January 30, 2020

3367 words 16 mins read

Paper Group ANR 466

Prediction of gaze direction using Convolutional Neural Networks for Autism diagnosis. Learning Phase Competition for Traffic Signal Control. Semi-supervised Learning with Adaptive Neighborhood Graph Propagation Network. Moviescope: Large-scale Analysis of Movies using Multiple Modalities. Generalized Self-concordant Hessian-barrier algorithms. Tow …

Prediction of gaze direction using Convolutional Neural Networks for Autism diagnosis


Title	Prediction of gaze direction using Convolutional Neural Networks for Autism diagnosis
Authors	Dennis Núñez-Fernández, Franklin Porras-Barrientos, Macarena Vittet-Mondoñedo, Robert H. Gilman, Mirko Zimic
Abstract	Autism is a developmental disorder that affects social interaction and communication of children. The gold standard diagnostic tools are very difficult to use and time consuming. However, diagnostic could be deduced from child gaze preferences by looking a video with social and abstract scenes. In this work, we propose an algorithm based on convolutional neural networks to predict gaze direction for a fast and effective autism diagnosis. Early results show that our algorithm achieves real-time response and robust high accuracy for prediction of gaze direction.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1911.05629v1
PDF	https://arxiv.org/pdf/1911.05629v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-gaze-direction-using
Repo
Framework

Learning Phase Competition for Traffic Signal Control


Title	Learning Phase Competition for Traffic Signal Control
Authors	Guanjie Zheng, Yuanhao Xiong, Xinshi Zang, Jie Feng, Hua Wei, Huichu Zhang, Yong Li, Kai Xu, Zhenhui Li
Abstract	Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions. Among them, improving the urban transportation efficiency is one of the most prominent topics. Recent studies have proposed to use reinforcement learning (RL) for traffic signal control. Different from traditional transportation approaches which rely heavily on prior knowledge, RL can learn directly from the feedback. On the other side, without a careful model design, existing RL methods typically take a long time to converge and the learned models may not be able to adapt to new scenarios. For example, a model that is trained well for morning traffic may not work for the afternoon traffic because the traffic flow could be reversed, resulting in a very different state representation. In this paper, we propose a novel design called FRAP, which is based on the intuitive principle of phase competition in traffic signal control: when two traffic signals conflict, priority should be given to one with larger traffic movement (i.e., higher demand). Through the phase competition modeling, our model achieves invariance to symmetrical cases such as flipping and rotation in traffic flow. By conducting comprehensive experiments, we demonstrate that our model finds better solutions than existing RL methods in the complicated all-phase selection problem, converges much faster during training, and achieves superior generalizability for different road structures and traffic conditions.
Tasks
Published	2019-05-12
URL	https://arxiv.org/abs/1905.04722v1
PDF	https://arxiv.org/pdf/1905.04722v1.pdf
PWC	https://paperswithcode.com/paper/learning-phase-competition-for-traffic-signal
Repo
Framework

Semi-supervised Learning with Adaptive Neighborhood Graph Propagation Network


Title	Semi-supervised Learning with Adaptive Neighborhood Graph Propagation Network
Authors	Bo Jiang, Leiling Wang, Jin Tang, Bin Luo
Abstract	Graph Convolutional Networks (GCNs) have been widely studied for compact data representation and semi-supervised learning tasks. However, existing GCNs usually use a fixed neighborhood graph which is not guaranteed to be optimal for semi-supervised learning tasks. In this paper, we first re-interpret graph convolution operation in GCNs as a composition of feature propagation and (non-linear) transformation. Based on this observation, we then propose a unified adaptive neighborhood feature propagation model and derive a novel Adaptive Neighborhood Graph Propagation Network (ANGPN) for data representation and semi-supervised learning. The aim of ANGPN is to conduct both graph construction and graph convolution simultaneously and cooperatively in a unified formulation and thus can learn an optimal neighborhood graph that best serves graph convolution for data representation and semi-supervised learning. One main benefit of ANGPN is that the learned (convolutional) representation can provide useful weakly supervised information for constructing a better neighborhood graph which meanwhile facilitates data representation and learning. Experimental results on four benchmark datasets demonstrate the effectiveness and benefit of the proposed ANGPN.
Tasks	graph construction
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05153v2
PDF	https://arxiv.org/pdf/1908.05153v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-with-adaptive
Repo
Framework

