October 16, 2019

3306 words 16 mins read

Paper Group ANR 1039

Three dimensional Deep Learning approach for remote sensing image classification. Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data. Block-wise Partitioning for Extreme Multi-label Classification. What Stands-in for a Missing Tool? A Prototypical Grounded Knowledge-based Approach to Tool Substitu …

Three dimensional Deep Learning approach for remote sensing image classification


Title	Three dimensional Deep Learning approach for remote sensing image classification
Authors	Amina Ben Hamida, A Benoit, Patrick Lambert, Chokri Ben Amar
Abstract	Recently, a variety of approaches has been enriching the field of Remote Sensing (RS) image processing and analysis. Unfortunately, existing methods remain limited faced to the rich spatio-spectral content of today’s large datasets. It would seem intriguing to resort to Deep Learning (DL) based approaches at this stage with regards to their ability to offer accurate semantic interpretation of the data. However, the specificity introduced by the coexistence of spectral and spatial content in the RS datasets widens the scope of the challenges presented to adapt DL methods to these contexts. Therefore, the aim of this paper is firstly to explore the performance of DL architectures for the RS hyperspectral dataset classification and secondly to introduce a new three-dimensional DL approach that enables a joint spectral and spatial information process. A set of three-dimensional schemes is proposed and evaluated. Experimental results based on well knownhyperspectral datasets demonstrate that the proposed method is able to achieve a better classification rate than state of the art methods with lower computational costs.
Tasks	Image Classification, Remote Sensing Image Classification
Published	2018-06-15
URL	http://arxiv.org/abs/1806.05824v1
PDF	http://arxiv.org/pdf/1806.05824v1.pdf
PWC	https://paperswithcode.com/paper/three-dimensional-deep-learning-approach-for
Repo
Framework

Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data


Title	Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data
Authors	Ehsan Hajiramezanali, Siamak Zamani Dadaneh, Alireza Karbalayghareh, Mingyuan Zhou, Xiaoning Qian
Abstract	Precision medicine aims for personalized prognosis and therapeutics by utilizing recent genome-scale high-throughput profiling techniques, including next-generation sequencing (NGS). However, translating NGS data faces several challenges. First, NGS count data are often overdispersed, requiring appropriate modeling. Second, compared to the number of involved molecules and system complexity, the number of available samples for studying complex disease, such as cancer, is often limited, especially considering disease heterogeneity. The key question is whether we may integrate available data from all different sources or domains to achieve reproducible disease prognosis based on NGS count data. In this paper, we develop a Bayesian Multi-Domain Learning (BMDL) model that derives domain-dependent latent representations of overdispersed count data based on hierarchical negative binomial factorization for accurate cancer subtyping even if the number of samples for a specific cancer type is small. Experimental results from both our simulated and NGS datasets from The Cancer Genome Atlas (TCGA) demonstrate the promising potential of BMDL for effective multi-domain learning without “negative transfer” effects often seen in existing multi-task learning and transfer learning methods.
Tasks	Multi-Task Learning, Transfer Learning
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09433v1
PDF	http://arxiv.org/pdf/1810.09433v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-multi-domain-learning-for-cancer
Repo
Framework

Block-wise Partitioning for Extreme Multi-label Classification


Title	Block-wise Partitioning for Extreme Multi-label Classification
Authors	Yuefeng Liang, Cho-Jui Hsieh, Thomas C. M. Lee
Abstract	Extreme multi-label classification aims to learn a classifier that annotates an instance with a relevant subset of labels from an extremely large label set. Many existing solutions embed the label matrix to a low-dimensional linear subspace, or examine the relevance of a test instance to every label via a linear scan. In practice, however, those approaches can be computationally exorbitant. To alleviate this drawback, we propose a Block-wise Partitioning (BP) pretreatment that divides all instances into disjoint clusters, to each of which the most frequently tagged label subset is attached. One multi-label classifier is trained on one pair of instance and label clusters, and the label set of a test instance is predicted by first delivering it to the most appropriate instance cluster. Experiments on benchmark multi-label data sets reveal that BP pretreatment significantly reduces prediction time, and retains almost the same level of prediction accuracy.
Tasks	Extreme Multi-Label Classification, Multi-Label Classification
Published	2018-11-04
URL	http://arxiv.org/abs/1811.01305v1
PDF	http://arxiv.org/pdf/1811.01305v1.pdf
PWC	https://paperswithcode.com/paper/block-wise-partitioning-for-extreme-multi
Repo
Framework

