January 27, 2020

3308 words 16 mins read

Paper Group ANR 1092

Brain Network Construction and Classification Toolbox (BrainNetClass). Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale. Revealing posturographic features associated with the risk of falling in patients with Parkinsonian syndromes via machine learning. Learning High-fidelity Light Field Images From Hybrid Inputs. ArduC …

Brain Network Construction and Classification Toolbox (BrainNetClass)


Title	Brain Network Construction and Classification Toolbox (BrainNetClass)
Authors	Zhen Zhou, Xiaobo Chen, Yu Zhang, Lishan Qiao, Renping Yu, Gang Pan, Han Zhang, Dinggang Shen
Abstract	Brain functional network has become an increasingly used approach in understanding brain functions and diseases. Many network construction methods have been developed, whereas the majority of the studies still used static pairwise Pearson’s correlation-based functional connectivity. The goal of this work is to introduce a toolbox namely “Brain Network Construction and Classification” (BrainNetClass) to the field to promote more advanced brain network construction methods. It comprises various brain network construction methods, including some state-of-the-art methods that were recently developed to capture more complex interactions among brain regions along with connectome feature extraction, reduction, parameter optimization towards network-based individualized classification. BrainNetClass is a MATLAB-based, open-source, cross-platform toolbox with graphical user-friendly interfaces for cognitive and clinical neuroscientists to perform rigorous computer-aided diagnosis with interpretable result presentations even though they do not possess neuroimage computing and machine learning knowledge. We demonstrate the implementations of this toolbox on real resting-state functional MRI datasets. BrainNetClass (v1.0) can be downloaded from https://github.com/zzstefan/BrainNetClass.
Tasks
Published	2019-06-17
URL	https://arxiv.org/abs/1906.09908v1
PDF	https://arxiv.org/pdf/1906.09908v1.pdf
PWC	https://paperswithcode.com/paper/brain-network-construction-and-classification
Repo
Framework

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale


Title	Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale
Authors	Atılım Güneş Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Lawrence Meadows, Jialin Liu, Andreas Munk, Saeid Naderiparizi, Bradley Gram-Hansen, Gilles Louppe, Mingfei Ma, Xiaohui Zhao, Philip Torr, Victor Lee, Kyle Cranmer, Prabhat, Frank Wood
Abstract	Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models. However, applications to science remain limited because of the impracticability of rewriting complex scientific simulators in a PPL, the computational cost of inference, and the lack of scalable implementations. To address these, we present a novel PPL framework that couples directly to existing scientific simulators through a cross-platform probabilistic execution protocol and provides Markov chain Monte Carlo (MCMC) and deep-learning-based inference compilation (IC) engines for tractable inference. To guide IC inference, we perform distributed training of a dynamic 3DCNN–LSTM architecture with a PyTorch-MPI-based framework on 1,024 32-core CPU nodes of the Cori supercomputer with a global minibatch size of 128k: achieving a performance of 450 Tflop/s through enhancements to PyTorch. We demonstrate a Large Hadron Collider (LHC) use-case with the C++ Sherpa simulator and achieve the largest-scale posterior inference in a Turing-complete PPL.
Tasks	Bayesian Inference, Probabilistic Programming
Published	2019-07-08
URL	https://arxiv.org/abs/1907.03382v2
PDF	https://arxiv.org/pdf/1907.03382v2.pdf
PWC	https://paperswithcode.com/paper/etalumis-bringing-probabilistic-programming
Repo
Framework

Revealing posturographic features associated with the risk of falling in patients with Parkinsonian syndromes via machine learning


