October 19, 2019

3126 words 15 mins read

Paper Group ANR 254

Secure Mobile Edge Computing in IoT via Collaborative Online Learning. Analysis of spectral clustering algorithms for community detection: the general bipartite setting. Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling. On semi-supervised learning. ANS: Adaptive Network Scaling for D …

Secure Mobile Edge Computing in IoT via Collaborative Online Learning


Title	Secure Mobile Edge Computing in IoT via Collaborative Online Learning
Authors	Bingcong Li, Tianyi Chen, Georgios B. Giannakis
Abstract	To accommodate heterogeneous tasks in Internet of Things (IoT), a new communication and computing paradigm termed mobile edge computing emerges that extends computing services from the cloud to edge, but at the same time exposes new challenges on security. The present paper studies online security-aware edge computing under jamming attacks. Leveraging online learning tools, novel algorithms abbreviated as SAVE-S and SAVE-A are developed to cope with the stochastic and adversarial forms of jamming, respectively. Without utilizing extra resources such as spectrum and transmission power to evade jamming attacks, SAVE-S and SAVE-A can select the most reliable server to offload computing tasks with minimal privacy and security concerns. It is analytically established that without any prior information on future jamming and server security risks, the proposed schemes can achieve ${\cal O}\big(\sqrt{T}\big)$ regret. Information sharing among devices can accelerate the security-aware computing tasks. Incorporating the information shared by other devices, SAVE-S and SAVE-A offer impressive improvements on the sublinear regret, which is guaranteed by what is termed “value of cooperation.” Effectiveness of the proposed schemes is tested on both synthetic and real datasets.
Tasks
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03591v1
PDF	http://arxiv.org/pdf/1805.03591v1.pdf
PWC	https://paperswithcode.com/paper/secure-mobile-edge-computing-in-iot-via
Repo
Framework

Analysis of spectral clustering algorithms for community detection: the general bipartite setting


Title	Analysis of spectral clustering algorithms for community detection: the general bipartite setting
Authors	Zhixin Zhou, Arash A. Amini
Abstract	We consider spectral clustering algorithms for community detection under a general bipartite stochastic block model (SBM). A modern spectral clustering algorithm consists of three steps: (1) regularization of an appropriate adjacency or Laplacian matrix (2) a form of spectral truncation and (3) a k-means type algorithm in the reduced spectral domain. We focus on the adjacency-based spectral clustering and for the first step, propose a new data-driven regularization that can restore the concentration of the adjacency matrix even for the sparse networks. This result is based on recent work on regularization of random binary matrices, but avoids using unknown population level parameters, and instead estimates the necessary quantities from the data. We also propose and study a novel variation of the spectral truncation step and show how this variation changes the nature of the misclassification rate in a general SBM. We then show how the consistency results can be extended to models beyond SBMs, such as inhomogeneous random graph models with approximate clusters, including a graphon clustering problem, as well as general sub-Gaussian biclustering. A theme of the paper is providing a better understanding of the analysis of spectral methods for community detection and establishing consistency results, under fairly general clustering models and for a wide regime of degree growths, including sparse cases where the average expected degree grows arbitrarily slowly.
Tasks	Community Detection
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04547v2
PDF	http://arxiv.org/pdf/1803.04547v2.pdf
PWC	https://paperswithcode.com/paper/analysis-of-spectral-clustering-algorithms
Repo
Framework

Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling


Title	Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling
Authors	Prashanth Gurunath Shivakumar, Haoqi Li, Kevin Knight, Panayiotis Georgiou
Abstract	Automatic speech recognition (ASR) systems often make unrecoverable errors due to subsystem pruning (acoustic, language and pronunciation models); for example pruning words due to acoustics using short-term context, prior to rescoring with long-term context based on linguistics. In this work we model ASR as a phrase-based noisy transformation channel and propose an error correction system that can learn from the aggregate errors of all the independent modules constituting the ASR and attempt to invert those. The proposed system can exploit long-term context using a neural network language model and can better choose between existing ASR output possibilities as well as re-introduce previously pruned or unseen (out-of-vocabulary) phrases. It provides corrections under poorly performing ASR conditions without degrading any accurate transcriptions; such corrections are greater on top of out-of-domain and mismatched data ASR. Our system consistently provides improvements over the baseline ASR, even when baseline is further optimized through recurrent neural network language model rescoring. This demonstrates that any ASR improvements can be exploited independently and that our proposed system can potentially still provide benefits on highly optimized ASR. Finally, we present an extensive analysis of the type of errors corrected by our system.
Tasks	Language Modelling, Speech Recognition
Published	2018-02-07
URL	http://arxiv.org/abs/1802.02607v2
PDF	http://arxiv.org/pdf/1802.02607v2.pdf
PWC	https://paperswithcode.com/paper/learning-from-past-mistakes-improving
Repo
Framework