What Stands-in for a Missing Tool? A Prototypical Grounded Knowledge-based Approach to Tool Substitution


Title	What Stands-in for a Missing Tool? A Prototypical Grounded Knowledge-based Approach to Tool Substitution
Authors	Madhura Thosar, Christian A. Mueller, Sebastian Zug
Abstract	When a robot is operating in a dynamic environment, it cannot be assumed that a tool required to solve a given task will always be available. In case of a missing tool, an ideal response would be to find a substitute to complete the task. In this paper, we present a proof of concept of a grounded knowledge-based approach to tool substitution. In order to validate the suitability of a substitute, we conducted experiments involving 22 substitution scenarios. The substitutes computed by the proposed approach were validated on the basis of the experts’ choices for each scenario. Our evaluation showed, in 20 out of 22 scenarios (91%), the approach identified the same substitutes as experts.
Tasks
Published	2018-08-20
URL	http://arxiv.org/abs/1808.06423v3
PDF	http://arxiv.org/pdf/1808.06423v3.pdf
PWC	https://paperswithcode.com/paper/what-stands-in-for-a-missing-tool-a
Repo
Framework

Online Parallel Portfolio Selection with Heterogeneous Island Model


Title	Online Parallel Portfolio Selection with Heterogeneous Island Model
Authors	Štěpán Balcar, Martin Pilát
Abstract	We present an online parallel portfolio selection algorithm based on the island model commonly used for parallelization of evolutionary algorithms. In our case each of the islands runs a different optimization algorithm. The distributed computation is managed by a central planner which periodically changes the running methods during the execution of the algorithm – less successful methods are removed while new instances of more successful methods are added. We compare different types of planners in the heterogeneous island model among themselves and also to the traditional homogeneous model on a wide set of problems. The tests include experiments with different representations of the individuals and different duration of fitness function evaluations. The results show that heterogeneous models are a more general and universal computational tool compared to homogeneous models.
Tasks
Published	2018-06-12
URL	http://arxiv.org/abs/1806.04528v1
PDF	http://arxiv.org/pdf/1806.04528v1.pdf
PWC	https://paperswithcode.com/paper/online-parallel-portfolio-selection-with
Repo
Framework

Context Mover’s Distance & Barycenters: Optimal Transport of Contexts for Building Representations


Title	Context Mover’s Distance & Barycenters: Optimal Transport of Contexts for Building Representations
Authors	Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi
Abstract	We present a framework for building unsupervised representations of entities and their compositions, where each entity is viewed as a probability distribution rather than a vector embedding. In particular, this distribution is supported over the contexts which co-occur with the entity and are embedded in a suitable low-dimensional space. This enables us to consider representation learning from the perspective of Optimal Transport and take advantage of its tools such as Wasserstein distance and barycenters. We elaborate how the method can be applied for obtaining unsupervised representations of text and illustrate the performance (quantitatively as well as qualitatively) on tasks such as measuring sentence similarity, word entailment and similarity, where we empirically observe significant gains (e.g., 4.1% relative improvement over Sent2vec, GenSen). The key benefits of the proposed approach include: (a) capturing uncertainty and polysemy via modeling the entities as distributions, (b) utilizing the underlying geometry of the particular task (with the ground cost), (c) simultaneously providing interpretability with the notion of optimal transport between contexts and (d) easy applicability on top of existing point embedding methods. The code, as well as prebuilt histograms, are available under https://github.com/context-mover/.
Tasks	Representation Learning
Published	2018-08-29
URL	https://arxiv.org/abs/1808.09663v6
PDF	https://arxiv.org/pdf/1808.09663v6.pdf
PWC	https://paperswithcode.com/paper/context-movers-distance-barycenters-optimal
Repo
Framework

Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling


Title	Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling
Authors	Shanshan Wu, Alexandros G. Dimakis, Sujay Sanghavi, Felix X. Yu, Daniel Holtmann-Rice, Dmitry Storcheus, Afshin Rostamizadeh, Sanjiv Kumar
Abstract	Linear encoding of sparse vectors is widely popular, but is commonly data-independent – missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used $\ell_1$ decoder. The convex $\ell_1$ decoder prevents gradient propagation as needed in standard gradient-based training. Our method is based on the insight that unrolling the convex decoder into $T$ projected subgradient steps can address this issue. Our method can be seen as a data-driven way to learn a compressed sensing measurement matrix. We compare the empirical performance of 10 algorithms over 6 sparse datasets (3 synthetic and 3 real). Our experiments show that there is indeed additional structure beyond sparsity in the real datasets; our method is able to discover it and exploit it to create excellent reconstructions with fewer measurements (by a factor of 1.1-3x) compared to the previous state-of-the-art methods. We illustrate an application of our method in learning label embeddings for extreme multi-label classification, and empirically show that our method is able to match or outperform the precision scores of SLEEC, which is one of the state-of-the-art embedding-based approaches.
Tasks	Extreme Multi-Label Classification, Multi-Label Classification, Multi-Label Learning
Published	2018-06-26
URL	https://arxiv.org/abs/1806.10175v4
PDF	https://arxiv.org/pdf/1806.10175v4.pdf
PWC	https://paperswithcode.com/paper/learning-a-compressed-sensing-measurement
Repo
Framework

A Divide-and-Conquer Approach to Compressed Sensing MRI


Title	A Divide-and-Conquer Approach to Compressed Sensing MRI
Authors	Liyan Sun, Zhiwen Fan, Xinghao Ding, Congbo Cai, Yue Huang, John Paisley
Abstract	Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires. In traditional CS-MRI inversion methods, the fact that the energy within the Fourier measurement domain is distributed non-uniformly is often neglected during reconstruction. As a result, more densely sampled low-frequency information tends to dominate penalization schemes for reconstructing MRI at the expense of high-frequency details. In this paper, we propose a new framework for CS-MRI inversion in which we decompose the observed k-space data into “subspaces” via sets of filters in a lossless way, and reconstruct the images in these various spaces individually using off-the-shelf algorithms. We then fuse the results to obtain the final reconstruction. In this way we are able to focus reconstruction on frequency information within the entire k-space more equally, preserving both high and low frequency details. We demonstrate that the proposed framework is competitive with state-of-the-art methods in CS-MRI in terms of quantitative performance, and often improves an algorithm’s results qualitatively compared with it’s direct application to k-space.
Tasks
Published	2018-03-27
URL	http://arxiv.org/abs/1803.09909v1
PDF	http://arxiv.org/pdf/1803.09909v1.pdf
PWC	https://paperswithcode.com/paper/a-divide-and-conquer-approach-to-compressed
Repo
Framework

Optimizing class partitioning in multi-class classification using a descriptive control language


Title	Optimizing class partitioning in multi-class classification using a descriptive control language
Authors	Peter Mills
Abstract	Many of the best statistical classification algorithms are binary classifiers, that is they can only distinguish between one of two classes. The number of possible ways of generalizing binary classification to multi-class increases exponentially with the number of classes. There is some indication that the best method of doing so will depend on the dataset. As such, we are particularly interested in data-driven solution design, whether based on prior considerations or on empirical examination of the data. Here we demonstrate how a recursive control language can be used to describe a multitude of different partitioning strategies in multi-class classification, including those in most common use. We use it both to manually construct new partitioning configurations as well as to examine those that have been automatically designed. Eight different strategies are tested on eight different datasets using both support vector machines (SVM) as well as logistic regression as the base binary classifiers. Numerical tests suggest that a one-size-fits-all solution consisting of one-versus-one is appropriate for most datasets however one dataset benefitted from the techniques applied in this paper. The best solution exploited a property of the dataset to produce an uncertainty coefficient 36% higher (0.016 absolute gain) than one-vs.-one. Adaptive solutions that empirically examined the data also produced gains over one-vs.-one while also being faster.
Tasks	Calibration
Published	2018-09-16
URL	https://arxiv.org/abs/1809.05929v6
PDF	https://arxiv.org/pdf/1809.05929v6.pdf
PWC	https://paperswithcode.com/paper/solving-for-multi-class-a-survey-and
Repo
Framework