Title	Revealing posturographic features associated with the risk of falling in patients with Parkinsonian syndromes via machine learning
Authors	Ioannis Bargiotas, Argyris Kalogeratos, Myrto Limnios, Pierre-Paul Vidal, Damien Ricard, Nicolas Vayatis
Abstract	Falling in Parkinsonian syndromes (PS) is associated with postural instability and consists a common cause of disability among PS patients. Current posturographic practices record the body’s center-of-pressure displacement (statokinesigram) while the patient stands on a force platform. Statokinesigrams, after appropriate signal processing, can offer numerous posturographic features, which however challenges the efforts for valid statistics via standard univariate approaches. In this work, we present the ts-AUC, a non-parametric multivariate two-sample test, which we employ to analyze statokinesigram differences among PS patients that are fallers (PSf) and non-fallers (PSNF). We included 123 PS patients who were classified into PSF or PSNF based on clinical assessment and underwent simple Romberg Test (eyes open/eyes closed). We analyzed posturographic features using both multiple testing with p-value adjustment and the ts-AUC. While the ts-AUC showed significant difference between groups (p-value = 0.01), multiple testing did not show any such difference. Interestingly, significant difference between the two groups was found only using the open-eyes protocol. PSF showed significantly increased antero-posterior movements as well as increased posturographic area, compared to PSNF. Our study demonstrates the superiority of the ts-AUC test compared to standard statistical tools in distinguishing PSF and PSNF in the multidimensional feature space. This result highlights more generally the fact that machine learning-based statistical tests can be seen as a natural extension of classical statistical approaches and should be considered, especially when dealing with multifactorial assessments.
Tasks
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06614v1
PDF	https://arxiv.org/pdf/1907.06614v1.pdf
PWC	https://paperswithcode.com/paper/revealing-posturographic-features-associated
Repo
Framework

Learning High-fidelity Light Field Images From Hybrid Inputs


Title	Learning High-fidelity Light Field Images From Hybrid Inputs
Authors	Jing Jin, Junhui Hou, Jie Chen, Sam Kwong, Jingyi Yu
Abstract	This paper explores the reconstruction of high-fidelity LF images (i.e., LF images with both high spatial and angular resolution) from hybrid inputs, including a high resolution RGB image and a low spatial but high angular resolution LF image. To tackle this challenging problem, we propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input from two complementary and parallel perspectives. Specifically, one module efficiently learns a deep multi-dimensional and cross-domain feature representation to regress an intermediate estimation; the other one propagates the information of the input, which is challenging to predict, to construct another intermediate estimation. We finally leverage the advantages of the two intermediate estimations via the learned confidence maps, leading to the final high-fidelity LF image. Extensive experiments demonstrate the significant superiority of our approach over the state-of-the-art ones. That is, our method not only improves the PSNR more than 2 dB, but also preserves the LF structure much better. To the best of our knowledge, this is the first end-to-end deep learning method for reconstructing a high-fidelity LF image with a hybrid input. We believe our framework could potentially decrease the cost of high-fidelity LF data acquisition and also be beneficial to LF data storage.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09640v1
PDF	https://arxiv.org/pdf/1907.09640v1.pdf
PWC	https://paperswithcode.com/paper/learning-high-fidelity-light-field-images
Repo
Framework

ArduCode: Predictive Framework for Automation Engineering


Title	ArduCode: Predictive Framework for Automation Engineering
Authors	Arquimedes Canedo, Palash Goyal, Di Huang, Amit Pandey
Abstract	Automation engineering is the task of integrating, via software, various sensors, actuators, and controls for automating a real-world process. Today, automation engineering is supported by a suite of software tools including integrated development environments (IDE), hardware configurators, compilers, and runtimes. These tools focus on the automation code itself, but leave the automation engineer unassisted in their decision making. This can lead to increased time for software development because of imperfections in decision making leading to multiple iterations between software and hardware. To address this, this paper defines multiple challenges often faced in automation engineering and propose solutions using machine learning to assist engineers tackle such challenges. We show that machine learning can be leveraged to assist the automation engineer in classifying automation, finding similar code snippets, and reasoning about the hardware selection of sensors and actuators. We validate our architecture on two real datasets consisting of 2,927 Arduino projects, and 683 Programmable Logic Controller (PLC) projects. Our results show that paragraph embedding techniques can be utilized to classify automation using code snippets with precision close to human annotation, giving an F1-score of 72%. Further, we show that such embedding techniques can help us find similar code snippets with high accuracy. Finally, we use autoencoder models for hardware recommendation and achieve a p@3 of 0.79 and p@5 of 0.95.
Tasks	Decision Making
Published	2019-09-06
URL	https://arxiv.org/abs/1909.04503v2
PDF	https://arxiv.org/pdf/1909.04503v2.pdf
PWC	https://paperswithcode.com/paper/arducode-predictive-framework-for-automation
Repo
Framework

