April 1, 2020

3255 words 16 mins read

Paper Group ANR 490

High-dimensional Neural Feature using Rectified Linear Unit and Random Matrix Instance. Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing. ABBA: Adaptive Brownian bridge-based symbolic aggregation of time series. New Perspectives on the Use of Online Learning for Congestion Level Prediction over Traffic Data. A Novel Fra …

High-dimensional Neural Feature using Rectified Linear Unit and Random Matrix Instance


Title	High-dimensional Neural Feature using Rectified Linear Unit and Random Matrix Instance
Authors	Alireza M. Javid, Arun Venkitaraman, Mikael Skoglund, Saikat Chatterjee
Abstract	We design a ReLU-based multilayer neural network to generate a rich high-dimensional feature vector. The feature guarantees a monotonically decreasing training cost as the number of layers increases. We design the weight matrix in each layer to extend the feature vectors to a higher dimensional space while providing a richer representation in the sense of training cost. Linear projection to the target in the higher dimensional space leads to a lower training cost if a convex cost is minimized. An $\ell_2$-norm convex constraint is used in the minimization to improve the generalization error and avoid overfitting. The regularization hyperparameters of the network are derived analytically to guarantee a monotonic decrement of the training cost and therefore, it eliminates the need for cross-validation to find the regularization hyperparameter in each layer.
Tasks
Published	2020-03-29
URL	https://arxiv.org/abs/2003.13058v1
PDF	https://arxiv.org/pdf/2003.13058v1.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-neural-feature-using
Repo
Framework

Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing


Title	Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing
Authors	Joel Stehouwer, Amin Jourabloo, Yaojie Liu, Xiaoming Liu
Abstract	Using printed photograph and replaying videos of biometric modalities, such as iris, fingerprint and face, are common attacks to fool the recognition systems for granting access as the genuine user. With the growing online person-to-person shopping (e.g., Ebay and Craigslist), such attacks also threaten those services, where the online photo illustration might not be captured from real items but from paper or digital screen. Thus, the study of anti-spoofing should be extended from modality-specific solutions to generic-object-based ones. In this work, we define and tackle the problem of Generic Object Anti-Spoofing (GOAS) for the first time. One significant cue to detect these attacks is the noise patterns introduced by the capture sensors and spoof mediums. Different sensor/medium combinations can result in diverse noise patterns. We propose a GAN-based architecture to synthesize and identify the noise patterns from seen and unseen medium/sensor combinations. We show that the procedure of synthesis and identification are mutually beneficial. We further demonstrate the learned GOAS models can directly contribute to modality-specific anti-spoofing without domain transfer. The code and GOSet dataset are available at cvlab.cse.msu.edu/project-goas.html.
Tasks
Published	2020-03-29
URL	https://arxiv.org/abs/2003.13043v2
PDF	https://arxiv.org/pdf/2003.13043v2.pdf
PWC	https://paperswithcode.com/paper/noise-modeling-synthesis-and-classification
Repo
Framework

ABBA: Adaptive Brownian bridge-based symbolic aggregation of time series


Title	ABBA: Adaptive Brownian bridge-based symbolic aggregation of time series
Authors	Steven Elsworth, Stefan Güttel
Abstract	A new symbolic representation of time series, called ABBA, is introduced. It is based on an adaptive polygonal chain approximation of the time series into a sequence of tuples, followed by a mean-based clustering to obtain the symbolic representation. We show that the reconstruction error of this representation can be modelled as a random walk with pinned start and end points, a so-called Brownian bridge. This insight allows us to make ABBA essentially parameter-free, except for the approximation tolerance which must be chosen. Extensive comparisons with the SAX and 1d-SAX representations are included in the form of performance profiles, showing that ABBA is able to better preserve the essential shape information of time series compared to other approaches. Advantages and applications of ABBA are discussed, including its in-built differencing property and use for anomaly detection, and Python implementations provided.
Tasks	Anomaly Detection, Time Series
Published	2020-03-27
URL	https://arxiv.org/abs/2003.12469v1
PDF	https://arxiv.org/pdf/2003.12469v1.pdf
PWC	https://paperswithcode.com/paper/abba-adaptive-brownian-bridge-based-symbolic
Repo
Framework

