April 1, 2020

3164 words 15 mins read

Paper Group ANR 457

Adaptive Conditional Neural Movement Primitives via Representation Sharing Between Supervised and Reinforcement Learning. Semantic Web Environments for Multi-Agent Systems: Enabling agents to use Web of Things via semantic web. Localization of Critical Findings in Chest X-Ray without Local Annotations Using Multi-Instance Learning. Hyperplane Arran …


Title	Adaptive Conditional Neural Movement Primitives via Representation Sharing Between Supervised and Reinforcement Learning
Authors	M. Tuluhan Akbulut, M. Yunus Seker, Ahmet E. Tekden, Yukie Nagai, Erhan Oztop, Emre Ugur
Abstract	Learning by Demonstration provides a sample efficient way to equip robots with complex sensorimotor skills in supervised manner. Several movement primitive representations can be used for flexible motor representation and learning. A recent state-of-the art approach is Conditional Neural Movement Primitives (CNMP) that can learn non-linear relations between environment parameters and complex multi-modal trajectories from a few expert demonstrations by forming powerful latent space representations. In this study, to improve the applicability of CNMP to changing tasks and/or environments, we couple it with a reinforcement learning agent that exploits the formed representations by the original CNMP network, and learns to generate synthetic demonstrations for further learning. This enables the CNMP network to generalize to new environments by adapting its internal representations. In the current implementation, the reinforcement learning agent is triggered when a failure in task execution is detected, and the CNMP is trained with the newly discovered demonstration (trajectory), which shares essential characteristics with the original demonstrations due to the representation sharing. As a result, the overall system increases its capacity and handle situations in scenarios where the initial CNMP network can not produce a useful trajectory. To show the validity of our proposed model, we compare our approach with original CNMP work and other movement primitives approaches. Furthermore, we presents the experimental results from the implementation of the proposed model on real robotics setups, which indicate the applicability of our approach as an effective adaptive learning by demonstration system.
Tasks
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11334v1
PDF	https://arxiv.org/pdf/2003.11334v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-conditional-neural-movement
Repo
Framework

Semantic Web Environments for Multi-Agent Systems: Enabling agents to use Web of Things via semantic web


Title	Semantic Web Environments for Multi-Agent Systems: Enabling agents to use Web of Things via semantic web
Authors	Alaa Daoud
Abstract	The Web is ubiquitous, increasingly populated with interconnected data, services, people, and objects. Semantic web technologies (SWT) promote uniformity of data formats, as well as modularization and reuse of specifications (e.g., ontologies), by allowing them to include and refer to information provided by other ontologies. In such a context, multi-agent system (MAS) technologies are the right abstraction for developing decentralized and open Web applications in which agents discover, reason and act on Web resources and cooperate with each other and with people. The aim of the project is to propose an approach to transform “Agent and artifact (A&A) meta-model” into a Web-readable format with ontologies in line with semantic web formats and to reuse already existing ontologies in order to provide uniform access for agents to things.
Tasks
Published	2020-02-20
URL	https://arxiv.org/abs/2003.02054v1
PDF	https://arxiv.org/pdf/2003.02054v1.pdf
PWC	https://paperswithcode.com/paper/semantic-web-environments-for-multi-agent
Repo
Framework

Localization of Critical Findings in Chest X-Ray without Local Annotations Using Multi-Instance Learning


Title	Localization of Critical Findings in Chest X-Ray without Local Annotations Using Multi-Instance Learning
Authors	Evan Schwab, André Gooßen, Hrishikesh Deshpande, Axel Saalbach
Abstract	The automatic detection of critical findings in chest X-rays (CXR), such as pneumothorax, is important for assisting radiologists in their clinical workflow like triaging time-sensitive cases and screening for incidental findings. While deep learning (DL) models has become a promising predictive technology with near-human accuracy, they commonly suffer from a lack of explainability, which is an important aspect for clinical deployment of DL models in the highly regulated healthcare industry. For example, localizing critical findings in an image is useful for explaining the predictions of DL classification algorithms. While there have been a host of joint classification and localization methods for computer vision, the state-of-the-art DL models require locally annotated training data in the form of pixel level labels or bounding box coordinates. In the medical domain, this requires an expensive amount of manual annotation by medical experts for each critical finding. This requirement becomes a major barrier for training models that can rapidly scale to various findings. In this work, we address these shortcomings with an interpretable DL algorithm based on multi-instance learning that jointly classifies and localizes critical findings in CXR without the need for local annotations. We show competitive classification results on three different critical findings (pneumothorax, pneumonia, and pulmonary edema) from three different CXR datasets.
Tasks
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08817v1
PDF	https://arxiv.org/pdf/2001.08817v1.pdf
PWC	https://paperswithcode.com/paper/localization-of-critical-findings-in-chest-x
Repo
Framework