On semi-supervised learning


Title	On semi-supervised learning
Authors	Alejandro Cholaquidis, Ricardo Fraimand, Mariela Sued
Abstract	Semi-supervised learning deals with the problem of how, if possible, to take advantage of a huge amount of unclassified data, to perform a classification in situations when, typically, there is little labeled data. Even though this is not always possible (it depends on how useful, for inferring the labels, it would be to know the distribution of the unlabeled data), several algorithm have been proposed recently. %but in general they are not proved to outperform A new algorithm is proposed, that under almost necessary conditions, %and it is proved that it attains asymptotically the performance of the best theoretical rule as the amount of unlabeled data tends to infinity. The set of necessary assumptions, although reasonable, show that semi-supervised classification only works for very well conditioned problems. The focus is on understanding when and why semi-supervised learning works when the size of the initial training sample remains fixed and the asymptotic is on the size of the unlabeled data. The performance of the algorithm is assessed in the well known “Isolet” real-data of phonemes, where a strong dependence on the choice of the initial training sample is shown.
Tasks
Published	2018-05-22
URL	https://arxiv.org/abs/1805.09180v3
PDF	https://arxiv.org/pdf/1805.09180v3.pdf
PWC	https://paperswithcode.com/paper/on-semi-supervised-learning
Repo
Framework

ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models


Title	ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models
Authors	Yueh-Hua Wu, Fan-Yun Sun, Yen-Yu Chang, Shou-De Lin
Abstract	This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation functions for deep learning models. We also propose an Adaptive Network Scaling framework to find a suitable scale of the rewards during learning for better performance. We conducted empirical studies to justify the solution.
Tasks
Published	2018-09-06
URL	http://arxiv.org/abs/1809.02112v3
PDF	http://arxiv.org/pdf/1809.02112v3.pdf
PWC	https://paperswithcode.com/paper/ans-adaptive-network-scaling-for-deep
Repo
Framework

Hyperspectral Images Classification Using Energy Profiles of Spatial and Spectral Features


Title	Hyperspectral Images Classification Using Energy Profiles of Spatial and Spectral Features
Authors	Hamid Reza Shahdoosti
Abstract	This paper proposes a spatial feature extraction method based on energy of the features for classification of the hyperspectral data. A proposed orthogonal filter set extracts spatial features with maximum energy from the principal components and then, a profile is constructed based on these features. The important characteristic of the proposed approach is that the filter sets coefficients are extracted from statistical properties of data, thus they are more consistent with the type and texture of the remotely sensed images compared with those of other filters such as Gabor. To assess the performance of the proposed feature extraction method, the extracted features are fed into a support vector machine (SVM) classifier. Experiments on the widely used hyperspectral images namely, Indian Pines, and Salinas data sets reveal that the proposed approach improves the classification results in comparison with some recent spectral spatial classification methods.
Tasks
Published	2018-07-24
URL	http://arxiv.org/abs/1807.08943v1
PDF	http://arxiv.org/pdf/1807.08943v1.pdf
PWC	https://paperswithcode.com/paper/hyperspectral-images-classification-using
Repo
Framework

End-to-end contextual speech recognition using class language models and a token passing decoder


Title	End-to-end contextual speech recognition using class language models and a token passing decoder
Authors	Zhehuai Chen, Mahaveer Jain, Yongqiang Wang, Michael L. Seltzer, Christian Fuegen
Abstract	End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to adapt when mismatch exists between training and test data. In this work, we focus on contextual speech recognition, which is particularly challenging for E2E models because it introduces significant mismatch between training and test data. To improve the performance in the presence of complex contextual information, we propose to use class-based language models(CLM) that can populate the classes with contextdependent information in real-time. To enable this approach to scale to a large number of class members and minimize search errors, we propose a token passing decoder with efficient token recombination for E2E systems for the first time. We evaluate the proposed system on general and contextual ASR, and achieve relative 62% Word Error Rate(WER) reduction for contextual ASR without hurting performance for general ASR. We show that the proposed method performs well without modification of the decoding hyper-parameters across tasks, making it a general solution for E2E ASR.
Tasks	Speech Recognition
Published	2018-12-05
URL	http://arxiv.org/abs/1812.02142v1
PDF	http://arxiv.org/pdf/1812.02142v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-contextual-speech-recognition
Repo
Framework

Prototyping Virtual Reality Serious Games for Building Earthquake Preparedness: The Auckland City Hospital Case Study