Attack Graph Convolutional Networks by Adding Fake Nodes


Title	Attack Graph Convolutional Networks by Adding Fake Nodes
Authors	Xiaoyun Wang, Minyhao Cheng, Joe Eaton, Cho-Jui Hsieh, Felix Wu
Abstract	In this paper, we study the robustness of graph convolutional networks (GCNs). Previous work have shown that GCNs are vulnerable to adversarial perturbation on adjacency or feature matrices of existing nodes; however, such attacks are usually unrealistic in real applications. For instance, in social network applications, the attacker will need to hack into either the client or server to change existing links or features. In this paper, we propose a new type of “fake node attacks” to attack GCNs by adding malicious fake nodes. This is much more realistic than previous attacks; in social network applications, the attacker only needs to register a set of fake accounts and link to existing ones. To conduct fake node attacks, a greedy algorithm is proposed to generate edges of malicious nodes and their corresponding features aiming to minimize the classification accuracy on the target nodes. In addition, we introduce a discriminator to classify malicious nodes from real nodes, and propose a Greedy-GAN attack to simultaneously update the discriminator and the attacker, to make malicious nodes indistinguishable from the real ones. Our non-targeted attack decreases the accuracy of GCN down to 0.03, and our targeted attack reaches a success rate of 78% on a group of 100 nodes, and 90% on average for attacking a single target node.
Tasks
Published	2018-10-25
URL	https://arxiv.org/abs/1810.10751v3
PDF	https://arxiv.org/pdf/1810.10751v3.pdf
PWC	https://paperswithcode.com/paper/attack-graph-convolutional-networks-by-adding
Repo
Framework

DeepCorr: Strong Flow Correlation Attacks on Tor Using Deep Learning


Title	DeepCorr: Strong Flow Correlation Attacks on Tor Using Deep Learning
Authors	Milad Nasr, Alireza Bahramali, Amir Houmansadr
Abstract	Flow correlation is the core technique used in a multitude of deanonymization attacks on Tor. Despite the importance of flow correlation attacks on Tor, existing flow correlation techniques are considered to be ineffective and unreliable in linking Tor flows when applied at a large scale, i.e., they impose high rates of false positive error rates or require impractically long flow observations to be able to make reliable correlations. In this paper, we show that, unfortunately, flow correlation attacks can be conducted on Tor traffic with drastically higher accuracies than before by leveraging emerging learning mechanisms. We particularly design a system, called DeepCorr, that outperforms the state-of-the-art by significant margins in correlating Tor connections. DeepCorr leverages an advanced deep learning architecture to learn a flow correlation function tailored to Tor’s complex network this is in contrast to previous works’ use of generic statistical correlation metrics to correlated Tor flows. We show that with moderate learning, DeepCorr can correlate Tor connections (and therefore break its anonymity) with accuracies significantly higher than existing algorithms, and using substantially shorter lengths of flow observations. For instance, by collecting only about 900 packets of each target Tor flow (roughly 900KB of Tor data), DeepCorr provides a flow correlation accuracy of 96% compared to 4% by the state-of-the-art system of RAPTOR using the same exact setting. We hope that our work demonstrates the escalating threat of flow correlation attacks on Tor given recent advances in learning algorithms, calling for the timely deployment of effective countermeasures by the Tor community.
Tasks
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07285v1
PDF	http://arxiv.org/pdf/1808.07285v1.pdf
PWC	https://paperswithcode.com/paper/deepcorr-strong-flow-correlation-attacks-on
Repo
Framework

Incremental learning abstract discrete planning domains and mappings to continuous perceptions


Title	Incremental learning abstract discrete planning domains and mappings to continuous perceptions
Authors	Luciano Serafini, Paolo Traverso
Abstract	Most of the works on planning and learning, e.g., planning by (model based) reinforcement learning, are based on two main assumptions: (i) the set of states of the planning domain is fixed; (ii) the mapping between the observations from the real word and the states is implicitly assumed or learned offline, and it is not part of the planning domain. Consequently, the focus is on learning the transitions between states. In this paper, we drop such assumptions. We provide a formal framework in which (i) the agent can learn dynamically new states of the planning domain; (ii) the mapping between abstract states and the perception from the real world, represented by continuous variables, is part of the planning domain; (iii) such mapping is learned and updated along the “life” of the agent. We define an algorithm that interleaves planning, acting, and learning, and allows the agent to update the planning domain depending on how much it trusts the model w.r.t. the new experiences learned by executing actions. We define a measure of coherence between the planning domain and the real world as perceived by the agent. We test our approach showing that the agent learns increasingly coherent models, and that the system can scale to deal with models with an order of $10^6$ states.
Tasks
Published	2018-10-16
URL	http://arxiv.org/abs/1810.07096v2
PDF	http://arxiv.org/pdf/1810.07096v2.pdf
PWC	https://paperswithcode.com/paper/incremental-learning-abstract-discrete
Repo
Framework

