April 1, 2020

3097 words 15 mins read

Paper Group ANR 475

aphBO-2GP-3B: A budgeted asynchronously-parallel multi-acquisition for known/unknown constrained Bayesian optimization on high-performing computing architecture. Shared Mobile-Cloud Inference for Collaborative Intelligence. Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything. Imbalance Learning for Variable Star Classi …

aphBO-2GP-3B: A budgeted asynchronously-parallel multi-acquisition for known/unknown constrained Bayesian optimization on high-performing computing architecture


Title	aphBO-2GP-3B: A budgeted asynchronously-parallel multi-acquisition for known/unknown constrained Bayesian optimization on high-performing computing architecture
Authors	Anh Tran, Scott McCann, John M. Furlan, Krishnan V. Pagalthivarthi, Robert J. Visintainer, Tim Wildey
Abstract	High-fidelity complex engineering simulations are highly predictive, but also computationally expensive and often require substantial computational efforts. The mitigation of computational burden is usually enabled through parallelism in high-performance cluster (HPC) architecture. In this paper, an asynchronous constrained batch-parallel Bayesian optimization method is proposed to efficiently solve the computationally-expensive simulation-based optimization problems on the HPC platform, with a budgeted computational resource, where the maximum number of simulations is a constant. The advantages of this method are three-fold. First, the efficiency of the Bayesian optimization is improved, where multiple input locations are evaluated massively parallel in an asynchronous manner to accelerate the optimization convergence with respect to physical runtime. This efficiency feature is further improved so that when each of the inputs is finished, another input is queried without waiting for the whole batch to complete. Second, the method can handle both known and unknown constraints. Third, the proposed method considers several acquisition functions at the same time and sample based on an evolving probability mass distribution function using GP-Hedge scheme, where parameters are corresponding to the performance of each acquisition function. The proposed framework is termed aphBO-2GP-3B, which corresponds to asynchronous parallel hedge Bayesian optimization with two Gaussian processes and three batches. The aphBO-2GP-3B framework is demonstrated using two high-fidelity expensive industrial applications, where the first one is based on finite element analysis (FEA) and the second one is based on computational fluid dynamics (CFD) simulations.
Tasks	Gaussian Processes
Published	2020-03-20
URL	https://arxiv.org/abs/2003.09436v1
PDF	https://arxiv.org/pdf/2003.09436v1.pdf
PWC	https://paperswithcode.com/paper/aphbo-2gp-3b-a-budgeted-asynchronously
Repo
Framework

Shared Mobile-Cloud Inference for Collaborative Intelligence


Title	Shared Mobile-Cloud Inference for Collaborative Intelligence
Authors	Mateen Ulhaq, Ivan V. Bajić
Abstract	As AI applications for mobile devices become more prevalent, there is an increasing need for faster execution and lower energy consumption for neural model inference. Historically, the models run on mobile devices have been smaller and simpler in comparison to large state-of-the-art research models, which can only run on the cloud. However, cloud-only inference has drawbacks such as increased network bandwidth consumption and higher latency. In addition, cloud-only inference requires the input data (images, audio) to be fully transferred to the cloud, creating concerns about potential privacy breaches. We demonstrate an alternative approach: shared mobile-cloud inference. Partial inference is performed on the mobile in order to reduce the dimensionality of the input data and arrive at a compact feature tensor, which is a latent space representation of the input signal. The feature tensor is then transmitted to the server for further inference. This strategy can improve inference latency, energy consumption, and network bandwidth usage, as well as provide privacy protection, because the original signal never leaves the mobile. Further performance gain can be achieved by compressing the feature tensor before its transmission.
Tasks
Published	2020-02-01
URL	https://arxiv.org/abs/2002.00157v1
PDF	https://arxiv.org/pdf/2002.00157v1.pdf
PWC	https://paperswithcode.com/paper/shared-mobile-cloud-inference-for
Repo
Framework

Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything


Title	Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything
Authors	Xiao Zhang, Dongrui Wu, Lieyun Ding, Hanbin Luo, Chin-Teng Lin, Tzyy-Ping Jung, Ricardo Chavarriaga
Abstract	An electroencephalogram (EEG) based brain-computer interface (BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g., amyotrophic lateral sclerosis patients, who have no other effective means of communication with another person or a computer. Most studies so far focused on making EEG-based BCI spellers faster and more reliable; however, few have considered their security. Here we show that P300 and steady-state visual evoked potential BCI spellers are very vulnerable, i.e., they can be severely attacked by adversarial perturbations, which are too tiny to be noticed when added to EEG signals, but can mislead the spellers to spell anything the attacker wants. The consequence could range from merely user frustration to severe misdiagnosis in clinical applications. We hope our research can attract more attention to the security of EEG-based BCI spellers, and more broadly, EEG-based BCIs, which has received little attention before.
Tasks	EEG
Published	2020-01-30
URL	https://arxiv.org/abs/2001.11569v3
PDF	https://arxiv.org/pdf/2001.11569v3.pdf
PWC	https://paperswithcode.com/paper/tiny-noise-can-make-an-eeg-based-brain
Repo
Framework

Imbalance Learning for Variable Star Classification


Title	Imbalance Learning for Variable Star Classification
Authors	Zafiirah Hosenie, Robert Lyon, Benjamin Stappers, Arrykrishna Mootoovaloo, Vanessa McBride
Abstract	The accurate automated classification of variable stars into their respective sub-types is difficult. Machine learning based solutions often fall foul of the imbalanced learning problem, which causes poor generalisation performance in practice, especially on rare variable star sub-types. In previous work, we attempted to overcome such deficiencies via the development of a hierarchical machine learning classifier. This ‘algorithm-level’ approach to tackling imbalance, yielded promising results on Catalina Real-Time Survey (CRTS) data, outperforming the binary and multi-class classification schemes previously applied in this area. In this work, we attempt to further improve hierarchical classification performance by applying ‘data-level’ approaches to directly augment the training data so that they better describe under-represented classes. We apply and report results for three data augmentation methods in particular: $\textit{R}$andomly $\textit{A}$ugmented $\textit{S}$ampled $\textit{L}$ight curves from magnitude $\textit{E}$rror ($\texttt{RASLE}$), augmenting light curves with Gaussian Process modelling ($\texttt{GpFit}$) and the Synthetic Minority Over-sampling Technique ($\texttt{SMOTE}$). When combining the ‘algorithm-level’ (i.e. the hierarchical scheme) together with the ‘data-level’ approach, we further improve variable star classification accuracy by 1-4$%$. We found that a higher classification rate is obtained when using $\texttt{GpFit}$ in the hierarchical model. Further improvement of the metric scores requires a better standard set of correctly identified variable stars and, perhaps enhanced features are needed.
Tasks	Classification Of Variable Stars, Data Augmentation
Published	2020-02-27
URL	https://arxiv.org/abs/2002.12386v1
PDF	https://arxiv.org/pdf/2002.12386v1.pdf
PWC	https://paperswithcode.com/paper/imbalance-learning-for-variable-star
Repo
Framework

Bibliometric-enhanced Information Retrieval 10th Anniversary Workshop Edition


Title	Bibliometric-enhanced Information Retrieval 10th Anniversary Workshop Edition
Authors	Guillaume Cabanac, Ingo Frommholz, Philipp Mayr
Abstract	The Bibliometric-enhanced Information Retrieval workshop series (BIR) was launched at ECIR in 2014 \cite{MayrEtAl2014} and it was held at ECIR each year since then. This year we organize the 10th iteration of BIR. The workshop series at ECIR and JCDL/SIGIR tackles issues related to academic search, at the crossroads between Information Retrieval, Natural Language Processing and Bibliometrics. In this overview paper, we summarize the past workshops, present the workshop topics for 2020 and reflect on some future steps for this workshop series.
Tasks	Information Retrieval
Published	2020-01-20
URL	https://arxiv.org/abs/2001.10336v1
PDF	https://arxiv.org/pdf/2001.10336v1.pdf
PWC	https://paperswithcode.com/paper/bibliometric-enhanced-information-retrieval
Repo
Framework

Palm-GAN: Generating Realistic Palmprint Images Using Total-Variation Regularized GAN