Title	Prototyping Virtual Reality Serious Games for Building Earthquake Preparedness: The Auckland City Hospital Case Study
Authors	Ruggiero Lovreglio, Vicente Gonzalez, Zhenan Feng, Robert Amor, Michael Spearpoint, Jared Thomas, Margaret Trotter, Rafael Sacks
Abstract	Enhancing evacuee safety is a key factor in reducing the number of injuries and deaths that result from earthquakes. One way this can be achieved is by training occupants. Virtual Reality (VR) and Serious Games (SGs), represent novel techniques that may overcome the limitations of traditional training approaches. VR and SGs have been examined in the fire emergency context, however, their application to earthquake preparedness has not yet been extensively examined. We provide a theoretical discussion of the advantages and limitations of using VR SGs to investigate how building occupants behave during earthquake evacuations and to train building occupants to cope with such emergencies. We explore key design components for developing a VR SG framework: (a) what features constitute an earthquake event, (b) which building types can be selected and represented within the VR environment, (c) how damage to the building can be determined and represented, (d) how non-player characters (NPC) can be designed, and (e) what level of interaction there can be between NPC and the human participants. We illustrate the above by presenting the Auckland City Hospital, New Zealand as a case study, and propose a possible VR SG training tool to enhance earthquake preparedness in public buildings.
Tasks
Published	2018-02-26
URL	http://arxiv.org/abs/1802.09119v1
PDF	http://arxiv.org/pdf/1802.09119v1.pdf
PWC	https://paperswithcode.com/paper/prototyping-virtual-reality-serious-games-for
Repo
Framework

Analyzing high-dimensional time-series data using kernel transfer operator eigenfunctions


Title	Analyzing high-dimensional time-series data using kernel transfer operator eigenfunctions
Authors	Stefan Klus, Sebastian Peitz, Ingmar Schuster
Abstract	Kernel transfer operators, which can be regarded as approximations of transfer operators such as the Perron-Frobenius or Koopman operator in reproducing kernel Hilbert spaces, are defined in terms of covariance and cross-covariance operators and have been shown to be closely related to the conditional mean embedding framework developed by the machine learning community. The goal of this paper is to show how the dominant eigenfunctions of these operators in combination with gradient-based optimization techniques can be used to detect long-lived coherent patterns in high-dimensional time-series data. The results will be illustrated using video data and a fluid flow example.
Tasks	Time Series
Published	2018-05-16
URL	http://arxiv.org/abs/1805.10118v1
PDF	http://arxiv.org/pdf/1805.10118v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-high-dimensional-time-series-data
Repo
Framework

Large Margin Few-Shot Learning


Title	Large Margin Few-Shot Learning
Authors	Yong Wang, Xiao-Ming Wu, Qimai Li, Jiatao Gu, Wangmeng Xiang, Lei Zhang, Victor O. K. Li
Abstract	The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the classification loss function with a large margin distance loss function for training. Extensive experiments on two state-of-the-art few-shot learning methods, graph neural networks and prototypical networks, show that our method can improve the performance of existing models substantially with very little computational overhead, demonstrating the effectiveness of the large margin principle and the potential of our method.
Tasks	Few-Shot Learning
Published	2018-07-08
URL	http://arxiv.org/abs/1807.02872v2
PDF	http://arxiv.org/pdf/1807.02872v2.pdf
PWC	https://paperswithcode.com/paper/large-margin-few-shot-learning
Repo
Framework

Learning a Policy for Opportunistic Active Learning


Title	Learning a Policy for Opportunistic Active Learning
Authors	Aishwarya Padmakumar, Peter Stone, Raymond J. Mooney
Abstract	Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions. Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in an interactive object retrieval task. In this work, we use reinforcement learning for such an object retrieval task, to learn a policy that effectively trades off task completion with model improvement that would benefit future tasks.
Tasks	Active Learning
Published	2018-08-29
URL	http://arxiv.org/abs/1808.10009v1
PDF	http://arxiv.org/pdf/1808.10009v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-policy-for-opportunistic-active
Repo
Framework


Title	Prediction of the Influence of Navigation Scan-path on Perceived Quality of Free-Viewpoint Videos
Authors	Suiyi Ling, Jesús Gutiérrez, Gu Ke, Patrick Le Callet
Abstract	Free-Viewpoint Video (FVV) systems allow the viewers to freely change the viewpoints of the scene. In such systems, view synthesis and compression are the two main sources of artifacts influencing the perceived quality. To assess this influence, quality evaluation studies are often carried out using conventional displays and generating predefined navigation trajectories mimicking the possible movement of the viewers when exploring the content. Nevertheless, as different trajectories may lead to different conclusions in terms of visual quality when benchmarking the performance of the systems, methods to identify critical trajectories are needed. This paper aims at exploring the impact of exploration trajectories (defined as Hypothetical Rendering Trajectories: HRT) on perceived quality of FVV subjectively and objectively, providing two main contributions. Firstly, a subjective assessment test including different HRTs was carried out and analyzed. The results demonstrate and quantify the influence of HRT in the perceived quality. Secondly, we propose a new objective video quality assessment measure to objectively predict the impact of HRT. This measure, based on Sketch-Token representation, models how the categories of the contours change spatially and temporally from a higher semantic level. Performance in comparison with existing quality metrics for FVV, highlight promising results for automatic detection of most critical HRTs for the benchmark of immersive systems.
Tasks	Video Quality Assessment
Published	2018-10-10
URL	http://arxiv.org/abs/1810.04409v1
PDF	http://arxiv.org/pdf/1810.04409v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-the-influence-of-navigation
Repo
Framework