Compiling Stochastic Constraint Programs to And-Or Decision Diagrams


Title	Compiling Stochastic Constraint Programs to And-Or Decision Diagrams
Authors	Behrouz Babaki, Golnoosh Farnadi, Gilles Pesant
Abstract	Factored stochastic constraint programming (FSCP) is a formalism to represent multi-stage decision making problems under uncertainty. FSCP models support factorized probabilistic models and involve constraints over decision and random variables. These models have many applications in real-world problems. However, solving these problems requires evaluating the best course of action for each possible outcome of the random variables and hence is computationally challenging. FSCP problems often involve repeated subproblems which ideally should be solved once. In this paper we show how identifying and exploiting these identical subproblems can simplify solving them and leads to a compact representation of the solution. We compile an And-Or search tree to a compact decision diagram. Preliminary experiments show that our proposed method significantly improves the search efficiency by reducing the size of the problem and outperforms the existing methods.
Tasks	Decision Making
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10622v1
PDF	https://arxiv.org/pdf/1909.10622v1.pdf
PWC	https://paperswithcode.com/paper/compiling-stochastic-constraint-programs-to
Repo
Framework

Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents


Title	Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents
Authors	Joseph Suarez, Yilun Du, Phillip Isola, Igor Mordatch
Abstract	The emergence of complex life on Earth is often attributed to the arms race that ensued from a huge number of organisms all competing for finite resources. We present an artificial intelligence research environment, inspired by the human game genre of MMORPGs (Massively Multiplayer Online Role-Playing Games, a.k.a. MMOs), that aims to simulate this setting in microcosm. As with MMORPGs and the real world alike, our environment is persistent and supports a large and variable number of agents. Our environment is well suited to the study of large-scale multiagent interaction: it requires that agents learn robust combat and navigation policies in the presence of large populations attempting to do the same. Baseline experiments reveal that population size magnifies and incentivizes the development of skillful behaviors and results in agents that outcompete agents trained in smaller populations. We further show that the policies of agents with unshared weights naturally diverge to fill different niches in order to avoid competition.
Tasks
Published	2019-03-02
URL	http://arxiv.org/abs/1903.00784v1
PDF	http://arxiv.org/pdf/1903.00784v1.pdf
PWC	https://paperswithcode.com/paper/neural-mmo-a-massively-multiagent-game
Repo
Framework


Title	Selling Multiple Items via Social Networks
Authors	Dengji Zhao, Bin Li, Junping Xu, Dong Hao, Nicholas R. Jennings
Abstract	We consider a market where a seller sells multiple units of a commodity in a social network. Each node/buyer in the social network can only directly communicate with her neighbours, i.e. the seller can only sell the commodity to her neighbours if she could not find a way to inform other buyers. In this paper, we design a novel promotion mechanism that incentivizes all buyers, who are aware of the sale, to invite all their neighbours to join the sale, even though there is no guarantee that their efforts will be paid. While traditional sale promotions such as sponsored search auctions cannot guarantee a positive return for the advertiser (the seller), our mechanism guarantees that the seller’s revenue is better than not using the advertising. More importantly, the seller does not need to pay if the advertising is not beneficial to her.
Tasks
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02703v1
PDF	http://arxiv.org/pdf/1903.02703v1.pdf
PWC	https://paperswithcode.com/paper/selling-multiple-items-via-social-networks
Repo
Framework

Are You for Real? Detecting Identity Fraud via Dialogue Interactions


Title	Are You for Real? Detecting Identity Fraud via Dialogue Interactions
Authors	Weikang Wang, Jiajun Zhang, Qian Li, Chengqing Zong, Zhifei Li
Abstract	Identity fraud detection is of great importance in many real-world scenarios such as the financial industry. However, few studies addressed this problem before. In this paper, we focus on identity fraud detection in loan applications and propose to solve this problem with a novel interactive dialogue system which consists of two modules. One is the knowledge graph (KG) constructor organizing the personal information for each loan applicant. The other is structured dialogue management that can dynamically generate a series of questions based on the personal KG to ask the applicants and determine their identity states. We also present a heuristic user simulator based on problem analysis to evaluate our method. Experiments have shown that the trainable dialogue system can effectively detect fraudsters, and achieve higher recognition accuracy compared with rule-based systems. Furthermore, our learned dialogue strategies are interpretable and flexible, which can help promote real-world applications.
Tasks	Dialogue Management, Fraud Detection
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06820v1
PDF	https://arxiv.org/pdf/1908.06820v1.pdf
PWC	https://paperswithcode.com/paper/are-you-for-real-detecting-identity-fraud-via
Repo
Framework