New Perspectives on the Use of Online Learning for Congestion Level Prediction over Traffic Data


Title	New Perspectives on the Use of Online Learning for Congestion Level Prediction over Traffic Data
Authors	Eric L. Manibardo, Ibai Laña, Jesus L. Lobo, Javier Del Ser
Abstract	This work focuses on classification over time series data. When a time series is generated by non-stationary phenomena, the pattern relating the series with the class to be predicted may evolve over time (concept drift). Consequently, predictive models aimed to learn this pattern may become eventually obsolete, hence failing to sustain performance levels of practical use. To overcome this model degradation, online learning methods incrementally learn from new data samples arriving over time, and accommodate eventual changes along the data stream by implementing assorted concept drift strategies. In this manuscript we elaborate on the suitability of online learning methods to predict the road congestion level based on traffic speed time series data. We draw interesting insights on the performance degradation when the forecasting horizon is increased. As opposed to what is done in most literature, we provide evidence of the importance of assessing the distribution of classes over time before designing and tuning the learning model. This previous exercise may give a hint of the predictability of the different congestion levels under target. Experimental results are discussed over real traffic speed data captured by inductive loops deployed over Seattle (USA). Several online learning methods are analyzed, from traditional incremental learning algorithms to more elaborated deep learning models. As shown by the reported results, when increasing the prediction horizon, the performance of all models degrade severely due to the distribution of classes along time, which supports our claim about the importance of analyzing this distribution prior to the design of the model.
Tasks	Time Series
Published	2020-03-27
URL	https://arxiv.org/abs/2003.14304v1
PDF	https://arxiv.org/pdf/2003.14304v1.pdf
PWC	https://paperswithcode.com/paper/new-perspectives-on-the-use-of-online
Repo
Framework

A Novel Framework with Information Fusion and Neighborhood Enhancement for User Identity Linkage


Title	A Novel Framework with Information Fusion and Neighborhood Enhancement for User Identity Linkage
Authors	Siyuan Chen, Jiahai Wang, Xin Du, Yanqing Hu
Abstract	User identity linkage across social networks is an essential problem for cross-network data mining. Since network structure, profile and content information describe different aspects of users, it is critical to learn effective user representations that integrate heterogeneous information. This paper proposes a novel framework with INformation FUsion and Neighborhood Enhancement (INFUNE) for user identity linkage. The information fusion component adopts a group of encoders and decoders to fuse heterogeneous information and generate discriminative node embeddings for preliminary matching. Then, these embeddings are fed to the neighborhood enhancement component, a novel graph neural network, to produce adaptive neighborhood embeddings that reflect the overlapping degree of neighborhoods of varying candidate user pairs. The importance of node embeddings and neighborhood embeddings are weighted for final prediction. The proposed method is evaluated on real-world social network data. The experimental results show that INFUNE significantly outperforms existing state-of-the-art methods.
Tasks
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07122v1
PDF	https://arxiv.org/pdf/2003.07122v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-framework-with-information-fusion-and
Repo
Framework

Unsupervised Pool-Based Active Learning for Linear Regression


Title	Unsupervised Pool-Based Active Learning for Linear Regression
Authors	Ziang Liu, Dongrui Wu
Abstract	In many real-world machine learning applications, unlabeled data can be easily obtained, but it is very time-consuming and/or expensive to label them. So, it is desirable to be able to select the optimal samples to label, so that a good machine learning model can be trained from a minimum amount of labeled data. Active learning (AL) has been widely used for this purpose. However, most existing AL approaches are supervised: they train an initial model from a small amount of labeled samples, query new samples based on the model, and then update the model iteratively. Few of them have considered the completely unsupervised AL problem, i.e., starting from zero, how to optimally select the very first few samples to label, without knowing any label information at all. This problem is very challenging, as no label information can be utilized. This paper studies unsupervised pool-based AL for linear regression problems. We propose a novel AL approach that considers simultaneously the informativeness, representativeness, and diversity, three essential criteria in AL. Extensive experiments on 14 datasets from various application domains, using three different linear regression models (ridge regression, LASSO, and linear support vector regression), demonstrated the effectiveness of our proposed approach.
Tasks	Active Learning
Published	2020-01-14
URL	https://arxiv.org/abs/2001.05028v1
PDF	https://arxiv.org/pdf/2001.05028v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-pool-based-active-learning-for
Repo
Framework

