April 1, 2020

3080 words 15 mins read

Paper Group ANR 443

COPT: Coordinated Optimal Transport on Graphs. Microvascular Dynamics from 4D Microscopy Using Temporal Segmentation. TopRank+: A Refinement of TopRank Algorithm. Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors. Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping. SOM- …

COPT: Coordinated Optimal Transport on Graphs


Title	COPT: Coordinated Optimal Transport on Graphs
Authors	Yihe Dong, Will Sawin
Abstract	We introduce COPT, a novel distance metric between graphs defined via an optimization routine, computing a coordinated pair of optimal transport maps simultaneously. This is an unsupervised way to learn general-purpose graph representations, it can be used for both graph sketching and graph comparison. COPT involves simultaneously optimizing dual transport plans, one between the vertices of two graphs, and another between graph signal probability distributions. We show both theoretically and empirically that our method preserves important global structural information on graphs, in particular spectral information, making it well-suited for tasks on graphs including retrieval, classification, summarization, and visualization.
Tasks
Published	2020-03-09
URL	https://arxiv.org/abs/2003.03892v1
PDF	https://arxiv.org/pdf/2003.03892v1.pdf
PWC	https://paperswithcode.com/paper/copt-coordinated-optimal-transport-on-graphs
Repo
Framework

Microvascular Dynamics from 4D Microscopy Using Temporal Segmentation


Title	Microvascular Dynamics from 4D Microscopy Using Temporal Segmentation
Authors	Shir Gur, Lior Wolf, Lior Golgher, Pablo Blinder
Abstract	Recently developed methods for rapid continuous volumetric two-photon microscopy facilitate the observation of neuronal activity in hundreds of individual neurons and changes in blood flow in adjacent blood vessels across a large volume of living brain at unprecedented spatio-temporal resolution. However, the high imaging rate necessitates fully automated image analysis, whereas tissue turbidity and photo-toxicity limitations lead to extremely sparse and noisy imagery. In this work, we extend a recently proposed deep learning volumetric blood vessel segmentation network, such that it supports temporal analysis. With this technology, we are able to track changes in cerebral blood volume over time and identify spontaneous arterial dilations that propagate towards the pial surface. This new capability is a promising step towards characterizing the hemodynamic response function upon which functional magnetic resonance imaging (fMRI) is based.
Tasks
Published	2020-01-14
URL	https://arxiv.org/abs/2001.05076v1
PDF	https://arxiv.org/pdf/2001.05076v1.pdf
PWC	https://paperswithcode.com/paper/microvascular-dynamics-from-4d-microscopy
Repo
Framework


Title	TopRank+: A Refinement of TopRank Algorithm
Authors	Victor de la Pena, Haolin Zou
Abstract	Online learning to rank is a core problem in machine learning. In Lattimore et al. (2018), a novel online learning algorithm was proposed based on topological sorting. In the paper they provided a set of self-normalized inequalities (a) in the algorithm as a criterion in iterations and (b) to provide an upper bound for cumulative regret, which is a measure of algorithm performance. In this work, we utilized method of mixtures and asymptotic expansions of certain implicit function to provide a tighter, iterated-log-like boundary for the inequalities, and as a consequence improve both the algorithm itself as well as its performance estimation.
Tasks	Learning-To-Rank
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07617v1
PDF	https://arxiv.org/pdf/2001.07617v1.pdf
PWC	https://paperswithcode.com/paper/toprank-a-refinement-of-toprank-algorithm
Repo
Framework

Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors


Title	Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors
Authors	Raphael Köster, Dylan Hadfield-Menell, Gillian K. Hadfield, Joel Z. Leibo
Abstract	How can societies learn to enforce and comply with social norms? Here we investigate the learning dynamics and emergence of compliance and enforcement of social norms in a foraging game, implemented in a multi-agent reinforcement learning setting. In this spatiotemporally extended game, individuals are incentivized to implement complex berry-foraging policies and punish transgressions against social taboos covering specific berry types. We show that agents benefit when eating poisonous berries is taboo, meaning the behavior is punished by other agents, as this helps overcome a credit-assignment problem in discovering delayed health effects. Critically, however, we also show that introducing an additional taboo, which results in punishment for eating a harmless berry, improves the rate and stability with which agents learn to punish taboo violations and comply with taboos. Counterintuitively, our results show that an arbitrary taboo (a “silly rule”) can enhance social learning dynamics and achieve better outcomes in the middle stages of learning. We discuss the results in the context of studying normativity as a group-level emergent phenomenon.
Tasks	Multi-agent Reinforcement Learning
Published	2020-01-25
URL	https://arxiv.org/abs/2001.09318v1
PDF	https://arxiv.org/pdf/2001.09318v1.pdf
PWC	https://paperswithcode.com/paper/silly-rules-improve-the-capacity-of-agents-to
Repo
Framework

Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping


Title	Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping
Authors	Eugenio Bargiacchi, Timothy Verstraeten, Diederik M. Roijers, Ann Nowé
Abstract	We present a new model-based reinforcement learning algorithm, Cooperative Prioritized Sweeping, for efficient learning in multi-agent Markov decision processes. The algorithm allows for sample-efficient learning on large problems by exploiting a factorization to approximate the value function. Our approach only requires knowledge about the structure of the problem in the form of a dynamic decision network. Using this information, our method learns a model of the environment and performs temporal difference updates which affect multiple joint states and actions at once. Batch updates are additionally performed which efficiently back-propagate knowledge throughout the factored Q-function. Our method outperforms the state-of-the-art algorithm sparse cooperative Q-learning algorithm, both on the well-known SysAdmin benchmark and randomized environments.
Tasks	Multi-agent Reinforcement Learning, Q-Learning
Published	2020-01-15
URL	https://arxiv.org/abs/2001.07527v1
PDF	https://arxiv.org/pdf/2001.07527v1.pdf
PWC	https://paperswithcode.com/paper/model-based-multi-agent-reinforcement
Repo
Framework

SOM-based DDoS Defense Mechanism using SDN for the Internet of Things


Title	SOM-based DDoS Defense Mechanism using SDN for the Internet of Things
Authors	Yunfei Meng, Zhiqiu Huang, Senzhang Wang, Guohua Shen, Changbo Ke
Abstract	To effectively tackle the security threats towards the Internet of things, we propose a SOM-based DDoS defense mechanism using software-defined networking (SDN) in this paper. The main idea of the mechanism is to deploy a SDN-based gateway to protect the device services in the Internet of things. The gateway provides DDoS defense mechanism based on SOM neural network. By means of SOM-based DDoS defense mechanism, the gateway can effectively identify the malicious sensing devices in the IoT, and automatically block those malicious devices after detecting them, so that it can effectively enforce the security and robustness of the system when it is under DDoS attacks. In order to validate the feasibility and effectiveness of the mechanism, we leverage POX controller and Mininet emulator to implement an experimental system, and further implement the aforementioned security enforcement mechanisms with Python. The final experimental results illustrate that the mechanism is truly effective under the different test scenarios.
Tasks
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06834v2
PDF	https://arxiv.org/pdf/2003.06834v2.pdf
PWC	https://paperswithcode.com/paper/som-based-ddos-defense-mechanism-using-sdn
Repo
Framework

Effect of top-down connections in Hierarchical Sparse Coding


Title	Effect of top-down connections in Hierarchical Sparse Coding
Authors	Victor Boutin, Angelo Franciosini, Franck Ruffier, Laurent Perrinet
Abstract	Hierarchical Sparse Coding (HSC) is a powerful model to efficiently represent multi-dimensional, structured data such as images. The simplest solution to solve this computationally hard problem is to decompose it into independent layer-wise subproblems. However, neuroscientific evidence would suggest inter-connecting these subproblems as in the Predictive Coding (PC) theory, which adds top-down connections between consecutive layers. In this study, a new model called 2-Layers Sparse Predictive Coding (2L-SPC) is introduced to assess the impact of this inter-layer feedback connection. In particular, the 2L-SPC is compared with a Hierarchical Lasso (Hi-La) network made out of a sequence of independent Lasso layers. The 2L-SPC and the 2-layers Hi-La networks are trained on 4 different databases and with different sparsity parameters on each layer. First, we show that the overall prediction error generated by 2L-SPC is lower thanks to the feedback mechanism as it transfers prediction error between layers. Second, we demonstrate that the inference stage of the 2L-SPC is faster to converge than for the Hi-La model. Third, we show that the 2L-SPC also accelerates the learning process. Finally, the qualitative analysis of both models dictionaries, supported by their activation probability, show that the 2L-SPC features are more generic and informative.
Tasks
Published	2020-02-03
URL	https://arxiv.org/abs/2002.00892v1
PDF	https://arxiv.org/pdf/2002.00892v1.pdf
PWC	https://paperswithcode.com/paper/effect-of-top-down-connections-in-1
Repo
Framework