Trustable and Automated Machine Learning Running with Blockchain and Its Applications


Title	Trustable and Automated Machine Learning Running with Blockchain and Its Applications
Authors	Tao Wang, Xinmin Wu, Taiping He
Abstract	Machine learning algorithms learn from data and use data from databases that are mutable; therefore, the data and the results of machine learning cannot be fully trusted. Also, the machine learning process is often difficult to automate. A unified analytical framework for trustable machine learning has been presented in the literature. It proposed building a trustable machine learning system by using blockchain technology, which can store data in a permanent and immutable way. In addition, smart contracts on blockchain are used to automate the machine learning process. In the proposed framework, a core machine learning algorithm can have three implementations: server layer implementation, streaming layer implementation, and smart contract implementation. However, there are still open questions. First, the streaming layer usually deploys on edge devices and therefore has limited memory and computing power. How can we run machine learning on the streaming layer? Second, most data that are stored on blockchain are financial transactions, for which fraud detection is often needed. However, in some applications, training data are hard to obtain. Can we build good machine learning models to do fraud detection with limited training data? These questions motivated this paper; which makes two contributions. First, it proposes training a machine learning model on the server layer and saving the model with a special binary data format. Then, the streaming layer can take this blob of binary data as input and score incoming data online. The blob of binary data is very compact and can be deployed on edge devices. Second, the paper presents a new method of synthetic data generation that can enrich the training data set. Experiments show that this synthetic data generation is very effective in applications such as fraud detection in financial data.
Tasks	Fraud Detection, Synthetic Data Generation
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05725v1
PDF	https://arxiv.org/pdf/1908.05725v1.pdf
PWC	https://paperswithcode.com/paper/trustable-and-automated-machine-learning
Repo
Framework

Federated Learning with Autotuned Communication-Efficient Secure Aggregation


Title	Federated Learning with Autotuned Communication-Efficient Secure Aggregation
Authors	Keith Bonawitz, Fariborz Salehi, Jakub Konečný, Brendan McMahan, Marco Gruteser
Abstract	Federated Learning enables mobile devices to collaboratively learn a shared inference model while keeping all the training data on a user’s device, decoupling the ability to do machine learning from the need to store the data in the cloud. Existing work on federated learning with limited communication demonstrates how random rotation can enable users’ model updates to be quantized much more efficiently, reducing the communication cost between users and the server. Meanwhile, secure aggregation enables the server to learn an aggregate of at least a threshold number of device’s model contributions without observing any individual device’s contribution in unaggregated form. In this paper, we highlight some of the challenges of setting the parameters for secure aggregation to achieve communication efficiency, especially in the context of the aggressively quantized inputs enabled by random rotation. We then develop a recipe for auto-tuning communication-efficient secure aggregation, based on specific properties of random rotation and secure aggregation – namely, the predictable distribution of vector entries post-rotation and the modular wrapping inherent in secure aggregation. We present both theoretical results and initial experiments.
Tasks
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00131v1
PDF	https://arxiv.org/pdf/1912.00131v1.pdf
PWC	https://paperswithcode.com/paper/federated-learning-with-autotuned
Repo
Framework

Nonparametric Regression on Low-Dimensional Manifolds using Deep ReLU Networks


Title	Nonparametric Regression on Low-Dimensional Manifolds using Deep ReLU Networks
Authors	Minshuo Chen, Haoming Jiang, Wenjing Liao, Tuo Zhao
Abstract	Real world data often exhibit low-dimensional geometric structures, and can be viewed as samples near a low-dimensional manifold. This paper studies nonparametric regression of H"older functions on low-dimensional manifolds using deep ReLU networks. Suppose $n$ training data are sampled from a H"older function in $\mathcal{H}^{s,\alpha}$ supported on a $d$-dimensional Riemannian manifold isometrically embedded in $\mathbb{R}^D$, with sub-gaussian noise. A deep ReLU network architecture is designed to estimate the underlying function from the training data. The mean squared error of the empirical estimator is proved to converge in the order of $n^{-\frac{2(s+\alpha)}{2(s+\alpha) + d}}\log^3 n$. This result shows that deep ReLU networks give rise to a fast convergence rate depending on the data intrinsic dimension $d$, which is usually much smaller than the ambient dimension $D$. It therefore demonstrates the adaptivity of deep ReLU networks to low-dimensional geometric structures of data, and partially explains the power of deep ReLU networks in tackling high-dimensional data with low-dimensional geometric structures.
Tasks
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01842v2
PDF	https://arxiv.org/pdf/1908.01842v2.pdf
PWC	https://paperswithcode.com/paper/efficient-approximation-of-deep-relu-networks
Repo
Framework

