions for end-users. Further, interpretable machine learning models allow healthcare experts to make reasonable and data-driven decisions to provide personalized decisions that can ultimately lead to higher quality of service in healthcare. Generally, we can classify interpretability approaches in two groups where the first focuses on personalized interpretation (local interpretability) while the second summarizes prediction models on a population level (global interpretability). Alternatively, we can group interpretability methods into model-specific techniques, which are designed to interpret predictions generated by a specific model, such as a neural network, and model-agnostic approaches, which provide easy-to-understand explanations of predictions made by any machine learning model. Here, we give an overview of interpretability approaches and provide examples of practical interpretability of machine learning in different areas of healthcare, including prediction of health-related outcomes, optimizing treatments or improving the efficiency of screening for specific conditions. Further, we outline future directions for interpretable machine learning and highlight the importance of developing algorithmic solutions that can enable machine-learning driven decision making in high-stakes healthcare problems.
Tasks	Decision Making, Interpretable Machine Learning
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08596v1
PDF	https://arxiv.org/pdf/2002.08596v1.pdf
PWC	https://paperswithcode.com/paper/interpretability-of-machine-learning-based
Repo
Framework

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction


Title	DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
Authors	Aviral Kumar, Abhishek Gupta, Sergey Levine
Abstract	Deep reinforcement learning can learn effective policies for a wide range of tasks, but is notoriously difficult to use due to instability and sensitivity to hyperparameters. The reasons for this remain unclear. When using standard supervised methods (e.g., for bandits), on-policy data collection provides “hard negatives” that correct the model in precisely those states and actions that the policy is likely to visit. We call this phenomenon “corrective feedback.” We show that bootstrapping-based Q-learning algorithms do not necessarily benefit from this corrective feedback, and training on the experience collected by the algorithm is not sufficient to correct errors in the Q-function. In fact, Q-learning and related methods can exhibit pathological interactions between the distribution of experience collected by the agent and the policy induced by training on that experience, leading to potential instability, sub-optimal convergence, and poor results when learning from noisy, sparse or delayed rewards. We demonstrate the existence of this problem, both theoretically and empirically. We then show that a specific correction to the data distribution can mitigate this issue. Based on these observations, we propose a new algorithm, DisCor, which computes an approximation to this optimal distribution and uses it to re-weight the transitions used for training, resulting in substantial improvements in a range of challenging RL settings, such as multi-task learning and learning from noisy reward signals. Blog post presenting a summary of this work is available at: https://bair.berkeley.edu/blog/2020/03/16/discor/.
Tasks	Multi-Task Learning, Q-Learning
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07305v1
PDF	https://arxiv.org/pdf/2003.07305v1.pdf
PWC	https://paperswithcode.com/paper/discor-corrective-feedback-in-reinforcement
Repo
Framework

Multiple Imputation with Denoising Autoencoder using Metamorphic Truth and Imputation Feedback


Title	Multiple Imputation with Denoising Autoencoder using Metamorphic Truth and Imputation Feedback
Authors	Haw-minn Lu, Giancarlo Perrone, José Unpingco
Abstract	Although data may be abundant, complete data is less so, due to missing columns or rows. This missingness undermines the performance of downstream data products that either omit incomplete cases or create derived completed data for subsequent processing. Appropriately managing missing data is required in order to fully exploit and correctly use data. We propose a Multiple Imputation model using Denoising Autoencoders to learn the internal representation of data. Furthermore, we use the novel mechanisms of Metamorphic Truth and Imputation Feedback to maintain statistical integrity of attributes and eliminate bias in the learning process. Our approach explores the effects of imputation on various missingness mechanisms and patterns of missing data, outperforming other methods in many standard test cases.
Tasks	Denoising, Imputation
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08338v1
PDF	https://arxiv.org/pdf/2002.08338v1.pdf
PWC	https://paperswithcode.com/paper/multiple-imputation-with-denoising
Repo
Framework