Moviescope: Large-scale Analysis of Movies using Multiple Modalities


Title	Moviescope: Large-scale Analysis of Movies using Multiple Modalities
Authors	Paola Cascante-Bonilla, Kalpathy Sitaraman, Mengjia Luo, Vicente Ordonez
Abstract	Film media is a rich form of artistic expression. Unlike photography, and short videos, movies contain a storyline that is deliberately complex and intricate in order to engage its audience. In this paper we present a large scale study comparing the effectiveness of visual, audio, text, and metadata-based features for predicting high-level information about movies such as their genre or estimated budget. We demonstrate the usefulness of content-based methods in this domain in contrast to human-based and metadata-based predictions in the era of deep learning. Additionally, we provide a comprehensive study of temporal feature aggregation methods for representing video and text and find that simple pooling operations are effective in this domain. We also show to what extent different modalities are complementary to each other. To this end, we also introduce Moviescope, a new large-scale dataset of 5,000 movies with corresponding movie trailers (video + audio), movie posters (images), movie plots (text), and metadata.
Tasks
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03180v1
PDF	https://arxiv.org/pdf/1908.03180v1.pdf
PWC	https://paperswithcode.com/paper/moviescope-large-scale-analysis-of-movies
Repo
Framework

Generalized Self-concordant Hessian-barrier algorithms


Title	Generalized Self-concordant Hessian-barrier algorithms
Authors	Pavel Dvurechensky, Mathias Staudigl, César A. Uribe
Abstract	Many problems in statistical learning, imaging, and computer vision involve the optimization of a non-convex objective function with singularities at the boundary of the feasible set. For such challenging instances, we develop a new interior-point technique building on the Hessian-barrier algorithm recently introduced in Bomze, Mertikopoulos, Schachinger and Staudigl, [SIAM J. Opt. 2019 29(3), pp. 2100-2127], where the Riemannian metric is induced by a generalized self-concordant function. This class of functions is sufficiently general to include most of the commonly used barrier functions in the literature of interior point methods. We prove global convergence to an approximate stationary point of the method, and in cases where the feasible set admits an easily computable self-concordant barrier, we verify worst-case optimal iteration complexity of the method. Applications in non-convex statistical estimation and $L^{p}$-minimization are discussed to given the efficiency of the method.
Tasks
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01522v2
PDF	https://arxiv.org/pdf/1911.01522v2.pdf
PWC	https://paperswithcode.com/paper/generalized-self-concordant-hessian-barrier
Repo
Framework

Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons


Title	Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons
Authors	Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu
Abstract	Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work. With the belief that modeling hierarchical structure is an essential complementary between SANs and RNNs, we propose to further enhance the strength of hybrid models with an advanced variant of RNNs - Ordered Neurons LSTM (ON-LSTM), which introduces a syntax-oriented inductive bias to perform tree-like composition. Experimental results on the benchmark machine translation task show that the proposed approach outperforms both individual architectures and a standard hybrid model. Further analyses on targeted linguistic evaluation and logical inference tasks demonstrate that the proposed approach indeed benefits from a better modeling of hierarchical structure.
Tasks	Machine Translation
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01562v2
PDF	https://arxiv.org/pdf/1909.01562v2.pdf
PWC	https://paperswithcode.com/paper/towards-better-modeling-hierarchical
Repo
Framework

TopicEq: A Joint Topic and Mathematical Equation Model for Scientific Texts


Title	TopicEq: A Joint Topic and Mathematical Equation Model for Scientific Texts
Authors	Michihiro Yasunaga, John Lafferty
Abstract	Scientific documents rely on both mathematics and text to communicate ideas. Inspired by the topical correspondence between mathematical equations and word contexts observed in scientific texts, we propose a novel topic model that jointly generates mathematical equations and their surrounding text (TopicEq). Using an extension of the correlated topic model, the context is generated from a mixture of latent topics, and the equation is generated by an RNN that depends on the latent topic activations. To experiment with this model, we create a corpus of 400K equation-context pairs extracted from a range of scientific articles from arXiv, and fit the model using a variational autoencoder approach. Experimental results show that this joint model significantly outperforms existing topic models and equation models for scientific texts. Moreover, we qualitatively show that the model effectively captures the relationship between topics and mathematics, enabling novel applications such as topic-aware equation generation, equation topic inference, and topic-aware alignment of mathematical symbols and words.
Tasks	Topic Models
Published	2019-02-16
URL	http://arxiv.org/abs/1902.06034v3
PDF	http://arxiv.org/pdf/1902.06034v3.pdf
PWC	https://paperswithcode.com/paper/topiceq-a-joint-topic-and-mathematical
Repo
Framework

