July 27, 2019

3357 words 16 mins read

Paper Group ANR 556

When Traffic Flow Prediction Meets Wireless Big Data Analytics. Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA. Embodied Artificial Intelligence through Distributed Adaptive Control: An Integrated Framework. Motif-based Rule Discovery for Predicting Real-valued Time Seri …

When Traffic Flow Prediction Meets Wireless Big Data Analytics


Title	When Traffic Flow Prediction Meets Wireless Big Data Analytics
Authors	Yuanfang Chen, Mohsen Guizani, Yan Zhang, Lei Wang, Noel Crespi, Gyu Myoung Lee
Abstract	Traffic flow prediction is an important research issue for solving the traffic congestion problem in an Intelligent Transportation System (ITS). Traffic congestion is one of the most serious problems in a city, which can be predicted in advance by analyzing traffic flow patterns. Such prediction is possible by analyzing the real-time transportation data from correlative roads and vehicles. This article first gives a brief introduction to the transportation data, and surveys the state-of-the-art prediction methods. Then, we verify whether or not the prediction performance is able to be improved by fitting actual data to optimize the parameters of the prediction model which is used to predict the traffic flow. Such verification is conducted by comparing the optimized time series prediction model with the normal time series prediction model. This means that in the era of big data, accurate use of the data becomes the focus of studying the traffic flow prediction to solve the congestion problem. Finally, experimental results of a case study are provided to verify the existence of such performance improvement, while the research challenges of this data-analytics-based prediction are presented and discussed.
Tasks	Time Series, Time Series Prediction
Published	2017-09-23
URL	http://arxiv.org/abs/1709.08024v1
PDF	http://arxiv.org/pdf/1709.08024v1.pdf
PWC	https://paperswithcode.com/paper/when-traffic-flow-prediction-meets-wireless
Repo
Framework

Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA


Title	Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA
Authors	Chuang Wang, Jonathan Mattingly, Yue M. Lu
Abstract	We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the high-dimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regression and principal component analysis. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-varying joint empirical measures of the target feature vector and its estimates provided by the algorithms will converge weakly to a deterministic measured-valued process that can be characterized as the unique solution of a nonlinear PDE. Numerical solutions of this PDE can be efficiently obtained. These solutions lead to precise predictions of the performance of the algorithms, as many practical performance metrics are linear functionals of the joint empirical measures. In addition to characterizing the dynamic performance of online learning algorithms, our asymptotic analysis also provides useful insights. In particular, in the high-dimensional limit, and due to exchangeability, the original coupled dynamics associated with the algorithms will be asymptotically “decoupled”, with each coordinate independently solving a 1-D effective minimization problem via stochastic gradient descent. Exploiting this insight for nonconvex optimization problems may prove an interesting line of future research.
Tasks
Published	2017-12-08
URL	http://arxiv.org/abs/1712.04332v1
PDF	http://arxiv.org/pdf/1712.04332v1.pdf
PWC	https://paperswithcode.com/paper/scaling-limit-exact-and-tractable-analysis-of
Repo
Framework

Embodied Artificial Intelligence through Distributed Adaptive Control: An Integrated Framework


Title	Embodied Artificial Intelligence through Distributed Adaptive Control: An Integrated Framework
Authors	Clément Moulin-Frier, Jordi-Ysard Puigbò, Xerxes D. Arsiwalla, Martì Sanchez-Fibla, Paul F. M. J. Verschure
Abstract	In this paper, we argue that the future of Artificial Intelligence research resides in two keywords: integration and embodiment. We support this claim by analyzing the recent advances of the field. Regarding integration, we note that the most impactful recent contributions have been made possible through the integration of recent Machine Learning methods (based in particular on Deep Learning and Recurrent Neural Networks) with more traditional ones (e.g. Monte-Carlo tree search, goal babbling exploration or addressable memory systems). Regarding embodiment, we note that the traditional benchmark tasks (e.g. visual classification or board games) are becoming obsolete as state-of-the-art learning algorithms approach or even surpass human performance in most of them, having recently encouraged the development of first-person 3D game platforms embedding realistic physics. Building upon this analysis, we first propose an embodied cognitive architecture integrating heterogenous sub-fields of Artificial Intelligence into a unified framework. We demonstrate the utility of our approach by showing how major contributions of the field can be expressed within the proposed framework. We then claim that benchmarking environments need to reproduce ecologically-valid conditions for bootstrapping the acquisition of increasingly complex cognitive skills through the concept of a cognitive arms race between embodied agents.
Tasks	Board Games
Published	2017-04-05
URL	http://arxiv.org/abs/1704.01407v3
PDF	http://arxiv.org/pdf/1704.01407v3.pdf
PWC	https://paperswithcode.com/paper/embodied-artificial-intelligence-through
Repo
Framework