Learning Generalized Quasi-Geostrophic Models Using Deep Neural Numerical Models


Title	Learning Generalized Quasi-Geostrophic Models Using Deep Neural Numerical Models
Authors	Redouane Lguensat, Julien Le Sommer, Sammy Metref, Emmanuel Cosme, Ronan Fablet
Abstract	We introduce a new strategy designed to help physicists discover hidden laws governing dynamical systems. We propose to use machine learning automatic differentiation libraries to develop hybrid numerical models that combine components based on prior physical knowledge with components based on neural networks. In these architectures, named Deep Neural Numerical Models (DNNMs), the neural network components are used as building-blocks then deployed for learning hidden variables of underlying physical laws governing dynamical systems. In this paper, we illustrate an application of DNNMs to upper ocean dynamics, more precisely the dynamics of a sea surface tracer, the Sea Surface Height (SSH). We develop an advection-based fully differentiable numerical scheme, where parts of the computations can be replaced with learnable ConvNets, and make connections with the single-layer Quasi-Geostrophic (QG) model, a baseline theory in physical oceanography developed decades ago.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08856v1
PDF	https://arxiv.org/pdf/1911.08856v1.pdf
PWC	https://paperswithcode.com/paper/learning-generalized-quasi-geostrophic-models
Repo
Framework

RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments


Title	RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments
Authors	Zhen-Liang Ni, Gui-Bin Bian, Xiao-Hu Zhou, Zeng-Guang Hou, Xiao-Liang Xie, Chen Wang, Yan-Jie Zhou, Rui-Qi Li, Zhen Li
Abstract	Semantic segmentation of surgical instruments plays a crucial role in robot-assisted surgery. However, accurate segmentation of cataract surgical instruments is still a challenge due to specular reflection and class imbalance issues. In this paper, an attention-guided network is proposed to segment the cataract surgical instrument. A new attention module is designed to learn discriminative features and address the specular reflection issue. It captures global context and encodes semantic dependencies to emphasize key semantic features, boosting the feature representation. This attention module has very few parameters, which helps to save memory. Thus, it can be flexibly plugged into other networks. Besides, a hybrid loss is introduced to train our network for addressing the class imbalance issue, which merges cross entropy and logarithms of Dice loss. A new dataset named Cata7 is constructed to evaluate our network. To the best of our knowledge, this is the first cataract surgical instrument dataset for semantic segmentation. Based on this dataset, RAUNet achieves state-of-the-art performance 97.71% mean Dice and 95.62% mean IOU.
Tasks	Semantic Segmentation
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10360v3
PDF	https://arxiv.org/pdf/1909.10360v3.pdf
PWC	https://paperswithcode.com/paper/190910360
Repo
Framework

GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization


Title	GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization
Authors	Lukas von Stumberg, Patrick Wenzel, Qadeer Khan, Daniel Cremers
Abstract	Direct SLAM methods have shown exceptional performance on odometry tasks. However, they are susceptible to dynamic lighting and weather changes while also suffering from a bad initialization on large baselines. To overcome this, we propose GN-Net: a network optimized with the novel Gauss-Newton loss for training weather invariant deep features, tailored for direct image alignment. Our network can be trained with pixel correspondences between images taken from different sequences. Experiments on both simulated and real-world datasets demonstrate that our approach is more robust against bad initialization, variations in day-time, and weather changes thereby outperforming state-of-the-art direct and indirect methods. Furthermore, we release an evaluation benchmark for relocalization tracking against different types of weather. Our benchmark is available at https://vision.in.tum.de/gn-net.
Tasks
Published	2019-04-26
URL	https://arxiv.org/abs/1904.11932v3
PDF	https://arxiv.org/pdf/1904.11932v3.pdf
PWC	https://paperswithcode.com/paper/gn-net-the-gauss-newton-loss-for-deep-direct
Repo
Framework