Simulations evaluating resampling methods for causal discovery: ensemble performance and calibration


Title	Simulations evaluating resampling methods for causal discovery: ensemble performance and calibration
Authors	Erich Kummerfeld, Alexander Rix
Abstract	Causal discovery can be a powerful tool for investigating causality when a system can be observed but is inaccessible to experiments in practice. Despite this, it is rarely used in any scientific or medical fields. One of the major hurdles preventing the field of causal discovery from having a larger impact is that it is difficult to determine when the output of a causal discovery method can be trusted in a real-world setting. Trust is especially critical when human health is on the line. In this paper, we report the results of a series of simulation studies investigating the performance of different resampling methods as indicators of confidence in discovered graph features. We found that subsampling and sampling with replacement both performed surprisingly well, suggesting that they can serve as grounds for confidence in graph features. We also found that the calibration of subsampling and sampling with replacement had different convergence properties, suggesting that one’s choice of which to use should depend on the sample size.
Tasks	Calibration, Causal Discovery
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02047v1
PDF	https://arxiv.org/pdf/1910.02047v1.pdf
PWC	https://paperswithcode.com/paper/simulations-evaluating-resampling-methods-for
Repo
Framework

AReN: Assured ReLU NN Architecture for Model Predictive Control of LTI Systems


Title	AReN: Assured ReLU NN Architecture for Model Predictive Control of LTI Systems
Authors	James Ferlez, Yasser Shoukry
Abstract	In this paper, we consider the problem of automatically designing a Rectified Linear Unit (ReLU) Neural Network (NN) architecture that is sufficient to implement the optimal Model Predictive Control (MPC) strategy for an LTI system with quadratic cost. Specifically, we propose AReN, an algorithm to generate Assured ReLU Architectures. AReN takes as input an LTI system with quadratic cost specification, and outputs a ReLU NN architecture with the assurance that there exist network weights that exactly implement the associated MPC controller. AReN thus offers new insight into the design of ReLU NN architectures for the control of LTI systems: instead of training a heuristically chosen NN architecture on data – or iterating over many architectures until a suitable one is found – AReN can suggest an adequate NN architecture before training begins. While several previous works were inspired by the fact that both ReLU NN controllers and optimal MPC controller are both Continuous, Piecewise-Linear (CPWL) functions, exploiting this similarity to design NN architectures with correctness guarantees has remained elusive. AReN achieves this using two novel features. First, we reinterpret a recent result about the implementation of CPWL functions via ReLU NNs to show that a CPWL function may be implemented by a ReLU architecture that is determined by the number of distinct affine regions in the function. Second, we show that we can efficiently over-approximate the number of affine regions in the optimal MPC controller without solving the MPC problem exactly. Together, these results connect the MPC problem to a ReLU NN implementation without explicitly solving the MPC and directly translates this feature to a ReLU NN architecture that comes with the assurance that it can implement the MPC controller. We show through numerical results the effectiveness of AReN in designing an NN architecture.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01608v1
PDF	https://arxiv.org/pdf/1911.01608v1.pdf
PWC	https://paperswithcode.com/paper/aren-assured-relu-nn-architecture-for-model
Repo
Framework

Incentive Compatible Active Learning


Title	Incentive Compatible Active Learning
Authors	Federico Echenique, Siddharth Prasad
Abstract	We consider active learning under incentive compatibility constraints. The main application of our results is to economic experiments, in which a learner seeks to infer the parameters of a subject’s preferences: for example their attitudes towards risk, or their beliefs over uncertain events. By cleverly adapting the experimental design, one can save on the time spent by subjects in the laboratory, or maximize the information obtained from each subject in a given laboratory session; but the resulting adaptive design raises complications due to incentive compatibility. A subject in the lab may answer questions strategically, and not truthfully, so as to steer subsequent questions in a profitable direction. We analyze two standard economic problems: inference of preferences over risk from multiple price lists, and belief elicitation in experiments on choice over uncertainty. In the first setting, we tune a simple and fast learning algorithm to retain certain incentive compatibility properties. In the second setting, we provide an incentive compatible learning algorithm based on scoring rules with query complexity that differs from obvious methods of achieving fast learning rates only by subpolynomial factors. Thus, for these areas of application, incentive compatibility may be achieved without paying a large sample complexity price.
Tasks	Active Learning
Published	2019-11-12
URL	https://arxiv.org/abs/1911.05171v1
PDF	https://arxiv.org/pdf/1911.05171v1.pdf
PWC	https://paperswithcode.com/paper/incentive-compatible-active-learning
Repo
Framework