Thompson Sampling Algorithms for Mean-Variance Bandits


Title	Thompson Sampling Algorithms for Mean-Variance Bandits
Authors	Qiuyu Zhu, Vincent Y. F. Tan
Abstract	The multi-armed bandit (MAB) problem is a classical learning task that exemplifies the exploration-exploitation tradeoff. However, standard formulations do not take into account risk. In online decision making systems, risk is a primary concern. In this regard, the mean-variance risk measure is one of the most common objective functions. Existing algorithms for mean-variance optimization in the context of MAB problems have unrealistic assumptions on the reward distributions. We develop Thompson Sampling-style algorithms for mean-variance MAB and provide comprehensive regret analyses for Gaussian and Bernoulli bandits with fewer assumptions. Our algorithms achieve the best known regret bounds for mean-variance MABs and also attain the information-theoretic bounds in some parameter regimes. Empirical simulations show that our algorithms significantly outperform existing LCB-based algorithms for all risk tolerances.
Tasks	Decision Making
Published	2020-02-01
URL	https://arxiv.org/abs/2002.00232v1
PDF	https://arxiv.org/pdf/2002.00232v1.pdf
PWC	https://paperswithcode.com/paper/thompson-sampling-algorithms-for-mean
Repo
Framework

Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with Bayesian inference for uncertainty-based quality-control


Title	Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with Bayesian inference for uncertainty-based quality-control
Authors	Esther Puyol Anton, Bram Ruijsink, Christian F. Baumgartner, Matthew Sinclair, Ender Konukoglu, Reza Razavi, Andrew P. King
Abstract	Tissue characterisation with CMR parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T1 mapping in particular has shown promise as a useful biomarker to support diagnostic, therapeutic and prognostic decision-making in ischaemic and non-ischaemic cardiomyopathies. Convolutional neural networks with Bayesian inference are a category of artificial neural networks which model the uncertainty of the network output. This study presents an automated framework for tissue characterisation from native ShMOLLI T1 mapping at 1.5T using a Probabilistic Hierarchical Segmentation (PHiSeg) network. In addition, we use the uncertainty information provided by the PHiSeg network in a novel automated quality control (QC) step to identify uncertain T1 values. The PHiSeg network and QC were validated against manual analysis on a cohort of the UK Biobank containing healthy subjects and chronic cardiomyopathy patients. We used the proposed method to obtain reference T1 ranges for the left ventricular myocardium in healthy subjects as well as common clinical cardiac conditions. T1 values computed from automatic and manual segmentations were highly correlated (r=0.97). Bland-Altman analysis showed good agreement between the automated and manual measurements. The average Dice metric was 0.84 for the left ventricular myocardium. The sensitivity of detection of erroneous outputs was 91%. Finally, T1 values were automatically derived from 14,683 CMR exams from the UK Biobank. The proposed pipeline allows for automatic analysis of myocardial native T1 mapping and includes a QC process to detect potentially erroneous results. T1 reference values were presented for healthy subjects and common clinical cardiac conditions from the largest cohort to date using T1-mapping images.
Tasks	Bayesian Inference, Decision Making
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11711v1
PDF	https://arxiv.org/pdf/2001.11711v1.pdf
PWC	https://paperswithcode.com/paper/automated-quantification-of-myocardial-tissue
Repo
Framework

Modeling Sensing and Perception Errors towards Robust Decision Making in Autonomous Vehicles


Title	Modeling Sensing and Perception Errors towards Robust Decision Making in Autonomous Vehicles
Authors	Andrea Piazzoni, Jim Cherian, Martin Slavik, Justin Dauwels
Abstract	Sensing and Perception (S&P) is a crucial component of an autonomous system (such as a robot), especially when deployed in highly dynamic environments where it is required to react to unexpected situations. This is particularly true in case of Autonomous Vehicles (AVs) driving on public roads. However, the current evaluation metrics for perception algorithms are typically designed to measure their accuracy per se and do not account for their impact on the decision making subsystem(s). This limitation does not help developers and third party evaluators to answer a critical question: is the performance of a perception subsystem sufficient for the decision making subsystem to make robust, safe decisions? In this paper, we propose a simulation-based methodology towards answering this question. At the same time, we show how to analyze the impact of different kinds of sensing and perception errors on the behavior of the autonomous system.
Tasks	Autonomous Vehicles, Decision Making
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11695v1
PDF	https://arxiv.org/pdf/2001.11695v1.pdf
PWC	https://paperswithcode.com/paper/modeling-sensing-and-perception-errors
Repo
Framework