hyperdoc2vec: Distributed Representations of Hypertext Documents


Title	hyperdoc2vec: Distributed Representations of Hypertext Documents
Authors	Jialong Han, Yan Song, Wayne Xin Zhao, Shuming Shi, Haisong Zhang
Abstract	Hypertext documents, such as web pages and academic papers, are of great importance in delivering information in our daily life. Although being effective on plain documents, conventional text embedding methods suffer from information loss if directly adapted to hyper-documents. In this paper, we propose a general embedding approach for hyper-documents, namely, hyperdoc2vec, along with four criteria characterizing necessary information that hyper-document embedding models should preserve. Systematic comparisons are conducted between hyperdoc2vec and several competitors on two tasks, i.e., paper classification and citation recommendation, in the academic paper domain. Analyses and experiments both validate the superiority of hyperdoc2vec to other models w.r.t. the four criteria.
Tasks	Document Embedding
Published	2018-05-10
URL	http://arxiv.org/abs/1805.03793v1
PDF	http://arxiv.org/pdf/1805.03793v1.pdf
PWC	https://paperswithcode.com/paper/hyperdoc2vec-distributed-representations-of
Repo
Framework

High quality ultrasonic multi-line transmission through deep learning


Title	High quality ultrasonic multi-line transmission through deep learning
Authors	Sanketh Vedula, Ortal Senouf, Grigoriy Zurakhov, Alex M. Bronstein, Michael Zibulevsky, Oleg Michailovich, Dan Adam, Diana Gaitini
Abstract	Frame rate is a crucial consideration in cardiac ultrasound imaging and 3D sonography. Several methods have been proposed in the medical ultrasound literature aiming at accelerating the image acquisition. In this paper, we consider one such method called \textit{multi-line transmission} (MLT), in which several evenly separated focused beams are transmitted simultaneously. While MLT reduces the acquisition time, it comes at the expense of a heavy loss of contrast due to the interactions between the beams (cross-talk artifact). In this paper, we introduce a data-driven method to reduce the artifacts arising in MLT. To this end, we propose to train an end-to-end convolutional neural network consisting of correction layers followed by a constant apodization layer. The network is trained on pairs of raw data obtained through MLT and the corresponding \textit{single-line transmission} (SLT) data. Experimental evaluation demonstrates significant improvement both in the visual image quality and in objective measures such as contrast ratio and contrast-to-noise ratio, while preserving resolution unlike traditional apodization-based methods. We show that the proposed method is able to generalize well across different patients and anatomies on real and phantom data.
Tasks
Published	2018-08-23
URL	http://arxiv.org/abs/1808.07819v1
PDF	http://arxiv.org/pdf/1808.07819v1.pdf
PWC	https://paperswithcode.com/paper/high-quality-ultrasonic-multi-line
Repo
Framework

Learning to score the figure skating sports videos


Title	Learning to score the figure skating sports videos
Authors	Chengming Xu, Yanwei Fu, Bing Zhang, Zitian Chen, Yu-Gang Jiang, Xiangyang Xue
Abstract	This paper targets at learning to score the figure skating sports videos. To address this task, we propose a deep architecture that includes two complementary components, i.e., Self-Attentive LSTM and Multi-scale Convolutional Skip LSTM. These two components can efficiently learn the local and global sequential information in each video. Furthermore, we present a large-scale figure skating sports video dataset – FisV dataset. This dataset includes 500 figure skating videos with the average length of 2 minutes and 50 seconds. Each video is annotated by two scores of nine different referees, i.e., Total Element Score(TES) and Total Program Component Score (PCS). Our proposed model is validated on FisV and MIT-skate datasets. The experimental results show the effectiveness of our models in learning to score the figure skating videos.
Tasks
Published	2018-02-08
URL	http://arxiv.org/abs/1802.02774v3
PDF	http://arxiv.org/pdf/1802.02774v3.pdf
PWC	https://paperswithcode.com/paper/learning-to-score-the-figure-skating-sports
Repo
Framework