Hyperplane Arrangements of Trained ConvNets Are Biased


Title	Hyperplane Arrangements of Trained ConvNets Are Biased
Authors	Matteo Gamba, Stefan Carlsson, Hossein Azizpour, Mårten Björkman
Abstract	We investigate the geometric properties of the functions learned by trained ConvNets in the preactivation space of their convolutional layers, by performing an empirical study of hyperplane arrangements induced by a convolutional layer. We introduce statistics over the weights of a trained network to study local arrangements and relate them to the training dynamics. We observe that trained ConvNets show a significant statistical bias towards regular hyperplane configurations. Furthermore, we find that layers showing biased configurations are critical to validation performance for the architectures considered, trained on CIFAR10, CIFAR100 and ImageNet.
Tasks
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07797v1
PDF	https://arxiv.org/pdf/2003.07797v1.pdf
PWC	https://paperswithcode.com/paper/hyperplane-arrangements-of-trained-convnets
Repo
Framework

Knowledge Graphs


Title	Knowledge Graphs
Authors	Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d’Amato, Gerard de Melo, Claudio Gutierrez, José Emilio Labra Gayo, Sabrina Kirrane, Sebastian Neumaier, Axel Polleres, Roberto Navigli, Axel-Cyrille Ngonga Ngomo, Sabbir M. Rashid, Anisa Rula, Lukas Schmelzeisen, Juan Sequeda, Steffen Staab, Antoine Zimmermann
Abstract	In this paper we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data. After a general introduction, we motivate and contrast various graph-based data models and query languages that are used for knowledge graphs. We discuss the roles of schema, identity, and context in knowledge graphs. We explain how knowledge can be represented and extracted using a combination of deductive and inductive techniques. We summarise methods for the creation, enrichment, quality assessment, refinement, and publication of knowledge graphs. We provide an overview of prominent open knowledge graphs and enterprise knowledge graphs, their applications, and how they use the aforementioned techniques. We conclude with high-level future research directions for knowledge graphs.
Tasks	Knowledge Graphs
Published	2020-03-04
URL	https://arxiv.org/abs/2003.02320v2
PDF	https://arxiv.org/pdf/2003.02320v2.pdf
PWC	https://paperswithcode.com/paper/knowledge-graphs
Repo
Framework

DeepQuarantine for Suspicious Mail


Title	DeepQuarantine for Suspicious Mail
Authors	Nikita Benkovich, Roman Dedenok, Dmitry Golubev
Abstract	In this paper, we introduce DeepQuarantine (DQ), a cloud technology to detect and quarantine potential spam messages. Spam attacks are becoming more diverse and can potentially be harmful to email users. Despite the high quality and performance of spam filtering systems, detection of a spam campaign can take some time. Unfortunately, in this case some unwanted messages get delivered to users. To solve this problem, we created DQ, which detects potential spam and keeps it in a special Quarantine folder for a while. The time gained allows us to double-check the messages to improve the reliability of the anti-spam solution. Due to high precision of the technology, most of the quarantined mail is spam, which allows clients to use email without delay. Our solution is based on applying Convolutional Neural Networks on MIME headers to extract deep features from large-scale historical data. We evaluated the proposed method on real-world data and showed that DQ enhances the quality of spam detection.
Tasks
Published	2020-01-13
URL	https://arxiv.org/abs/2001.04168v1
PDF	https://arxiv.org/pdf/2001.04168v1.pdf
PWC	https://paperswithcode.com/paper/deepquarantine-for-suspicious-mail
Repo
Framework

Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation


Title	Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
Authors	Byung Hoon Ahn, Prannoy Pilligundla, Amir Yazdanbakhsh, Hadi Esmaeilzadeh
Abstract	Achieving faster execution with shorter compilation time can foster further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional compilation heuristics, or very recently genetic algorithms and other stochastic methods. These methods suffer from frequent costly hardware measurements rendering them not only too time consuming but also suboptimal. As such, we devise a solution that can learn to quickly adapt to a previously unseen design space for code optimization, both accelerating the search and improving the output performance. This solution dubbed Chameleon leverages reinforcement learning whose solution takes fewer steps to converge, and develops an adaptive sampling algorithm that not only focuses on the costly samples (real hardware measurements) on representative points but also uses a domain-knowledge inspired logic to improve the samples itself. Experimentation with real hardware shows that Chameleon provides 4.45x speed up in optimization time over AutoTVM, while also improving inference time of the modern deep networks by 5.6%.
Tasks
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08743v1
PDF	https://arxiv.org/pdf/2001.08743v1.pdf
PWC	https://paperswithcode.com/paper/chameleon-adaptive-code-optimization-for-1
Repo
Framework

Equivalence relations and $L^p$ distances between time series


Title	Equivalence relations and $L^p$ distances between time series
Authors	Nick James, Max Menzies
Abstract	We introduce a general framework for defining equivalence and measuring distances between time series, and a first concrete method for doing so. We prove the existence of equivalence relations on the space of time series, such that the quotient spaces can be equipped with a metrizable topology. We illustrate algorithmically how to calculate such distances among a collection of time series, and perform clustering analysis based on these distances. We apply these insights to analyse the recent bushfires in NSW, Australia. There, we introduce a new method to analyse time series in a cross-contextual setting.
Tasks	Time Series
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02592v1
PDF	https://arxiv.org/pdf/2002.02592v1.pdf
PWC	https://paperswithcode.com/paper/equivalence-relations-and-lp-distances
Repo
Framework

Deep learning-based prediction of response to HER2-targeted neoadjuvant chemotherapy from pre-treatment dynamic breast MRI: A multi-institutional validation study


Title	Deep learning-based prediction of response to HER2-targeted neoadjuvant chemotherapy from pre-treatment dynamic breast MRI: A multi-institutional validation study
Authors	Nathaniel Braman, Mohammed El Adoui, Manasa Vulchi, Paulette Turk, Maryam Etesami, Pingfu Fu, Kaustav Bera, Stylianos Drisis, Vinay Varadan, Donna Plecha, Mohammed Benjelloun, Jame Abraham, Anant Madabhushi
Abstract	Predicting response to neoadjuvant therapy is a vexing challenge in breast cancer. In this study, we evaluate the ability of deep learning to predict response to HER2-targeted neo-adjuvant chemotherapy (NAC) from pre-treatment dynamic contrast-enhanced (DCE) MRI acquired prior to treatment. In a retrospective study encompassing DCE-MRI data from a total of 157 HER2+ breast cancer patients from 5 institutions, we developed and validated a deep learning approach for predicting pathological complete response (pCR) to HER2-targeted NAC prior to treatment. 100 patients who received HER2-targeted neoadjuvant chemotherapy at a single institution were used to train (n=85) and tune (n=15) a convolutional neural network (CNN) to predict pCR. A multi-input CNN leveraging both pre-contrast and late post-contrast DCE-MRI acquisitions was identified to achieve optimal response prediction within the validation set (AUC=0.93). This model was then tested on two independent testing cohorts with pre-treatment DCE-MRI data. It achieved strong performance in a 28 patient testing set from a second institution (AUC=0.85, 95% CI 0.67-1.0, p=.0008) and a 29 patient multicenter trial including data from 3 additional institutions (AUC=0.77, 95% CI 0.58-0.97, p=0.006). Deep learning-based response prediction model was found to exceed a multivariable model incorporating predictive clinical variables (AUC < .65 in testing cohorts) and a model of semi-quantitative DCE-MRI pharmacokinetic measurements (AUC < .60 in testing cohorts). The results presented in this work across multiple sites suggest that with further validation deep learning could provide an effective and reliable tool to guide targeted therapy in breast cancer, thus reducing overtreatment among HER2+ patients.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08570v1
PDF	https://arxiv.org/pdf/2001.08570v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-prediction-of-response-to
Repo
Framework