MetaGrasp: Data Efficient Grasping by Affordance Interpreter Network


Title	MetaGrasp: Data Efficient Grasping by Affordance Interpreter Network
Authors	Junhao Cai, Hui Cheng, Zhanpeng Zhang, Jingcheng Su
Abstract	Data-driven approach for grasping shows significant advance recently. But these approaches usually require much training data. To increase the efficiency of grasping data collection, this paper presents a novel grasp training system including the whole pipeline from data collection to model inference. The system can collect effective grasp sample with a corrective strategy assisted by antipodal grasp rule, and we design an affordance interpreter network to predict pixelwise grasp affordance map. We define graspability, ungraspability and background as grasp affordances. The key advantage of our system is that the pixel-level affordance interpreter network trained with only a small number of grasp samples under antipodal rule can achieve significant performance on totally unseen objects and backgrounds. The training sample is only collected in simulation. Extensive qualitative and quantitative experiments demonstrate the accuracy and robustness of our proposed approach. In the real-world grasp experiments, we achieve a grasp success rate of 93% on a set of household items and 91% on a set of adversarial items with only about 6,300 simulated samples. We also achieve 87% accuracy in clutter scenario. Although the model is trained using only RGB image, when changing the background textures, it also performs well and can achieve even 94% accuracy on the set of adversarial objects, which outperforms current state-of-the-art methods.
Tasks
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06554v2
PDF	http://arxiv.org/pdf/1902.06554v2.pdf
PWC	https://paperswithcode.com/paper/metagrasp-data-efficient-grasping-by
Repo
Framework

JEC-QA: A Legal-Domain Question Answering Dataset


Title	JEC-QA: A Legal-Domain Question Answering Dataset
Authors	Haoxi Zhong, Chaojun Xiao, Cunchao Tu, Tianyang Zhang, Zhiyuan Liu, Maosong Sun
Abstract	We present JEC-QA, the largest question answering dataset in the legal domain, collected from the National Judicial Examination of China. The examination is a comprehensive evaluation of professional skills for legal practitioners. College students are required to pass the examination to be certified as a lawyer or a judge. The dataset is challenging for existing question answering methods, because both retrieving relevant materials and answering questions require the ability of logic reasoning. Due to the high demand of multiple reasoning abilities to answer legal questions, the state-of-the-art models can only achieve about 28% accuracy on JEC-QA, while skilled humans and unskilled humans can reach 81% and 64% accuracy respectively, which indicates a huge gap between humans and machines on this task. We will release JEC-QA and our baselines to help improve the reasoning ability of machine comprehension models. You can access the dataset from http://jecqa.thunlp.org/.
Tasks	Question Answering, Reading Comprehension
Published	2019-11-27
URL	https://arxiv.org/abs/1911.12011v1
PDF	https://arxiv.org/pdf/1911.12011v1.pdf
PWC	https://paperswithcode.com/paper/jec-qa-a-legal-domain-question-answering
Repo
Framework