Title	Palm-GAN: Generating Realistic Palmprint Images Using Total-Variation Regularized GAN
Authors	Shervin Minaee, Mehdi Minaei, Amirali Abdolrashidi
Abstract	Generating realistic palmprint (more generally biometric) images has always been an interesting and, at the same time, challenging problem. Classical statistical models fail to generate realistic-looking palmprint images, as they are not powerful enough to capture the complicated texture representation of palmprint images. In this work, we present a deep learning framework based on generative adversarial networks (GAN), which is able to generate realistic palmprint images. To help the model learn more realistic images, we proposed to add a suitable regularization to the loss function, which imposes the line connectivity of generated palmprint images. This is very desirable for palmprints, as the principal lines in palm are usually connected. We apply this framework to a popular palmprint databases, and generate images which look very realistic, and similar to the samples in this database. Through experimental results, we show that the generated palmprint images look very realistic, have a good diversity, and are able to capture different parts of the prior distribution. We also report the Frechet Inception distance (FID) of the proposed model, and show that our model is able to achieve really good quantitative performance in terms of FID score.
Tasks
Published	2020-03-21
URL	https://arxiv.org/abs/2003.10834v1
PDF	https://arxiv.org/pdf/2003.10834v1.pdf
PWC	https://paperswithcode.com/paper/palm-gan-generating-realistic-palmprint
Repo
Framework

Comparison of scanned administrative document images


Title	Comparison of scanned administrative document images
Authors	Elena Andreeva, Vladimir V. Arlazarov, Oleg Slavin, Aleksey Mishev
Abstract	In this work the methods of comparison of digitized copies of administrative documents were considered. This problem arises, for example, when comparing two copies of documents signed by two parties in order to find possible modifications made by one party, in the banking sector at the conclusion of contracts in paper form. The proposed method of document image comparison is based on a combination of several ways of image comparison of words that are descriptors of text feature points. Testing was conducted on public Payslip Dataset (French). The results showed the high quality and the reliability of finding differences in two images that are versions of the same document.
Tasks
Published	2020-01-29
URL	https://arxiv.org/abs/2001.10785v1
PDF	https://arxiv.org/pdf/2001.10785v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-scanned-administrative-document
Repo
Framework

Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification


Title	Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification
Authors	Xiaoxiao Li, Joao Saude
Abstract	Real data collected from different applications that have additional topological structures and connection information are amenable to be represented as a weighted graph. Considering the node labeling problem, Graph Neural Networks (GNNs) is a powerful tool, which can mimic experts’ decision on node labeling. GNNs combine node features, connection patterns, and graph structure by using a neural network to embed node information and pass it through edges in the graph. We want to identify the patterns in the input data used by the GNN model to make a decision and examine if the model works as we desire. However, due to the complex data representation and non-linear transformations, explaining decisions made by GNNs is challenging. In this work, we propose new graph features’ explanation methods to identify the informative components and important node features. Besides, we propose a pipeline to identify the key factors used for node classification. We use four datasets (two synthetic and two real) to validate our methods. Our results demonstrate that our explanation approach can mimic data patterns used for node classification by human interpretation and disentangle different features in the graphs. Furthermore, our explanation methods can be used for understanding data, debugging GNN models, and examine model decisions.
Tasks	Node Classification
Published	2020-02-02
URL	https://arxiv.org/abs/2002.00514v1
PDF	https://arxiv.org/pdf/2002.00514v1.pdf
PWC	https://paperswithcode.com/paper/explain-graph-neural-networks-to-understand
Repo
Framework

Node Masking: Making Graph Neural Networks Generalize and Scale Better


Title	Node Masking: Making Graph Neural Networks Generalize and Scale Better
Authors	Pushkar Mishra, Aleksandra Piktus, Gerard Goossen, Fabrizio Silvestri
Abstract	Graph Neural Networks (GNNs) have received a lot of interest in the recent times. From the early spectral architectures that could only operate on undirected graphs per a transductive learning paradigm to the current state of the art spatial ones that can apply inductively to arbitrary graphs, GNNs have seen significant contributions from the research community. In this paper, we discuss some theoretical tools to better visualize the operations performed by state of the art spatial GNNs. We analyze the inner workings of these architectures and introduce a simple concept, node masking, that allows them to generalize and scale better. To empirically validate the theory, we perform several experiments on three widely-used benchmark datasets for node classification in both transductive and inductive settings.
Tasks	Node Classification
Published	2020-01-17
URL	https://arxiv.org/abs/2001.07524v2
PDF	https://arxiv.org/pdf/2001.07524v2.pdf
PWC	https://paperswithcode.com/paper/node-masking-making-graph-neural-networks
Repo
Framework

HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection


Title	HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
Authors	Maosheng Ye, Shuangjie Xu, Tongyi Cao
Abstract	We present Hybrid Voxel Network (HVNet), a novel one-stage unified network for point cloud based 3D object detection for autonomous driving. Recent studies show that 2D voxelization with per voxel PointNet style feature extractor leads to accurate and efficient detector for large 3D scenes. Since the size of the feature map determines the computation and memory cost, the size of the voxel becomes a parameter that is hard to balance. A smaller voxel size gives a better performance, especially for small objects, but a longer inference time. A larger voxel can cover the same area with a smaller feature map, but fails to capture intricate features and accurate location for smaller objects. We present a Hybrid Voxel network that solves this problem by fusing voxel feature encoder (VFE) of different scales at point-wise level and project into multiple pseudo-image feature maps. We further propose an attentive voxel feature encoding that outperforms plain VFE and a feature fusion pyramid network to aggregate multi-scale information at feature map level. Experiments on the KITTI benchmark show that a single HVNet achieves the best mAP among all existing methods with a real time inference speed of 31Hz.
Tasks	3D Object Detection, Autonomous Driving, Object Detection
Published	2020-02-29
URL	https://arxiv.org/abs/2003.00186v2
PDF	https://arxiv.org/pdf/2003.00186v2.pdf
PWC	https://paperswithcode.com/paper/hvnet-hybrid-voxel-network-for-lidar-based-3d
Repo
Framework

Document Network Projection in Pretrained Word Embedding Space


Title	Document Network Projection in Pretrained Word Embedding Space
Authors	Antoine Gourru, Adrien Guille, Julien Velcin, Julien Jacques
Abstract	We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents (e.g. citation network) into a pretrained word embedding space. In addition to the textual content, we leverage a matrix of pairwise similarities providing complementary information (e.g., the network proximity of two documents in a citation graph). We first build a simple word vector average for each document, and we use the similarities to alter this average representation. The document representations can help to solve many information retrieval tasks, such as recommendation, classification and clustering. We demonstrate that our approach outperforms or matches existing document network embedding methods on node classification and link prediction tasks. Furthermore, we show that it helps identifying relevant keywords to describe document classes.
Tasks	Information Retrieval, Link Prediction, Network Embedding, Node Classification
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05727v1
PDF	https://arxiv.org/pdf/2001.05727v1.pdf
PWC	https://paperswithcode.com/paper/document-network-projection-in-pretrained
Repo
Framework

Graph-FCN for image semantic segmentation


Title	Graph-FCN for image semantic segmentation
Authors	Yi Lu, Yaran Chen, Dongbin Zhao, Jianxin Chen
Abstract	Semantic segmentation with deep learning has achieved great progress in classifying the pixels in the image. However, the local location information is usually ignored in the high-level feature extraction by the deep learning, which is important for image semantic segmentation. To avoid this problem, we propose a graph model initialized by a fully convolutional network (FCN) named Graph-FCN for image semantic segmentation. Firstly, the image grid data is extended to graph structure data by a convolutional network, which transforms the semantic segmentation problem into a graph node classification problem. Then we apply graph convolutional network to solve this graph node classification problem. As far as we know, it is the first time that we apply the graph convolutional network in image semantic segmentation. Our method achieves competitive performance in mean intersection over union (mIOU) on the VOC dataset(about 1.34% improvement), compared to the original FCN model.
Tasks	Node Classification, Semantic Segmentation
Published	2020-01-02
URL	https://arxiv.org/abs/2001.00335v1
PDF	https://arxiv.org/pdf/2001.00335v1.pdf
PWC	https://paperswithcode.com/paper/graph-fcn-for-image-semantic-segmentation
Repo
Framework