Reduction of Surgical Risk Through the Evaluation of Medical Imaging Diagnostics


Title	Reduction of Surgical Risk Through the Evaluation of Medical Imaging Diagnostics
Authors	Marco A. V. M. Grinet, Nuno M. Garcia, Ana I. R. Gouveia, Jose A. F. Moutinho, Abel J. P. Gomes
Abstract	Computer aided diagnosis (CAD) of Breast Cancer (BRCA) images has been an active area of research in recent years. The main goals of this research is to develop reliable automatic methods for detecting and diagnosing different types of BRCA from diagnostic images. In this paper, we present a review of the state of the art CAD methods applied to magnetic resonance (MRI) and mammography images of BRCA patients. The review aims to provide an extensive introduction to different features extracted from BRCA images through texture and statistical analysis and to categorize deep learning frameworks and data structures capable of using metadata to aggregate relevant information to assist oncologists and radiologists. We divide the existing literature according to the imaging modality and into radiomics, machine learning, or combination of both. We also emphasize the difference between each modality and methods strengths and weaknesses and analyze their performance in detecting BRCA through a quantitative comparison. We compare the results of various approaches for implementing CAD systems for the detection of BRCA. Each approachs standard workflow components are reviewed and summary tables provided. We present an extensive literature review of radiomics feature extraction techniques and machine learning methods applied in BRCA diagnosis and detection, focusing on data preparation, data structures, pre processing and post processing strategies available in the literature. There is a growing interest on radiomic feature extraction and machine learning methods for BRCA detection through histopathological images, MRI and mammography images. However, there isnt a CAD method able to combine distinct data types to provide the best diagnostic results. Employing data fusion techniques to medical images and patient data could lead to improved detection and classification results.
Tasks
Published	2020-03-08
URL	https://arxiv.org/abs/2003.08748v1
PDF	https://arxiv.org/pdf/2003.08748v1.pdf
PWC	https://paperswithcode.com/paper/reduction-of-surgical-risk-through-the
Repo
Framework

Volumization as a Natural Generalization of Weight Decay


Title	Volumization as a Natural Generalization of Weight Decay
Authors	Liu Ziyin, Zihao Wang, Makoto Yamada, Masahito Ueda
Abstract	We propose a novel regularization method, called \textit{volumization}, for neural networks. Inspired by physics, we define a physical volume for the weight parameters in neural networks, and we show that this method is an effective way of regularizing neural networks. Intuitively, this method interpolates between an $L_2$ and $L_\infty$ regularization. Therefore, weight decay and weight clipping become special cases of the proposed algorithm. We prove, on a toy example, that the essence of this method is a regularization technique to control bias-variance tradeoff. The method is shown to do well in the categories where the standard weight decay method is shown to work well, including improving the generalization of networks and preventing memorization. Moreover, we show that the volumization might lead to a simple method for training a neural network whose weight is binary or ternary.
Tasks
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11243v2
PDF	https://arxiv.org/pdf/2003.11243v2.pdf
PWC	https://paperswithcode.com/paper/volumization-as-a-natural-generalization-of
Repo
Framework

Attention Flow: End-to-End Joint Attention Estimation


Title	Attention Flow: End-to-End Joint Attention Estimation
Authors	Ömer Sümer, Peter Gerjets, Ulrich Trautwein, Enkelejda Kasneci
Abstract	This paper addresses the problem of understanding joint attention in third-person social scene videos. Joint attention is the shared gaze behaviour of two or more individuals on an object or an area of interest and has a wide range of applications such as human-computer interaction, educational assessment, treatment of patients with attention disorders, and many more. Our method, Attention Flow, learns joint attention in an end-to-end fashion by using saliency-augmented attention maps and two novel convolutional attention mechanisms that determine to select relevant features and improve joint attention localization. We compare the effect of saliency maps and attention mechanisms and report quantitative and qualitative results on the detection and localization of joint attention in the VideoCoAtt dataset, which contains complex social scenes.
Tasks
Published	2020-01-12
URL	https://arxiv.org/abs/2001.03960v1
PDF	https://arxiv.org/pdf/2001.03960v1.pdf
PWC	https://paperswithcode.com/paper/attention-flow-end-to-end-joint-attention
Repo
Framework