Motif-based Rule Discovery for Predicting Real-valued Time Series


Title	Motif-based Rule Discovery for Predicting Real-valued Time Series
Authors	Yuanduo He, Xu Chu, Juguang Peng, Jingyue Gao, Yasha Wang
Abstract	Time series prediction is of great significance in many applications and has attracted extensive attention from the data mining community. Existing work suggests that for many problems, the shape in the current time series may correlate an upcoming shape in the same or another series. Therefore, it is a promising strategy to associate two recurring patterns as a rule’s antecedent and consequent: the occurrence of the antecedent can foretell the occurrence of the consequent, and the learned shape of consequent will give accurate predictions. Earlier work employs symbolization methods, but the symbolized representation maintains too little information of the original series to mine valid rules. The state-of-the-art work, though directly manipulating the series, fails to segment the series precisely for seeking antecedents/consequents, resulting in inaccurate rules in common scenarios. In this paper, we propose a novel motif-based rule discovery method, which utilizes motif discovery to accurately extract frequently occurring consecutive subsequences, i.e. motifs, as antecedents/consequents. It then investigates the underlying relationships between motifs by matching motifs as rule candidates and ranking them based on the similarities. Experimental results on real open datasets show that the proposed approach outperforms the baseline method by 23.9%. Furthermore, it extends the applicability from single time series to multiple ones.
Tasks	Time Series, Time Series Prediction
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04763v4
PDF	http://arxiv.org/pdf/1709.04763v4.pdf
PWC	https://paperswithcode.com/paper/motif-based-rule-discovery-for-predicting
Repo
Framework

Big Data Regression Using Tree Based Segmentation


Title	Big Data Regression Using Tree Based Segmentation
Authors	Rajiv Sambasivan, Sourish Das
Abstract	Scaling regression to large datasets is a common problem in many application areas. We propose a two step approach to scaling regression to large datasets. Using a regression tree (CART) to segment the large dataset constitutes the first step of this approach. The second step of this approach is to develop a suitable regression model for each segment. Since segment sizes are not very large, we have the ability to apply sophisticated regression techniques if required. A nice feature of this two step approach is that it can yield models that have good explanatory power as well as good predictive performance. Ensemble methods like Gradient Boosted Trees can offer excellent predictive performance but may not provide interpretable models. In the experiments reported in this study, we found that the predictive performance of the proposed approach matched the predictive performance of Gradient Boosted Trees.
Tasks
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07409v2
PDF	http://arxiv.org/pdf/1707.07409v2.pdf
PWC	https://paperswithcode.com/paper/big-data-regression-using-tree-based
Repo
Framework

Reservoir Computing on the Hypersphere


Title	Reservoir Computing on the Hypersphere
Authors	M. Andrecut
Abstract	Reservoir Computing (RC) refers to a Recurrent Neural Networks (RNNs) framework, frequently used for sequence learning and time series prediction. The RC system consists of a random fixed-weight RNN (the input-hidden reservoir layer) and a classifier (the hidden-output readout layer). Here we focus on the sequence learning problem, and we explore a different approach to RC. More specifically, we remove the non-linear neural activation function, and we consider an orthogonal reservoir acting on normalized states on the unit hypersphere. Surprisingly, our numerical results show that the system’s memory capacity exceeds the dimensionality of the reservoir, which is the upper bound for the typical RC approach based on Echo State Networks (ESNs). We also show how the proposed system can be applied to symmetric cryptography problems, and we include a numerical implementation.
Tasks	Time Series, Time Series Prediction
Published	2017-06-24
URL	http://arxiv.org/abs/1706.07896v1
PDF	http://arxiv.org/pdf/1706.07896v1.pdf
PWC	https://paperswithcode.com/paper/reservoir-computing-on-the-hypersphere
Repo
Framework