NoiseRank: Unsupervised Label Noise Reduction with Dependence Models


Title	NoiseRank: Unsupervised Label Noise Reduction with Dependence Models
Authors	Karishma Sharma, Pinar Donmez, Enming Luo, Yan Liu, I. Zeki Yalniz
Abstract	Label noise is increasingly prevalent in datasets acquired from noisy channels. Existing approaches that detect and remove label noise generally rely on some form of supervision, which is not scalable and error-prone. In this paper, we propose NoiseRank, for unsupervised label noise reduction using Markov Random Fields (MRF). We construct a dependence model to estimate the posterior probability of an instance being incorrectly labeled given the dataset, and rank instances based on their estimated probabilities. Our method 1) Does not require supervision from ground-truth labels, or priors on label or noise distribution. 2) It is interpretable by design, enabling transparency in label noise removal. 3) It is agnostic to classifier architecture/optimization framework and content modality. These advantages enable wide applicability in real noise settings, unlike prior works constrained by one or more conditions. NoiseRank improves state-of-the-art classification on Food101-N (~20% noise), and is effective on high noise Clothing-1M (~40% noise).
Tasks	Image Classification
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06729v1
PDF	https://arxiv.org/pdf/2003.06729v1.pdf
PWC	https://paperswithcode.com/paper/noiserank-unsupervised-label-noise-reduction
Repo
Framework

Prediction of MRI Hardware Failures based on Image Features using Time Series Classification


Title	Prediction of MRI Hardware Failures based on Image Features using Time Series Classification
Authors	Nadine Kuhnert, Lea Pflüger, Andreas Maier
Abstract	Already before systems malfunction one has to know if hardware components will fail in near future in order to counteract in time. Thus, unplanned downtime is ought to be avoided. In medical imaging, maximizing the system’s uptime is crucial for patients’ health and healthcare provider’s daily business. We aim to predict failures of Head/Neck coils used in Magnetic Resonance Imaging (MRI) by training a statistical model on sequential data collected over time. As image features depend on the coil’s condition, their deviations from the normal range already hint to future failure. Thus, we used image features and their variation over time to predict coil damage. After comparison of different time series classification methods we found Long Short Term Memorys (LSTMs) to achieve the highest F-score of 86.43% and to tell with 98.33% accuracy if hardware should be replaced.
Tasks	Time Series, Time Series Classification
Published	2020-01-05
URL	https://arxiv.org/abs/2001.02127v1
PDF	https://arxiv.org/pdf/2001.02127v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-mri-hardware-failures-based-on-1
Repo
Framework

Improper Learning for Non-Stochastic Control


Title	Improper Learning for Non-Stochastic Control
Authors	Max Simchowitz, Karan Singh, Elad Hazan
Abstract	We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed states, known as non-stochastic control. We introduce a controller parametrization based on the denoised observations, and prove that applying online gradient descent to this parametrization yields a new controller which attains sublinear regret vs. a large class of closed-loop policies. In the fully-adversarial setting, our controller attains an optimal regret bound of $\sqrt{T}$-when the system is known, and, when combined with an initial stage of least-squares estimation, $T^{2/3}$ when the system is unknown; both yield the first sublinear regret for the partially observed setting. Our bounds are the first in the non-stochastic control setting that compete with \emph{all} stabilizing linear dynamical controllers, not just state feedback. Moreover, in the presence of semi-adversarial noise containing both stochastic and adversarial components, our controller attains the optimal regret bounds of $\mathrm{poly}(\log T)$ when the system is known, and $\sqrt{T}$ when unknown. To our knowledge, this gives the first end-to-end $\sqrt{T}$ regret for online Linear Quadratic Gaussian controller, and applies in a more general setting with adversarial losses and semi-adversarial noise.
Tasks
Published	2020-01-25
URL	https://arxiv.org/abs/2001.09254v2
PDF	https://arxiv.org/pdf/2001.09254v2.pdf
PWC	https://paperswithcode.com/paper/improper-learning-for-non-stochastic-control
Repo
Framework