Uniform Interpolation Constrained Geodesic Learning on Data Manifold


Title	Uniform Interpolation Constrained Geodesic Learning on Data Manifold
Authors	Cong Geng, Jia Wang, Li Chen, Wenbo Bao, Chu Chu, Zhiyong Gao
Abstract	In this paper, we propose a method to learn a minimizing geodesic within a data manifold. Along the learned geodesic, our method can generate high-quality interpolations between two given data samples. Specifically, we use an autoencoder network to map data samples into latent space and perform interpolation via an interpolation network. We add prior geometric information to regularize our autoencoder for the convexity of representations so that for any given interpolation approach, the generated interpolations remain within the distribution of the data manifold. Before the learning of a geodesic, a proper Riemannianmetric should be defined. Therefore, we induce a Riemannian metric by the canonical metric in the Euclidean space which the data manifold is isometrically immersed in. Based on this defined Riemannian metric, we introduce a constant speed loss and a minimizing geodesic loss to regularize the interpolation network to generate uniform interpolation along the learned geodesic on the manifold. We provide a theoretical analysis of our model and use image translation as an example to demonstrate the effectiveness of our method.
Tasks
Published	2020-02-12
URL	https://arxiv.org/abs/2002.04829v2
PDF	https://arxiv.org/pdf/2002.04829v2.pdf
PWC	https://paperswithcode.com/paper/uniform-interpolation-constrained-geodesic
Repo
Framework

Abdominal multi-organ segmentation with cascaded convolutional and adversarial deep networks


Title	Abdominal multi-organ segmentation with cascaded convolutional and adversarial deep networks
Authors	Pierre-Henri Conze, Ali Emre Kavur, Emilie Cornec-Le Gall, Naciye Sinem Gezer, Yannick Le Meur, M. Alper Selver, François Rousseau
Abstract	Objective : Abdominal anatomy segmentation is crucial for numerous applications from computer-assisted diagnosis to image-guided surgery. In this context, we address fully-automated multi-organ segmentation from abdominal CT and MR images using deep learning. Methods: The proposed model extends standard conditional generative adversarial networks. Additionally to the discriminator which enforces the model to create realistic organ delineations, it embeds cascaded partially pre-trained convolutional encoder-decoders as generator. Encoder fine-tuning from a large amount of non-medical images alleviates data scarcity limitations. The network is trained end-to-end to benefit from simultaneous multi-level segmentation refinements using auto-context. Results : Employed for healthy liver, kidneys and spleen segmentation, our pipeline provides promising results by outperforming state-of-the-art encoder-decoder schemes. Followed for the Combined Healthy Abdominal Organ Segmentation (CHAOS) challenge organized in conjunction with the IEEE International Symposium on Biomedical Imaging 2019, it gave us the first rank for three competition categories: liver CT, liver MR and multi-organ MR segmentation. Conclusion : Combining cascaded convolutional and adversarial networks strengthens the ability of deep learning pipelines to automatically delineate multiple abdominal organs, with good generalization capability. Significance : The comprehensive evaluation provided suggests that better guidance could be achieved to help clinicians in abdominal image interpretation and clinical decision making.
Tasks	Decision Making
Published	2020-01-26
URL	https://arxiv.org/abs/2001.09521v1
PDF	https://arxiv.org/pdf/2001.09521v1.pdf
PWC	https://paperswithcode.com/paper/abdominal-multi-organ-segmentation-with
Repo
Framework

Decoding pedestrian and automated vehicle interactions using immersive virtual reality and interpretable deep learning