Detecting (Un)Important Content for Single-Document News Summarization


Title	Detecting (Un)Important Content for Single-Document News Summarization
Authors	Yinfei Yang, Forrest Sheng Bao, Ani Nenkova
Abstract	We present a robust approach for detecting intrinsic sentence importance in news, by training on two corpora of document-summary pairs. When used for single-document summarization, our approach, combined with the “beginning of document” heuristic, outperforms a state-of-the-art summarizer and the beginning-of-article baseline in both automatic and manual evaluations. These results represent an important advance because in the absence of cross-document repetition, single document summarizers for news have not been able to consistently outperform the strong beginning-of-article baseline.
Tasks	Document Summarization
Published	2017-02-26
URL	http://arxiv.org/abs/1702.07998v1
PDF	http://arxiv.org/pdf/1702.07998v1.pdf
PWC	https://paperswithcode.com/paper/detecting-unimportant-content-for-single
Repo
Framework

Embedding Deep Networks into Visual Explanations


Title	Embedding Deep Networks into Visual Explanations
Authors	Zhongang Qi, Saeed Khorram, Fuxin Li
Abstract	In this paper, we propose a novel explanation module to explain the predictions made by a deep network. The explanation module works by embedding a high-dimensional deep network layer nonlinearly into a low-dimensional explanation space while retaining faithfulness, so that the original deep learning predictions can be constructed from the few concepts extracted by the explanation module. We then visualize such concepts for human to learn about the high-level concepts that deep learning is using to make decisions. We propose an algorithm called Sparse Reconstruction Autoencoder (SRAE) for learning the embedding to the explanation space. SRAE aims to reconstruct part of the original feature space while retaining faithfulness. A pull-away term is applied to SRAE to make the explanation space more orthogonal. A visualization system is then introduced for human understanding of the features in the explanation space. The proposed method is applied to explain CNN models in image classification tasks, and several novel metrics are introduced to evaluate the performance of explanations quantitatively without human involvement. Experiments show that the proposed approach generates interesting explanations of the mechanisms CNN use for making predictions.
Tasks	Image Classification
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05360v2
PDF	http://arxiv.org/pdf/1709.05360v2.pdf
PWC	https://paperswithcode.com/paper/embedding-deep-networks-into-visual
Repo
Framework

Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach


Title	Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach
Authors	Jintao Ke, Hongyu Zheng, Hai Yang, Xiqun, Chen
Abstract	Short-term passenger demand forecasting is of great importance to the on-demand ride service platform, which can incentivize vacant cars moving from over-supply regions to over-demand regions. The spatial dependences, temporal dependences, and exogenous dependences need to be considered simultaneously, however, which makes short-term passenger demand forecasting challenging. We propose a novel deep learning (DL) approach, named the fusion convolutional long short-term memory network (FCL-Net), to address these three dependences within one end-to-end learning architecture. The model is stacked and fused by multiple convolutional long short-term memory (LSTM) layers, standard LSTM layers, and convolutional layers. The fusion of convolutional techniques and the LSTM network enables the proposed DL approach to better capture the spatio-temporal characteristics and correlations of explanatory variables. A tailored spatially aggregated random forest is employed to rank the importance of the explanatory variables. The ranking is then used for feature selection. The proposed DL approach is applied to the short-term forecasting of passenger demand under an on-demand ride service platform in Hangzhou, China. Experimental results, validated on real-world data provided by DiDi Chuxing, show that the FCL-Net achieves better predictive performance than traditional approaches including both classical time-series prediction models and neural network based algorithms (e.g., artificial neural network and LSTM). This paper is one of the first DL studies to forecast the short-term passenger demand of an on-demand ride service platform by examining the spatio-temporal correlations.
Tasks	Feature Selection, Time Series, Time Series Prediction
Published	2017-06-20
URL	http://arxiv.org/abs/1706.06279v1
PDF	http://arxiv.org/pdf/1706.06279v1.pdf
PWC	https://paperswithcode.com/paper/short-term-forecasting-of-passenger-demand
Repo
Framework