Patient-Specific Finetuning of Deep Learning Models for Adaptive Radiotherapy in Prostate CT


Title	Patient-Specific Finetuning of Deep Learning Models for Adaptive Radiotherapy in Prostate CT
Authors	Mohamed S. Elmahdy, Tanuj Ahuja, U. A. van der Heide, Marius Staring
Abstract	Contouring of the target volume and Organs-At-Risk (OARs) is a crucial step in radiotherapy treatment planning. In an adaptive radiotherapy setting, updated contours need to be generated based on daily imaging. In this work, we leverage personalized anatomical knowledge accumulated over the treatment sessions, to improve the segmentation accuracy of a pre-trained Convolution Neural Network (CNN), for a specific patient. We investigate a transfer learning approach, fine-tuning the baseline CNN model to a specific patient, based on imaging acquired in earlier treatment fractions. The baseline CNN model is trained on a prostate CT dataset from one hospital of 379 patients. This model is then fine-tuned and tested on an independent dataset of another hospital of 18 patients, each having 7 to 10 daily CT scans. For the prostate, seminal vesicles, bladder and rectum, the model fine-tuned on each specific patient achieved a Mean Surface Distance (MSD) of $1.64 \pm 0.43$ mm, $2.38 \pm 2.76$ mm, $2.30 \pm 0.96$ mm, and $1.24 \pm 0.89$ mm, respectively, which was significantly better than the baseline model. The proposed personalized model adaptation is therefore very promising for clinical implementation in the context of adaptive radiotherapy of prostate cancer.
Tasks	Transfer Learning
Published	2020-02-17
URL	https://arxiv.org/abs/2002.06927v1
PDF	https://arxiv.org/pdf/2002.06927v1.pdf
PWC	https://paperswithcode.com/paper/patient-specific-finetuning-of-deep-learning
Repo
Framework

Learning from Suspected Target: Bootstrapping Performance for Breast Cancer Detection in Mammography


Title	Learning from Suspected Target: Bootstrapping Performance for Breast Cancer Detection in Mammography
Authors	Li Xiao, Cheng Zhu, Junjun Liu, Chunlong Luo, Peifang Liu, Yi Zhao
Abstract	Deep learning object detection algorithm has been widely used in medical image analysis. Currently all the object detection tasks are based on the data annotated with object classes and their bounding boxes. On the other hand, medical images such as mammography usually contain normal regions or objects that are similar to the lesion region, and may be misclassified in the testing stage if they are not taken care of. In this paper, we address such problem by introducing a novel top likelihood loss together with a new sampling procedure to select and train the suspected target regions, as well as proposing a similarity loss to further identify suspected targets from targets. Mean average precision (mAP) according to the predicted targets and specificity, sensitivity, accuracy, AUC values according to classification of patients are adopted for performance comparisons. We firstly test our proposed method on a private dense mammogram dataset. Results show that our proposed method greatly reduce the false positive rate and the specificity is increased by 0.25 on detecting mass type cancer. It is worth mention that dense breast typically has a higher risk for developing breast cancers and also are harder for cancer detection in diagnosis, and our method outperforms a reported result from performance of radiologists. Our method is also validated on the public Digital Database for Screening Mammography (DDSM) dataset, brings significant improvement on mass type cancer detection and outperforms the most state-of-the-art work.
Tasks	Breast Cancer Detection, Object Detection
Published	2020-03-01
URL	https://arxiv.org/abs/2003.01109v1
PDF	https://arxiv.org/pdf/2003.01109v1.pdf
PWC	https://paperswithcode.com/paper/learning-from-suspected-target-bootstrapping
Repo
Framework