Title	Decoding pedestrian and automated vehicle interactions using immersive virtual reality and interpretable deep learning
Authors	Arash Kalatian, Bilal Farooq
Abstract	To ensure pedestrian friendly streets in the era of automated vehicles, reassessment of current policies, practices, design, rules and regulations of urban areas is of importance. This study investigates pedestrian crossing behaviour, as an important element of urban dynamics that is expected to be affected by the presence of automated vehicles. For this purpose, an interpretable machine learning framework is proposed to explore factors affecting pedestrians’ wait time before crossing mid-block crosswalks in the presence of automated vehicles. To collect rich behavioural data, we developed a dynamic and immersive virtual reality experiment, with 180 participants from a heterogeneous population in 4 different locations in the Greater Toronto Area (GTA). Pedestrian wait time behaviour is then analyzed using a data-driven Cox Proportional Hazards (CPH) model, in which the linear combination of the covariates is replaced by a flexible non-linear deep neural network. The proposed model achieved a 5% improvement in goodness of fit, but more importantly, enabled us to incorporate a richer set of covariates. A game theoretic based interpretability method is used to understand the contribution of different covariates to the time pedestrians wait before crossing. Results show that the presence of automated vehicles on roads, wider lane widths, high density on roads, limited sight distance, and lack of walking habits are the main contributing factors to longer wait times. Our study suggested that, to move towards pedestrian-friendly urban areas, national level educational programs for children, enhanced safety measures for seniors, promotion of active modes of transportation, and revised traffic rules and regulations should be considered.
Tasks	Interpretable Machine Learning
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07325v1
PDF	https://arxiv.org/pdf/2002.07325v1.pdf
PWC	https://paperswithcode.com/paper/decoding-pedestrian-and-automated-vehicle
Repo
Framework

An Autonomous Intrusion Detection System Using Ensemble of Advanced Learners


Title	An Autonomous Intrusion Detection System Using Ensemble of Advanced Learners
Authors	Amir Andalib, Vahid Tabataba Vakili
Abstract	An intrusion detection system (IDS) is a vital security component of modern computer networks. With networks finding their ways into providing sensitive services, IDSs need to be more intelligent and autonomous. Aside from autonomy, another important attribute for an IDS is its ability to detect zero-day attacks. To address these issues in this paper we propose an IDS which reduces the amount of manual interaction and needed expert knowledge and is able to yield acceptable performance under zero-day attacks. Our approach is to use three learning techniques in parallel, gated recurrent unit (GRU), convolutional neural network as deep techniques and Random Forest as an ensemble technique. These systems are trained in parallel and the results are combined under two logics, majority vote and “OR” logic. We use the NSL-KDD dataset to verify the proficiency of our proposed system. Simulation results show that the system has the potential to operate with a very low technician interaction under the zero-day attacks. We achieved 87.28% accuracy in the NSL-KDD’s “KDDTest+” dataset and 76.61% accuracy on the challenging “KDDTest-21” with lower training time and lower needed computational resources.
Tasks	Intrusion Detection
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11936v1
PDF	https://arxiv.org/pdf/2001.11936v1.pdf
PWC	https://paperswithcode.com/paper/an-autonomous-intrusion-detection-system
Repo
Framework

Interpretable MTL from Heterogeneous Domains using Boosted Tree


Title	Interpretable MTL from Heterogeneous Domains using Boosted Tree
Authors	Ya-Lin Zhang, Longfei Li
Abstract	Multi-task learning (MTL) aims at improving the generalization performance of several related tasks by leveraging useful information contained in them. However, in industrial scenarios, interpretability is always demanded, and the data of different tasks may be in heterogeneous domains, making the existing methods unsuitable or unsatisfactory. In this paper, following the philosophy of boosted tree, we proposed a two-stage method. In stage one, a common model is built to learn the commonalities using the common features of all instances. Different from the training of conventional boosted tree model, we proposed a regularization strategy and an early-stopping mechanism to optimize the multi-task learning process. In stage two, started by fitting the residual error of the common model, a specific model is constructed with the task-specific instances to further boost the performance. Experiments on both benchmark and real-world datasets validate the effectiveness of the proposed method. What’s more, interpretability can be naturally obtained from the tree based method, satisfying the industrial needs.
Tasks	Multi-Task Learning
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07077v1
PDF	https://arxiv.org/pdf/2003.07077v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-mtl-from-heterogeneous-domains
Repo
Framework