Radial Line Fourier Descriptor for Historical Handwritten Text Representation


Title	Radial Line Fourier Descriptor for Historical Handwritten Text Representation
Authors	Anders Hast, Ekta Vats
Abstract	Automatic recognition of historical handwritten manuscripts is a daunting task due to paper degradation over time. Recognition-free retrieval or word spotting is popularly used for information retrieval and digitization of the historical handwritten documents. However, the performance of word spotting algorithms depends heavily on feature detection and representation methods. Although there exist popular feature descriptors such as Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF), the invariant properties of these descriptors amplify the noise in the degraded document images, rendering them more sensitive to noise and complex characteristics of historical manuscripts. Therefore, an efficient and relaxed feature descriptor is required as handwritten words across different documents are indeed similar, but not identical. This paper introduces a Radial Line Fourier (RLF) descriptor for handwritten word representation, with a short feature vector of 32 dimensions. A segmentation-free and training-free handwritten word spotting method is studied herein that relies on the proposed RLF descriptor, takes into account different keypoint representations and uses a simple preconditioner-based feature matching algorithm. The effectiveness of the RLF descriptor for segmentation-free handwritten word spotting is empirically evaluated on well-known historical handwritten datasets using standard evaluation measures.
Tasks	Information Retrieval
Published	2017-09-06
URL	http://arxiv.org/abs/1709.01788v4
PDF	http://arxiv.org/pdf/1709.01788v4.pdf
PWC	https://paperswithcode.com/paper/radial-line-fourier-descriptor-for-historical
Repo
Framework

Indirect Match Highlights Detection with Deep Convolutional Neural Networks


Title	Indirect Match Highlights Detection with Deep Convolutional Neural Networks
Authors	Marco Godi, Paolo Rota, Francesco Setti
Abstract	Highlights in a sport video are usually referred as actions that stimulate excitement or attract attention of the audience. A big effort is spent in designing techniques which find automatically highlights, in order to automatize the otherwise manual editing process. Most of the state-of-the-art approaches try to solve the problem by training a classifier using the information extracted on the tv-like framing of players playing on the game pitch, learning to detect game actions which are labeled by human observers according to their perception of highlight. Obviously, this is a long and expensive work. In this paper, we reverse the paradigm: instead of looking at the gameplay, inferring what could be exciting for the audience, we directly analyze the audience behavior, which we assume is triggered by events happening during the game. We apply deep 3D Convolutional Neural Network (3D-CNN) to extract visual features from cropped video recordings of the supporters that are attending the event. Outputs of the crops belonging to the same frame are then accumulated to produce a value indicating the Highlight Likelihood (HL) which is then used to discriminate between positive (i.e. when a highlight occurs) and negative samples (i.e. standard play or time-outs). Experimental results on a public dataset of ice-hockey matches demonstrate the effectiveness of our method and promote further research in this new exciting direction.
Tasks
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00568v1
PDF	http://arxiv.org/pdf/1710.00568v1.pdf
PWC	https://paperswithcode.com/paper/indirect-match-highlights-detection-with-deep
Repo
Framework

Time Series Prediction for Graphs in Kernel and Dissimilarity Spaces


Title	Time Series Prediction for Graphs in Kernel and Dissimilarity Spaces
Authors	Benjamin Paaßen, Christina Göpfert, Barbara Hammer
Abstract	Graph models are relevant in many fields, such as distributed computing, intelligent tutoring systems or social network analysis. In many cases, such models need to take changes in the graph structure into account, i.e. a varying number of nodes or edges. Predicting such changes within graphs can be expected to yield important insight with respect to the underlying dynamics, e.g. with respect to user behaviour. However, predictive techniques in the past have almost exclusively focused on single edges or nodes. In this contribution, we attempt to predict the future state of a graph as a whole. We propose to phrase time series prediction as a regression problem and apply dissimilarity- or kernel-based regression techniques, such as 1-nearest neighbor, kernel regression and Gaussian process regression, which can be applied to graphs via graph kernels. The output of the regression is a point embedded in a pseudo-Euclidean space, which can be analyzed using subsequent dissimilarity- or kernel-based processing methods. We discuss strategies to speed up Gaussian Processes regression from cubic to linear time and evaluate our approach on two well-established theoretical models of graph evolution as well as two real data sets from the domain of intelligent tutoring systems. We find that simple regression methods, such as kernel regression, are sufficient to capture the dynamics in the theoretical models, but that Gaussian process regression significantly improves the prediction error for real-world data.
Tasks	Gaussian Processes, Time Series, Time Series Prediction
Published	2017-04-21
URL	http://arxiv.org/abs/1704.06498v3
PDF	http://arxiv.org/pdf/1704.06498v3.pdf
PWC	https://paperswithcode.com/paper/time-series-prediction-for-graphs-in-kernel
Repo
Framework