Ranking Data with Continuous Labels through Oriented Recursive Partitions


Title	Ranking Data with Continuous Labels through Oriented Recursive Partitions
Authors	Stephan Clémençon, Mastane Achab
Abstract	We formulate a supervised learning problem, referred to as continuous ranking, where a continuous real-valued label Y is assigned to an observable r.v. X taking its values in a feature space $\mathcal{X}$ and the goal is to order all possible observations x in $\mathcal{X}$ by means of a scoring function $s:\mathcal{X}\rightarrow \mathbb{R}$ so that s(X) and Y tend to increase or decrease together with highest probability. This problem generalizes bi/multi-partite ranking to a certain extent and the task of finding optimal scoring functions s(x) can be naturally cast as optimization of a dedicated functional criterion, called the IROC curve here, or as maximization of the Kendall ${\tau}$ related to the pair (s(X), Y ). From the theoretical side, we describe the optimal elements of this problem and provide statistical guarantees for empirical Kendall ${\tau}$ maximization under appropriate conditions for the class of scoring function candidates. We also propose a recursive statistical learning algorithm tailored to empirical IROC curve optimization and producing a piecewise constant scoring function that is fully described by an oriented binary tree. Preliminary numerical experiments highlight the difference in nature between regression and continuous ranking and provide strong empirical evidence of the performance of empirical optimizers of the criteria proposed.
Tasks
Published	2018-01-17
URL	http://arxiv.org/abs/1801.05772v1
PDF	http://arxiv.org/pdf/1801.05772v1.pdf
PWC	https://paperswithcode.com/paper/ranking-data-with-continuous-labels-through
Repo
Framework

Interpretable Deep Convolutional Neural Networks via Meta-learning


Title	Interpretable Deep Convolutional Neural Networks via Meta-learning
Authors	Xuan Liu, Xiaoguang Wang, Stan Matwin
Abstract	Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model’s outputs. The recent movement for “algorithmic fairness” also stipulates explainability, and therefore interpretability of learning models. And yet the most successful contemporary Machine Learning approaches, the Deep Neural Networks, produce models that are highly non-interpretable. We attempt to address this challenge by proposing a technique called CNN-INTE to interpret deep Convolutional Neural Networks (CNN) via meta-learning. In this work, we interpret a specific hidden layer of the deep CNN model on the MNIST image dataset. We use a clustering algorithm in a two-level structure to find the meta-level training data and Random Forest as base learning algorithms to generate the meta-level test data. The interpretation results are displayed visually via diagrams, which clearly indicates how a specific test instance is classified. Our method achieves global interpretation for all the test instances without sacrificing the accuracy obtained by the original deep CNN model. This means our model is faithful to the deep CNN model, which leads to reliable interpretations.
Tasks	Meta-Learning
Published	2018-02-02
URL	http://arxiv.org/abs/1802.00560v2
PDF	http://arxiv.org/pdf/1802.00560v2.pdf
PWC	https://paperswithcode.com/paper/interpretable-deep-convolutional-neural
Repo
Framework

A mosaic of Chu spaces and Channel Theory with applications to Object Identification and Mereological Complexity


Title	A mosaic of Chu spaces and Channel Theory with applications to Object Identification and Mereological Complexity
Authors	Chris Fields, James F. Glazebrook
Abstract	Chu Spaces and Channel Theory are well established areas of investigation in the general context of category theory. We review a range of examples and applications of these methods in logic and computer science, including Formal Concept Analysis, distributed systems and ontology development. We then employ these methods to describe human object perception, beginning with the construction of uncategorized object files and proceeding through categorization, individual object identification and the tracking of object identity through time. We investigate the relationship between abstraction and mereological categorization, particularly as these affect object identity tracking. This we accomplish in terms of information flow that is semantically structured in terms of local logics, while at the same time this framework also provides an inferential mechanism towards identification and perception. We show how a mereotopology naturally emerges from the representation of classifications by simplicial complexes, and briefly explore the emergence of geometric relations and interactions between objects.
Tasks
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08874v1
PDF	http://arxiv.org/pdf/1803.08874v1.pdf
PWC	https://paperswithcode.com/paper/a-mosaic-of-chu-spaces-and-channel-theory
Repo
Framework