January 29, 2020

3312 words 16 mins read

Paper Group ANR 511

Spectral Graph Matching and Regularized Quadratic Relaxations II: Erdős-Rényi Graphs and Universality. Multiple kernel learning for integrative consensus clustering of ‘omic datasets. Desaturating EUV observations of solar flaring storms. Deep Fuzzy Systems. Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learn …

Spectral Graph Matching and Regularized Quadratic Relaxations II: Erdős-Rényi Graphs and Universality


Title	Spectral Graph Matching and Regularized Quadratic Relaxations II: Erdős-Rényi Graphs and Universality
Authors	Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu
Abstract	We analyze a new spectral graph matching algorithm, GRAph Matching by Pairwise eigen-Alignments (GRAMPA), for recovering the latent vertex correspondence between two unlabeled, edge-correlated weighted graphs. Extending the exact recovery guarantees established in the companion paper for Gaussian weights, in this work, we prove the universality of these guarantees for a general correlated Wigner model. In particular, for two Erd\H{o}s-R'enyi graphs with edge correlation coefficient $1-\sigma^2$ and average degree at least $\operatorname{polylog}(n)$, we show that GRAMPA exactly recovers the latent vertex correspondence with high probability when $\sigma \lesssim 1/\operatorname{polylog}(n)$. Moreover, we establish a similar guarantee for a variant of GRAMPA, corresponding to a tighter quadratic programming relaxation of the quadratic assignment problem. Our analysis exploits a resolvent representation of the GRAMPA similarity matrix and local laws for the resolvents of sparse Wigner matrices.
Tasks	Graph Matching
Published	2019-07-20
URL	https://arxiv.org/abs/1907.08883v1
PDF	https://arxiv.org/pdf/1907.08883v1.pdf
PWC	https://paperswithcode.com/paper/spectral-graph-matching-and-regularized
Repo
Framework

Multiple kernel learning for integrative consensus clustering of ‘omic datasets


Title	Multiple kernel learning for integrative consensus clustering of ‘omic datasets
Authors	Alessandra Cabassi, Paul D. W. Kirk
Abstract	Diverse applications - particularly in tumour subtyping - have demonstrated the importance of integrative clustering techniques for combining information from multiple data sources. Cluster-Of-Clusters Analysis (COCA) is one such approach that has been widely applied in the context of tumour subtyping. However, the properties of COCA have never been systematically explored, and its robustness to the inclusion of noisy datasets, or datasets that define conflicting clustering structures, is unclear. We rigorously benchmark COCA, and present Kernel Learning Integrative Clustering (KLIC) as an alternative strategy. KLIC frames the challenge of combining clustering structures as a multiple kernel learning problem, in which different datasets each provide a weighted contribution to the final clustering. This allows the contribution of noisy datasets to be down-weighted relative to more informative datasets. We show through simulation studies that KLIC is more robust than COCA in a variety of situations. We also compare the output of KLIC and COCA in real data applications to cancer subtyping and transcriptional module discovery. R code to run KLIC and COCA can be found at https://github.com/acabassi/klic.
Tasks
Published	2019-04-15
URL	https://arxiv.org/abs/1904.07701v2
PDF	https://arxiv.org/pdf/1904.07701v2.pdf
PWC	https://paperswithcode.com/paper/multiple-kernel-learning-for-integrative
Repo
Framework

Desaturating EUV observations of solar flaring storms


Title	Desaturating EUV observations of solar flaring storms
Authors	Sabrina Guastavino, Michele Piana, Anna Maria Massone, Richard Schwartz, Federico Benvenuto
Abstract	Image saturation has been an issue for several instruments in solar astronomy, mainly at EUV wavelengths. However, with the launch of the Atmospheric Imaging Assembly (AIA) as part of the payload of the Solar Dynamic Observatory (SDO) image saturation has become a big data issue, involving around 10^$ frames of the impressive dataset this beautiful telescope has been providing every year since February 2010. This paper introduces a novel desaturation method, which is able to recover the signal in the saturated region of any AIA image by exploiting no other information but the one contained in the image itself. This peculiar methodological property, jointly with the unprecedented statistical reliability of the desaturated images, could make this algorithm the perfect tool for the realization of a reconstruction pipeline for AIA data, able to work properly even in the case of long-lasting, very energetic flaring events.
Tasks
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04211v1
PDF	http://arxiv.org/pdf/1904.04211v1.pdf
PWC	https://paperswithcode.com/paper/desaturating-euv-observations-of-solar
Repo
Framework

Deep Fuzzy Systems


Title	Deep Fuzzy Systems
Authors	Khaled Ahmed Nagaty
Abstract	An investigation of deep fuzzy systems is presented in this paper. A deep fuzzy system is represented by recursive fuzzy systems from an input terminal to output terminal. Recursive fuzzy systems are sequences of fuzzy grade memberships obtained using fuzzy transmition functions and recursive calls to fuzzy systems. A recursive fuzzy system which calls a fuzzy system n times includes fuzzy chains to evaluate the final grade membership of this recursive system. A connection matrix which includes recursive calls are used to represent recursive fuzzy systems.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1906.08222v1
PDF	https://arxiv.org/pdf/1906.08222v1.pdf
PWC	https://paperswithcode.com/paper/deep-fuzzy-systems
Repo
Framework

Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learning


Title	Active 6D Multi-Object Pose Estimation in Cluttered Scenarios with Deep Reinforcement Learning
Authors	Juil Sock, Guillermo Garcia-Hernando, Tae-Kyun Kim
Abstract	In this work, we explore how a strategic selection of camera movements can facilitate the task of 6D multi-object pose estimation in cluttered scenarios while respecting real-world constraints important in robotics and augmented reality applications, such as time and distance traveled. In the proposed framework, a set of multiple object hypotheses is given to an agent, which is inferred by an object pose estimator and subsequently spatio-temporally selected by a fusion function that makes use of a verification score that circumvents the need of ground-truth annotations. The agent reasons about these hypotheses, directing its attention to the object which it is most uncertain about, moving the camera towards such an object. Unlike previous works that propose short-sighted policies, our agent is trained in simulated scenarios using reinforcement learning, attempting to learn the camera moves that produce the most accurate object poses hypotheses for a given temporal and spatial budget, without the need of viewpoints rendering during inference. Our experiments show that the proposed approach successfully estimates the 6D object pose of a stack of objects in both challenging cluttered synthetic and real scenarios, showing superior performance compared to strong baselines.
Tasks	Pose Estimation
Published	2019-10-19
URL	https://arxiv.org/abs/1910.08811v1
PDF	https://arxiv.org/pdf/1910.08811v1.pdf
PWC	https://paperswithcode.com/paper/active-6d-multi-object-pose-estimation-in
Repo
Framework

How big can style be? Addressing high dimensionality for recommending with style


Title	How big can style be? Addressing high dimensionality for recommending with style
Authors	Diogo Goncalves, Liweu Liu, Ana Magalhães
Abstract	Using embeddings as representations of products is quite commonplace in recommender systems, either by extracting the semantic embeddings of text descriptions, user sessions, collaborative relationships, or product images. In this paper, we present an approach to extract style embeddings for using in fashion recommender systems, with a special focus on style information such as textures, prints, material, etc. The main issue of using such a type of embeddings is its high dimensionality. So, we propose feature reduction solutions alongside the investigation of its influence in the overall task of recommending products of the same style based on their main image. The feature reduction we propose allows for reducing the embedding vector from 600k features to 512, leading to a memory reduction of 99.91% without critically compromising the quality of the recommendations.
Tasks	Recommendation Systems
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10642v1
PDF	https://arxiv.org/pdf/1908.10642v1.pdf
PWC	https://paperswithcode.com/paper/how-big-can-style-be-addressing-high
Repo
Framework

A Biologically Plausible Benchmark for Contextual Bandit Algorithms in Precision Oncology Using in vitro Data


Title	A Biologically Plausible Benchmark for Contextual Bandit Algorithms in Precision Oncology Using in vitro Data
Authors	Niklas T. Rindtorff, MingYu Lu, Nisarg A. Patel, Huahua Zheng, Alexander D’Amour
Abstract	Precision oncology, the genetic sequencing of tumors to identify druggable targets, has emerged as the standard of care in the treatment of many cancers. Nonetheless, due to the pace of therapy development and variability in patient information, designing effective protocols for individual treatment assignment in a sample-efficient way remains a major challenge. One promising approach to this problem is to frame precision oncology treatment as a contextual bandit problem and to apply sequential decision-making algorithms designed to minimize regret in this setting. However, a clear prerequisite for considering this methodology in high-stakes clinical decisions is careful benchmarking to understand realistic costs and benefits. Here, we propose a benchmark dataset to evaluate contextual bandit algorithms based on real in vitro drug response of approximately 900 cancer cell lines. Specifically, we curated a dataset of complete treatment responses for a subset of 7 treatments from prior in vitro studies. This allows us to compute the regret of proposed decision policies using biologically plausible counterfactuals. We ran a suite of Bayesian bandit algorithms on our benchmark, and found that the methods accumulate less regret over a sequence of treatment assignment tasks than a rule-based baseline derived from current clinical practice. This effect was more pronounced when genomic information was included as context. We expect this work to be a starting point for evaluation of both the unique structural requirements and ethical implications for real-world testing of bandit based clinical decision support.
Tasks	Decision Making
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04389v1
PDF	https://arxiv.org/pdf/1911.04389v1.pdf
PWC	https://paperswithcode.com/paper/a-biologically-plausible-benchmark-for
Repo
Framework