Multi-Label Learning with Global and Local Label Correlation


Title	Multi-Label Learning with Global and Local Label Correlation
Authors	Yue Zhu, James T. Kwok, Zhi-Hua Zhou
Abstract	It is well-known that exploiting label correlations is important to multi-label learning. Existing approaches either assume that the label correlations are global and shared by all instances; or that the label correlations are local and shared only by a data subset. In fact, in the real-world applications, both cases may occur that some label correlations are globally applicable and some are shared only in a local group of instances. Moreover, it is also a usual case that only partial labels are observed, which makes the exploitation of the label correlations much more difficult. That is, it is hard to estimate the label correlations when many labels are absent. In this paper, we propose a new multi-label approach GLOCAL dealing with both the full-label and the missing-label cases, exploiting global and local label correlations simultaneously, through learning a latent label representation and optimizing label manifolds. The extensive experimental studies validate the effectiveness of our approach on both full-label and missing-label data.
Tasks	Multi-Label Learning
Published	2017-04-04
URL	http://arxiv.org/abs/1704.01415v1
PDF	http://arxiv.org/pdf/1704.01415v1.pdf
PWC	https://paperswithcode.com/paper/multi-label-learning-with-global-and-local
Repo
Framework

Échantillonnage de signaux sur graphes via des processus déterminantaux


Title	Échantillonnage de signaux sur graphes via des processus déterminantaux
Authors	Nicolas Tremblay, Simon Barthelme, Pierre-Olivier Amblard
Abstract	We consider the problem of sampling k-bandlimited graph signals, ie, linear combinations of the first k graph Fourier modes. We know that a set of k nodes embedding all k-bandlimited signals always exists, thereby enabling their perfect reconstruction after sampling. Unfortunately, to exhibit such a set, one needs to partially diagonalize the graph Laplacian, which becomes prohibitive at large scale. We propose a novel strategy based on determinantal point processes that side-steps partial diagonalisation and enables reconstruction with only O(k) samples. While doing so, we exhibit a new general algorithm to sample determinantal process, faster than the state-of-the-art algorithm by an order k.
Tasks	Point Processes
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02239v2
PDF	http://arxiv.org/pdf/1704.02239v2.pdf
PWC	https://paperswithcode.com/paper/echantillonnage-de-signaux-sur-graphes-via
Repo
Framework

Modular Resource Centric Learning for Workflow Performance Prediction


Title	Modular Resource Centric Learning for Workflow Performance Prediction
Authors	Alok Singh, Mai Nguyen, Shweta Purawat, Daniel Crawl, Ilkay Altintas
Abstract	Workflows provide an expressive programming model for fine-grained control of large-scale applications in distributed computing environments. Accurate estimates of complex workflow execution metrics on large-scale machines have several key advantages. The performance of scheduling algorithms that rely on estimates of execution metrics degrades when the accuracy of predicted execution metrics decreases. This in-progress paper presents a technique being developed to improve the accuracy of predicted performance metrics of large-scale workflows on distributed platforms. The central idea of this work is to train resource-centric machine learning agents to capture complex relationships between a set of program instructions and their performance metrics when executed on a specific resource. This resource-centric view of a workflow exploits the fact that predicting execution times of sub-modules of a workflow requires monitoring and modeling of a few dynamic and static features. We transform the input workflow that is essentially a directed acyclic graph of actions into a Physical Resource Execution Plan (PREP). This transformation enables us to model an arbitrarily complex workflow as a set of simpler programs running on physical nodes. We delegate a machine learning model to capture performance metrics for each resource type when it executes different program instructions under varying degrees of resource contention. Our algorithm takes the prediction metrics from each resource agent and composes the overall workflow performance metrics by utilizing the structure of the corresponding Physical Resource Execution Plan.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05429v3
PDF	http://arxiv.org/pdf/1711.05429v3.pdf
PWC	https://paperswithcode.com/paper/modular-resource-centric-learning-for
Repo
Framework