Hybrid modeling: Applications in real-time diagnosis


Title	Hybrid modeling: Applications in real-time diagnosis
Authors	Ion Matei, Johan de Kleer, Alexander Feldman, Rahul Rai, Souma Chowdhury
Abstract	Reduced-order models that accurately abstract high fidelity models and enable faster simulation is vital for real-time, model-based diagnosis applications. In this paper, we outline a novel hybrid modeling approach that combines machine learning inspired models and physics-based models to generate reduced-order models from high fidelity models. We are using such models for real-time diagnosis applications. Specifically, we have developed machine learning inspired representations to generate reduced order component models that preserve, in part, the physical interpretation of the original high fidelity component models. To ensure the accuracy, scalability and numerical stability of the learning algorithms when training the reduced-order models we use optimization platforms featuring automatic differentiation. Training data is generated by simulating the high-fidelity model. We showcase our approach in the context of fault diagnosis of a rail switch system. Three new model abstractions whose complexities are two orders of magnitude smaller than the complexity of the high fidelity model, both in the number of equations and simulation time are shown. The numerical experiments and results demonstrate the efficacy of the proposed hybrid modeling approach.
Tasks
Published	2020-03-04
URL	https://arxiv.org/abs/2003.02671v1
PDF	https://arxiv.org/pdf/2003.02671v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-modeling-applications-in-real-time
Repo
Framework

Nonconvex Matrix Completion with Linearly Parameterized Factors


Title	Nonconvex Matrix Completion with Linearly Parameterized Factors
Authors	Ji Chen, Xiaodong Li, Zongming Ma
Abstract	Techniques of matrix completion aim to impute a large portion of missing entries in a data matrix through a small portion of observed ones, with broad machine learning applications including collaborative filtering, pairwise ranking, etc. In practice, additional structures are usually employed in order to improve the accuracy of matrix completion. Examples include subspace constraints formed by side information in collaborative filtering, and skew symmetry in pairwise ranking. This paper performs a unified analysis of nonconvex matrix completion with linearly parameterized factorization, which covers the aforementioned examples as special cases. Importantly, uniform upper bounds for estimation errors are established for all local minima, provided that the sampling rate satisfies certain conditions determined by the rank, condition number, and incoherence parameter of the ground-truth low rank matrix. Empirical efficiency of the proposed method is further illustrated by numerical simulations.
Tasks	Matrix Completion
Published	2020-03-29
URL	https://arxiv.org/abs/2003.13153v1
PDF	https://arxiv.org/pdf/2003.13153v1.pdf
PWC	https://paperswithcode.com/paper/nonconvex-matrix-completion-with-linearly
Repo
Framework

Solving the Robust Matrix Completion Problem via a System of Nonlinear Equations


Title	Solving the Robust Matrix Completion Problem via a System of Nonlinear Equations
Authors	Yunfeng Cai, Ping Li
Abstract	We consider the problem of robust matrix completion, which aims to recover a low rank matrix $L_$ and a sparse matrix $S_$ from incomplete observations of their sum $M=L_+S_\in\mathbb{R}^{m\times n}$. Algorithmically, the robust matrix completion problem is transformed into a problem of solving a system of nonlinear equations, and the alternative direction method is then used to solve the nonlinear equations. In addition, the algorithm is highly parallelizable and suitable for large scale problems. Theoretically, we characterize the sufficient conditions for when $L_$ can be approximated by a low rank approximation of the observed $M_$. And under proper assumptions, it is shown that the algorithm converges to the true solution linearly. Numerical simulations show that the simple method works as expected and is comparable with state-of-the-art methods.
Tasks	Matrix Completion
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10992v1
PDF	https://arxiv.org/pdf/2003.10992v1.pdf
PWC	https://paperswithcode.com/paper/solving-the-robust-matrix-completion-problem
Repo
Framework