The Risk to Population Health Equity Posed by Automated Decision Systems: A Narrative Review


Title	The Risk to Population Health Equity Posed by Automated Decision Systems: A Narrative Review
Authors	Mitchell Burger
Abstract	Artificial intelligence is already ubiquitous, and is increasingly being used to autonomously make ever more consequential decisions. However, there has been relatively little research into the consequences for equity of the use of narrow AI and automated decision systems in medicine and public health. A narrative review using a hermeneutic approach was undertaken to explore current and future uses of AI in medicine and public health, issues that have emerged, and longer-term implications for population health. Accounts in the literature reveal a tremendous expectation on AI to transform medical and public health practices, especially regarding precision medicine and precision public health. Automated decisions being made about disease detection, diagnosis, treatment, and health funding allocation have significant consequences for individual and population health and wellbeing. Meanwhile, it is evident that issues of bias, incontestability, and erosion of privacy have emerged in sensitive domains where narrow AI and automated decision systems are in common use. As the use of automated decision systems expands, it is probable that these same issues will manifest widely in medicine and public health applications. Bias, incontestability, and erosion of privacy are mechanisms by which existing social, economic and health disparities are perpetuated and amplified. The implication is that there is a significant risk that use of automated decision systems in health will exacerbate existing population health inequities. The industrial scale and rapidity with which automated decision systems can be applied to whole populations heightens the risk to population health equity. There is a need therefore to design and implement automated decision systems with care, monitor their impact over time, and develop capacities to respond to issues as they emerge.
Tasks
Published	2020-01-18
URL	https://arxiv.org/abs/2001.06615v1
PDF	https://arxiv.org/pdf/2001.06615v1.pdf
PWC	https://paperswithcode.com/paper/the-risk-to-population-health-equity-posed-by
Repo
Framework

Transformer Networks for Trajectory Forecasting


Title	Transformer Networks for Trajectory Forecasting
Authors	Francesco Giuliari, Irtiza Hasan, Marco Cristani, Fabio Galasso
Abstract	Most recent successes on forecasting the people motion are based on LSTM models and all most recent progress has been achieved by modelling the social interaction among people and the people interaction with the scene. We question the use of the LSTM models and propose the novel use of Transformer Networks for trajectory forecasting. This is a fundamental switch from the sequential step-by-step processing of LSTMs to the only-attention-based memory mechanisms of Transformers. In particular, we consider both the original Transformer Network (TF) and the larger Bidirectional Transformer (BERT), state-of-the-art on all natural language processing tasks. Our proposed Transformers predict the trajectories of the individual people in the scene. These are \simple” model because each person is modelled separately without any complex human-human nor scene interaction terms. In particular, the TF model without bells and whistles yields the best score on the largest and most challenging trajectory forecasting benchmark of TrajNet. Additionally, its extension which predicts multiple plausible future trajectories performs on par with more engineered techniques on the 5 datasets of ETH+UCY. Finally, we show that Transformers may deal with missing observations, as it may be the case with real sensor data.
Tasks
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08111v1
PDF	https://arxiv.org/pdf/2003.08111v1.pdf
PWC	https://paperswithcode.com/paper/transformer-networks-for-trajectory
Repo
Framework