A deep learning framework for solution and discovery in solid mechanics: linear elasticity


Title	A deep learning framework for solution and discovery in solid mechanics: linear elasticity
Authors	Ehsan Haghighat, Maziar Raissi, Adrian Moure, Hector Gomez, Ruben Juanes
Abstract	We present the application of a class of deep learning, known as Physics Informed Neural Networks (PINN), to learning and discovery in solid mechanics. We explain how to incorporate the momentum balance and constitutive relations into PINN, and explore in detail the application to linear elasticity, although the framework is rather general and can be extended to other solid-mechanics problems. While common PINN algorithms are based on training one deep neural network (DNN), we propose a multi-network model that results in more accurate representation of the field variables. To validate the model, we test the framework on synthetic data generated from analytical and numerical reference solutions. We study convergence of the PINN model, and show that Isogeometric Analysis (IGA) results in superior accuracy and convergence characteristics compared with classic low-order Finite Element Method (FEM). We also show the applicability of the framework for transfer learning, and find vastly accelerated convergence during network re-training. Finally, we find that honoring the physics leads to improved robustness: when trained only on a few parameters, we find that the PINN model can accurately predict the solution for a wide range of parameters new to the network—thus pointing to an important application of this framework to sensitivity analysis and surrogate modeling.
Tasks	Transfer Learning
Published	2020-02-14
URL	https://arxiv.org/abs/2003.02751v1
PDF	https://arxiv.org/pdf/2003.02751v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-framework-for-solution-and
Repo
Framework

2D Convolutional Neural Networks for 3D Digital Breast Tomosynthesis Classification


Title	2D Convolutional Neural Networks for 3D Digital Breast Tomosynthesis Classification
Authors	Yu Zhang, Xiaoqin Wang, Hunter Blanton, Gongbo Liang, Xin Xing, Nathan Jacobs
Abstract	Automated methods for breast cancer detection have focused on 2D mammography and have largely ignored 3D digital breast tomosynthesis (DBT), which is frequently used in clinical practice. The two key challenges in developing automated methods for DBT classification are handling the variable number of slices and retaining slice-to-slice changes. We propose a novel deep 2D convolutional neural network (CNN) architecture for DBT classification that simultaneously overcomes both challenges. Our approach operates on the full volume, regardless of the number of slices, and allows the use of pre-trained 2D CNNs for feature extraction, which is important given the limited amount of annotated training data. In an extensive evaluation on a real-world clinical dataset, our approach achieves 0.854 auROC, which is 28.80% higher than approaches based on 3D CNNs. We also find that these improvements are stable across a range of model configurations.
Tasks	Breast Cancer Detection
Published	2020-02-27
URL	https://arxiv.org/abs/2002.12314v1
PDF	https://arxiv.org/pdf/2002.12314v1.pdf
PWC	https://paperswithcode.com/paper/2d-convolutional-neural-networks-for-3d
Repo
Framework

Finite-time Identification of Stable Linear Systems: Optimality of the Least-Squares Estimator


Title	Finite-time Identification of Stable Linear Systems: Optimality of the Least-Squares Estimator
Authors	Yassir Jedra, Alexandre Proutiere
Abstract	We present a new finite-time analysis of the estimation error of the Ordinary Least Squares (OLS) estimator for stable linear time-invariant systems. We characterize the number of observed samples (the length of the observed trajectory) sufficient for the OLS estimator to be $(\varepsilon,\delta)$-PAC, i.e., to yield an estimation error less than $\varepsilon$ with probability at least $1-\delta$. We show that this number matches existing sample complexity lower bounds [1,2] up to universal multiplicative factors (independent of ($\varepsilon,\delta)$ and of the system). This paper hence establishes the optimality of the OLS estimator for stable systems, a result conjectured in [1]. Our analysis of the performance of the OLS estimator is simpler, sharper, and easier to interpret than existing analyses. It relies on new concentration results for the covariates matrix.
Tasks
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07937v3
PDF	https://arxiv.org/pdf/2003.07937v3.pdf
PWC	https://paperswithcode.com/paper/finite-time-identification-of-stable-linear
Repo
Framework