IoT Behavioral Monitoring via Network Traffic Analysis


Title	IoT Behavioral Monitoring via Network Traffic Analysis
Authors	Arunan Sivanathan
Abstract	Smart homes, enterprises, and cities are increasingly being equipped with a plethora of Internet of Things (IoT), ranging from smart-lights to security cameras. While IoT networks have the potential to benefit our lives, they create privacy and security challenges not seen with traditional IT networks. Due to the lack of visibility, operators of such smart environments are not often aware of their IoT assets, let alone whether each IoT device is functioning properly safe from cyber-attacks. This thesis is the culmination of our efforts to develop techniques to profile the network behavioral pattern of IoTs, automate IoT classification, deduce their operating context, and detect anomalous behavior indicative of cyber-attacks. We begin this thesis by surveying IoT ecosystem, while reviewing current approaches to vulnerability assessments, intrusion detection, and behavioral monitoring. For our first contribution, we collect traffic traces and characterize the network behavior of IoT devices via attributes from traffic patterns. We develop a robust machine learning-based inference engine trained with these attributes and demonstrate real-time classification of 28 IoT devices with over 99% accuracy. Our second contribution enhances the classification by reducing the cost of attribute extraction while also identifying IoT device states. Prototype implementation and evaluation demonstrate the ability of our supervised machine learning method to detect behavioral changes for five IoT devices. Our third and final contribution develops a modularized unsupervised inference engine that dynamically accommodates the addition of new IoT devices and/or updates to existing ones, without requiring system-wide retraining of the model. We demonstrate via experiments that our model can automatically detect attacks and firmware changes in ten IoT devices with over 94% accuracy.
Tasks	Intrusion Detection
Published	2020-01-28
URL	https://arxiv.org/abs/2001.10632v1
PDF	https://arxiv.org/pdf/2001.10632v1.pdf
PWC	https://paperswithcode.com/paper/iot-behavioral-monitoring-via-network-traffic
Repo
Framework

A Content-Based Deep Intrusion Detection System


Title	A Content-Based Deep Intrusion Detection System
Authors	Mahdi Soltani, Mahdi Jafari Siavoshani, Amir Hossein Jahangir
Abstract	By growing the number of Internet users and the prevalence of web applications, we have to deal with very complex software and applications in the network. This results in an increasing number of new vulnerabilities in the systems, which consequently leads to an increase in the cyber and, in particular, zero-day attacks. The cost of generating appropriate signatures for these attacks is a potential motive for using machine learning-based methodologies. Although there exist many studies on the use of learning-based methods for attack detection, they generally use extracted features and overlook raw contents. This approach can lessen the performance of detection systems against content-based attacks like SQL injection, Cross-site Scripting (XSS), and various viruses. As a new paradigm, in this work, we propose a scheme, called deep intrusion detection (DID) system that uses the pure content of traffic flows in addition to traffic metadata in the learning and detection phases. To this end, we employ deep learning techniques recently developed in the machine learning community. Due to the inherent nature of deep learning, it can process high dimensional data content and, accordingly, discover the sophisticated relations between the auto extracted features of the traffic. To evaluate the proposed DID system, we use the ISCX IDS 2017 dataset. The evaluation metrics, such as precision and recall, reach $0.992$ and $0.998$, respectively, which show the high performance of the proposed DID method.
Tasks	Intrusion Detection
Published	2020-01-14
URL	https://arxiv.org/abs/2001.05009v1
PDF	https://arxiv.org/pdf/2001.05009v1.pdf
PWC	https://paperswithcode.com/paper/a-content-based-deep-intrusion-detection
Repo
Framework

CAAI – A Cognitive Architecture to Introduce Artificial Intelligence in Cyber-Physical Production Systems


Title	CAAI – A Cognitive Architecture to Introduce Artificial Intelligence in Cyber-Physical Production Systems
Authors	Andreas Fischbach, Jan Strohschein, Andreas Bunte, Jörg Stork, Heide Faeskorn-Woyke, Natalia Moriz, Thomas Bartz-Beielstein
Abstract	This paper introduces CAAI, a novel cognitive architecture for artificial intelligence in cyber-physical production systems. The goal of the architecture is to reduce the implementation effort for the usage of artificial intelligence algorithms. The core of the CAAI is a cognitive module that processes declarative goals of the user, selects suitable models and algorithms, and creates a configuration for the execution of a processing pipeline on a big data platform. Constant observation and evaluation against performance criteria assess the performance of pipelines for many and varying use cases. Based on these evaluations, the pipelines are automatically adapted if necessary. The modular design with well-defined interfaces enables the reusability and extensibility of pipeline components. A big data platform implements this modular design supported by technologies such as Docker, Kubernetes, and Kafka for virtualization and orchestration of the individual components and their communication. The implementation of the architecture is evaluated using a real-world use case.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2003.00925v1
PDF	https://arxiv.org/pdf/2003.00925v1.pdf
PWC	https://paperswithcode.com/paper/caai-a-cognitive-architecture-to-introduce
Repo
Framework