What is the Value of Data? On Mathematical Methods for Data Quality Estimation


Title	What is the Value of Data? On Mathematical Methods for Data Quality Estimation
Authors	Netanel Raviv, Siddharth Jain, Jehoshua Bruck
Abstract	Data is one of the most important assets of the information age, and its societal impact is undisputed. Yet, rigorous methods of assessing the quality of data are lacking. In this paper, we propose a formal definition for the quality of a given dataset. We assess a dataset’s quality by a quantity we call the expected diameter, which measures the expected disagreement between two randomly chosen hypotheses that explain it, and has recently found applications in active learning. We focus on Boolean hyperplanes, and utilize a collection of Fourier analytic, algebraic, and probabilistic methods to come up with theoretical guarantees and practical solutions for the computation of the expected diameter. We also study the behaviour of the expected diameter on algebraically structured datasets, conduct experiments that validate this notion of quality, and demonstrate the feasibility of our techniques.
Tasks	Active Learning
Published	2020-01-09
URL	https://arxiv.org/abs/2001.03464v1
PDF	https://arxiv.org/pdf/2001.03464v1.pdf
PWC	https://paperswithcode.com/paper/what-is-the-value-of-data-on-mathematical
Repo
Framework

Predicting Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and Recurrent Neural Networks


Title	Predicting Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and Recurrent Neural Networks
Authors	Hao Liu, Chang Liu, Jason T. L. Wang, Haimin Wang
Abstract	We present two recurrent neural networks (RNNs), one based on gated recurrent units and the other based on long short-term memory, for predicting whether an active region (AR) that produces an M- or X-class flare will also produce a coronal mass ejection (CME). We model data samples in an AR as time series and use the RNNs to capture temporal information of the data samples. Each data sample has 18 physical parameters, or features, derived from photospheric vector magnetic field data taken by the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO). We survey M- and X-class flares that occurred from 2010 May to 2019 May using the Geostationary Operational Environmental Satellite’s X-ray flare catalogs provided by the National Centers for Environmental Information (NCEI), and select those flares with identified ARs in the NCEI catalogs. In addition, we extract the associations of flares and CMEs from the Space Weather Database Of Notifications, Knowledge, Information (DONKI). We use the information gathered above to build the labels (positive versus negative) of the data samples at hand. Experimental results demonstrate the superiority of our RNNs over closely related machine learning methods in predicting the labels of the data samples. We also discuss an extension of our approach to predict a probabilistic estimate of how likely an M- or X-class flare will initiate a CME, with good performance results. To our knowledge this is the first time that RNNs have been used for CME prediction.
Tasks	Time Series
Published	2020-02-22
URL	https://arxiv.org/abs/2002.10953v1
PDF	https://arxiv.org/pdf/2002.10953v1.pdf
PWC	https://paperswithcode.com/paper/predicting-coronal-mass-ejections-using-1
Repo
Framework

Cat Swarm Optimization Algorithm – A Survey and Performance Evaluation


Title	Cat Swarm Optimization Algorithm – A Survey and Performance Evaluation
Authors	Aram M. Ahmed, Tarik A. Rashid, Soran Ab. M. Saeed
Abstract	This paper presents an in-depth survey and performance evaluation of the Cat Swarm Optimization (CSO) Algorithm. CSO is a robust and powerful metaheuristic swarm-based optimization approach that has received very positive feedback since its emergence. It has been tackling many optimization problems and many variants of it have been introduced. However, the literature lacks a detailed survey or a performance evaluation in this regard. Therefore, this paper is an attempt to review all these works, including its developments and applications, and group them accordingly. In addition, CSO is tested on 23 classical benchmark functions and 10 modern benchmark functions (CEC 2019). The results are then compared against three novel and powerful optimization algorithms, namely Dragonfly algorithm (DA), Butterfly optimization algorithm (BOA) and Fitness Dependent Optimizer (FDO). These algorithms are then ranked according to Friedman test and the results show that CSO ranks first on the whole. Finally, statistical approaches are employed to further confirm the outperformance of CSO algorithm.
Tasks
Published	2020-01-10
URL	https://arxiv.org/abs/2001.11822v1
PDF	https://arxiv.org/pdf/2001.11822v1.pdf
PWC	https://paperswithcode.com/paper/cat-swarm-optimization-algorithm-a-survey-and
Repo
Framework