DeepFactors: Real-Time Probabilistic Dense Monocular SLAM


Title	DeepFactors: Real-Time Probabilistic Dense Monocular SLAM
Authors	Jan Czarnowski, Tristan Laidlow, Ronald Clark, Andrew J. Davison
Abstract	The ability to estimate rich geometry and camera motion from monocular imagery is fundamental to future interactive robotics and augmented reality applications. Different approaches have been proposed that vary in scene geometry representation (sparse landmarks, dense maps), the consistency metric used for optimising the multi-view problem, and the use of learned priors. We present a SLAM system that unifies these methods in a probabilistic framework while still maintaining real-time performance. This is achieved through the use of a learned compact depth map representation and reformulating three different types of errors: photometric, reprojection and geometric, which we make use of within standard factor graph software. We evaluate our system on trajectory estimation and depth reconstruction on real-world sequences and present various examples of estimated dense geometry.
Tasks
Published	2020-01-14
URL	https://arxiv.org/abs/2001.05049v1
PDF	https://arxiv.org/pdf/2001.05049v1.pdf
PWC	https://paperswithcode.com/paper/deepfactors-real-time-probabilistic-dense
Repo
Framework

Joint 2D-3D Breast Cancer Classification


Title	Joint 2D-3D Breast Cancer Classification
Authors	Gongbo Liang, Xiaoqin Wang, Yu Zhang, Xin Xing, Hunter Blanton, Tawfiq Salem, Nathan Jacobs
Abstract	Breast cancer is the malignant tumor that causes the highest number of cancer deaths in females. Digital mammograms (DM or 2D mammogram) and digital breast tomosynthesis (DBT or 3D mammogram) are the two types of mammography imagery that are used in clinical practice for breast cancer detection and diagnosis. Radiologists usually read both imaging modalities in combination; however, existing computer-aided diagnosis tools are designed using only one imaging modality. Inspired by clinical practice, we propose an innovative convolutional neural network (CNN) architecture for breast cancer classification, which uses both 2D and 3D mammograms, simultaneously. Our experiment shows that the proposed method significantly improves the performance of breast cancer classification. By assembling three CNN classifiers, the proposed model achieves 0.97 AUC, which is 34.72% higher than the methods using only one imaging modality.
Tasks	Breast Cancer Detection
Published	2020-02-27
URL	https://arxiv.org/abs/2002.12392v1
PDF	https://arxiv.org/pdf/2002.12392v1.pdf
PWC	https://paperswithcode.com/paper/joint-2d-3d-breast-cancer-classification
Repo
Framework

An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environments


Title	An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environments
Authors	Javier Naranjo-Alcazar, Sergi Perez-Castanos, Pedro Zuccarrello, Maximo Cobos
Abstract	The problem of training a deep neural network with a small set of positive samples is known as few-shot learning (FSL). It is widely known that traditional deep learning (DL) algorithms usually show very good performance when trained with large datasets. However, in many applications, it is not possible to obtain such a high number of samples. In the image domain, typical FSL applications are those related to face recognition. In the audio domain, music fraud or speaker recognition can be clearly benefited from FSL methods. This paper deals with the application of FSL to the detection of specific and intentional acoustic events given by different types of sound alarms, such as door bells or fire alarms, using a limited number of samples. These sounds typically occur in domestic environments where many events corresponding to a wide variety of sound classes take place. Therefore, the detection of such alarms in a practical scenario can be considered an open-set recognition (OSR) problem. To address the lack of a dedicated public dataset for audio FSL, researchers usually make modifications on other available datasets. This paper is aimed at providing the audio recognition community with a carefully annotated dataset for FSL and OSR comprised of 1360 clips from 34 classes divided into pattern sounds and unwanted sounds. To facilitate and promote research in this area, results with two baseline systems (one trained from scratch and another based on transfer learning), are presented.
Tasks	Face Recognition, Few-Shot Learning, Open Set Learning, Speaker Recognition, Transfer Learning
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11561v6
PDF	https://arxiv.org/pdf/2002.11561v6.pdf
PWC	https://paperswithcode.com/paper/an-open-set-recognition-and-few-shot-learning
Repo
Framework