Deep recurrent Gaussian process with variational Sparse Spectrum approximation


Title	Deep recurrent Gaussian process with variational Sparse Spectrum approximation
Authors	Roman Föll, Bernard Haasdonk, Markus Hanselmann, Holger Ulmer
Abstract	Modeling sequential data has become more and more important in practice. Some applications are autonomous driving, virtual sensors and weather forecasting. To model such systems, so called recurrent models are frequently used. In this paper we introduce several new Deep recurrent Gaussian process (DRGP) models based on the Sparse Spectrum Gaussian process (SSGP) and the improved version, called variational Sparse Spectrum Gaussian process (VSSGP). We follow the recurrent structure given by an existing DRGP based on a specific variational sparse Nystr"om approximation, the recurrent Gaussian process (RGP). Similar to previous work, we also variationally integrate out the input-space and hence can propagate uncertainty through the Gaussian process (GP) layers. Our approach can deal with a larger class of covariance functions than the RGP, because its spectral nature allows variational integration in all stationary cases. Furthermore, we combine the (variational) Sparse Spectrum ((V)SS) approximations with a well known inducing-input regularization framework. We improve over current state of the art methods in prediction accuracy for experimental data-sets used for their evaluation and introduce a new data-set for engine control, named Emission.
Tasks	Autonomous Driving, Weather Forecasting
Published	2019-09-27
URL	https://arxiv.org/abs/1909.13743v1
PDF	https://arxiv.org/pdf/1909.13743v1.pdf
PWC	https://paperswithcode.com/paper/deep-recurrent-gaussian-process-with-2
Repo
Framework

Image classification using quantum inference on the D-Wave 2X


Title	Image classification using quantum inference on the D-Wave 2X
Authors	Nga T. T. Nguyen, Garrett T. Kenyon
Abstract	We use a quantum annealing D-Wave 2X computer to obtain solutions to NP-hard sparse coding problems. To reduce the dimensionality of the sparse coding problem to fit on the quantum D-Wave 2X hardware, we passed downsampled MNIST images through a bottleneck autoencoder. To establish a benchmark for classification performance on this reduced dimensional data set, we used an AlexNet-like architecture implemented in TensorFlow, obtaining a classification score of $94.54 \pm 0.7 %$. As a control, we showed that the same AlexNet-like architecture produced near-state-of-the-art classification performance $(\sim 99%)$ on the original MNIST images. To obtain a set of optimized features for inferring sparse representations of the reduced dimensional MNIST dataset, we imprinted on a random set of $47$ image patches followed by an off-line unsupervised learning algorithm using stochastic gradient descent to optimize for sparse coding. Our single-layer of sparse coding matched the stride and patch size of the first convolutional layer of the AlexNet-like deep neural network and contained $47$ fully-connected features, $47$ being the maximum number of dictionary elements that could be embedded onto the D-Wave $2$X hardware. Recent work suggests that the optimal level of sparsity corresponds to a critical value of the trade-off parameter associated with a putative second order phase transition, an observation supported by a free energy analysis of D-Wave energy states. When the sparse representations inferred by the D-Wave $2$X were passed to a linear support vector machine, we obtained a classification score of $95.68%$. Thus, on this problem, we find that a single-layer of quantum inference is able to outperform a standard deep neural network architecture.
Tasks	Image Classification
Published	2019-05-28
URL	https://arxiv.org/abs/1905.13215v1
PDF	https://arxiv.org/pdf/1905.13215v1.pdf
PWC	https://paperswithcode.com/paper/image-classification-using-quantum-inference
Repo
Framework

Straggler Resilient Serverless Computing Based on Polar Codes


Title	Straggler Resilient Serverless Computing Based on Polar Codes
Authors	Burak Bartan, Mert Pilanci
Abstract	We propose a serverless computing mechanism for distributed computation based on polar codes. Serverless computing is an emerging cloud based computation model that lets users run their functions on the cloud without provisioning or managing servers. Our proposed approach is a hybrid computing framework that carries out computationally expensive tasks such as linear algebraic operations involving large-scale data using serverless computing and does the rest of the processing locally. We address the limitations and reliability issues of serverless platforms such as straggling workers using coding theory, drawing ideas from recent literature on coded computation. The proposed mechanism uses polar codes to ensure straggler-resilience in a computationally effective manner. We provide extensive evidence showing polar codes outperform other coding methods. We have designed a sequential decoder specifically for polar codes in erasure channels with full-precision input and outputs. In addition, we have extended the proposed method to the matrix multiplication case where both matrices being multiplied are coded. The proposed coded computation scheme is implemented for AWS Lambda. Experiment results are presented where the performance of the proposed coded computation technique is tested in optimization via gradient descent. Finally, we introduce the idea of partial polarization which reduces the computational burden of encoding and decoding at the expense of straggler-resilience.
Tasks
Published	2019-01-21
URL	https://arxiv.org/abs/1901.06811v2
PDF	https://arxiv.org/pdf/1901.06811v2.pdf
PWC	https://paperswithcode.com/paper/polar-coded-distributed-matrix-multiplication
Repo
Framework