Flexible Bayesian Nonlinear Model Configuration


Title	Flexible Bayesian Nonlinear Model Configuration
Authors	Aliaksandr Hubin, Geir Storvik, Florian Frommlet
Abstract	Regression models are used in a wide range of applications providing a powerful scientific tool for researchers from different fields. Linear models are often not sufficient to describe the complex relationship between input variables and a response. This relationship can be better described by non-linearities and complex functional interactions. Deep learning models have been extremely successful in terms of prediction although they are often difficult to specify and potentially suffer from overfitting. In this paper, we introduce a class of Bayesian generalized nonlinear regression models with a comprehensive non-linear feature space. Non-linear features are generated hierarchically, similarly to deep learning, but have additional flexibility on the possible types of features to be considered. This flexibility, combined with variable selection, allows us to find a small set of important features and thereby more interpretable models. A genetically modified Markov chain Monte Carlo algorithm is developed to make inference. Model averaging is also possible within our framework. In various applications, we illustrate how our approach is used to obtain meaningful non-linear models. Additionally, we compare its predictive performance with a number of machine learning algorithms.
Tasks
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02929v1
PDF	https://arxiv.org/pdf/2003.02929v1.pdf
PWC	https://paperswithcode.com/paper/flexible-bayesian-nonlinear-model
Repo
Framework

KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations


Title	KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
Authors	Yang You, Yujing Lou, Chengkun Li, Zhoujun Cheng, Liangwei Li, Lizhuang Ma, Cewu Lu, Weiming Wang
Abstract	Detecting 3D objects keypoints is of great interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either lack scalability or bring ambiguity to the definition of keypoints. Therefore, we present KeypointNet: the first large-scale and diverse 3D keypoint dataset that contains 83,231 keypoints and 8,329 3D models from 16 object categories, by leveraging numerous human annotations. To handle the inconsistency between annotations from different people, we propose a novel method to aggregate these keypoints automatically, through minimization of a fidelity loss. Finally, ten state-of-the-art methods are benchmarked on our proposed dataset.
Tasks
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12687v2
PDF	https://arxiv.org/pdf/2002.12687v2.pdf
PWC	https://paperswithcode.com/paper/keypointnet-a-large-scale-3d-keypoint-dataset
Repo
Framework

Sentiment Analysis with Contextual Embeddings and Self-Attention


Title	Sentiment Analysis with Contextual Embeddings and Self-Attention
Authors	Katarzyna Biesialska, Magdalena Biesialska, Henryk Rybinski
Abstract	In natural language the intended meaning of a word or phrase is often implicit and depends on the context. In this work, we propose a simple yet effective method for sentiment analysis using contextual embeddings and a self-attention mechanism. The experimental results for three languages, including morphologically rich Polish and German, show that our model is comparable to or even outperforms state-of-the-art models. In all cases the superiority of models leveraging contextual embeddings is demonstrated. Finally, this work is intended as a step towards introducing a universal, multilingual sentiment classifier.
Tasks	Sentiment Analysis
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05574v1
PDF	https://arxiv.org/pdf/2003.05574v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-with-contextual-embeddings
Repo
Framework

Natural Language Interaction to Facilitate Mental Models of Remote Robots


Title	Natural Language Interaction to Facilitate Mental Models of Remote Robots
Authors	Francisco J. Chiyah Garcia, José Lopes, Helen Hastie
Abstract	Increasingly complex and autonomous robots are being deployed in real-world environments with far-reaching consequences. High-stakes scenarios, such as emergency response or offshore energy platform and nuclear inspections, require robot operators to have clear mental models of what the robots can and can’t do. However, operators are often not the original designers of the robots and thus, they do not necessarily have such clear mental models, especially if they are novice users. This lack of mental model clarity can slow adoption and can negatively impact human-machine teaming. We propose that interaction with a conversational assistant, who acts as a mediator, can help the user with understanding the functionality of remote robots and increase transparency through natural language explanations, as well as facilitate the evaluation of operators’ mental models.
Tasks
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05870v1
PDF	https://arxiv.org/pdf/2003.05870v1.pdf
PWC	https://paperswithcode.com/paper/natural-language-interaction-to-facilitate
Repo
Framework