Quantifying Layerwise Information Discarding of Neural Networks


Title	Quantifying Layerwise Information Discarding of Neural Networks
Authors	Haotian Ma, Yinqing Zhang, Fan Zhou, Quanshi Zhang
Abstract	This paper presents a method to explain how input information is discarded through intermediate layers of a neural network during the forward propagation, in order to quantify and diagnose knowledge representations of pre-trained deep neural networks. We define two types of entropy-based metrics, i.e., the strict information discarding and the reconstruction uncertainty, which measure input information of a specific layer from two perspectives. We develop a method to enable efficient computation of such entropy-based metrics. Our method can be broadly applied to various neural networks and enable comprehensive comparisons between different layers of different networks. Preliminary experiments have shown the effectiveness of our metrics in analyzing benchmark networks and explaining existing deep-learning techniques.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04109v1
PDF	https://arxiv.org/pdf/1906.04109v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-layerwise-information-discarding
Repo
Framework

Reinforcement with Fading Memories


Title	Reinforcement with Fading Memories
Authors	Kuang Xu, Se-Young Yun
Abstract	We study the effect of imperfect memory on decision making in the context of a stochastic sequential action-reward problem. An agent chooses a sequence of actions which generate discrete rewards at different rates. She is allowed to make new choices at rate $\beta$, while past rewards disappear from her memory at rate $\mu$. We focus on a family of decision rules where the agent makes a new choice by randomly selecting an action with a probability approximately proportional to the amount of past rewards associated with each action in her memory. We provide closed-form formulae for the agent’s steady-state choice distribution in the regime where the memory span is large ($\mu \to 0$), and show that the agent’s success critically depends on how quickly she updates her choices relative to the speed of memory decay. If $\beta \gg \mu$, the agent almost always chooses the best action, i.e., the one with the highest reward rate. Conversely, if $\beta \ll \mu$, the agent chooses an action with a probability roughly proportional to its reward rate.
Tasks	Decision Making
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12227v2
PDF	https://arxiv.org/pdf/1907.12227v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-with-fading-memories
Repo
Framework

Unsupervised Automated Event Detection using an Iterative Clustering based Segmentation Approach


Title	Unsupervised Automated Event Detection using an Iterative Clustering based Segmentation Approach
Authors	Deepak K. Gupta, Rohit K. Shrivastava, Suhas Phadke, Jeroen Goudswaard
Abstract	A class of vision problems, less commonly studied, consists of detecting objects in imagery obtained from physics-based experiments. These objects can span in 4D (x, y, z, t) and are visible as disturbances (caused due to physical phenomena) in the image with background distribution being approximately uniform. Such objects, occasionally referred to as `events’, can be considered as high energy blobs in the image. Unlike the images analyzed in conventional vision problems, very limited features are associated with such events, and their shape, size and count can vary significantly. This poses a challenge on the use of pre-trained models obtained from supervised approaches. In this paper, we propose an unsupervised approach involving iterative clustering based segmentation (ICS) which can detect target objects (events) in real-time. In this approach, a test image is analyzed over several cycles, and one event is identified per cycle. Each cycle consists of the following steps: (1) image segmentation using a modified k-means clustering method, (2) elimination of empty (with no events) segments based on statistical analysis of each segment, (3) merging segments that overlap (correspond to same event), and (4) selecting the strongest event. These four steps are repeated until all the events have been identified. The ICS approach consists of a few hyper-parameters that have been chosen based on statistical study performed over a set of test images. The applicability of ICS method is demonstrated on several 2D and 3D test examples. \|
Tasks	Semantic Segmentation
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07222v1
PDF	http://arxiv.org/pdf/1901.07222v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-automated-event-detection-using
Repo
Framework

A long short-term memory stochastic volatility model


Title	A long short-term memory stochastic volatility model
Authors	Nghia Nguyen, Minh-Ngoc Tran, David Gunawan, R. Kohn
Abstract	Stochastic Volatility (SV) models are widely used in the financial sector while Long Short-Term Memory (LSTM) models are successfully used in many large-scale industrial applications of Deep Learning. Our article combines these two methods in a non-trivial way and proposes a model, which we call the LSTM-SV model, to capture the dynamics of stochastic volatility. The proposed model overcomes the short-term memory problem in conventional SV models, is able to capture non-linear dependence in the latent volatility process, and often has a better out-of-sample forecast performance than SV models. These properties are illustrated through simulation study and applications to three financial time series datasets: The US stock market weekly index SP500, the Australian stock weekly index ASX200 and the Australian-US dollar daily exchange rates. Based on our analysis, we argue that there are significant differences in the underlying dynamics between the volatility process of the SP500 and ASX200 datasets and that of the exchange rate dataset. For the stock index data, there is strong evidence of long-term memory and non-linear dependence in the volatility process, while this is not the case for the exchange rates. An user-friendly software package together with the examples reported in the paper are available at https://github.com/vbayeslab.
Tasks	Time Series
Published	2019-06-07
URL	https://arxiv.org/abs/1906.02884v2
PDF	https://arxiv.org/pdf/1906.02884v2.pdf
PWC	https://paperswithcode.com/paper/a-long-short-term-memory-stochastic
Repo
Framework

Few-Shot Deep Adversarial Learning for Video-based Person Re-identification


Title	Few-Shot Deep Adversarial Learning for Video-based Person Re-identification
Authors	Lin Wu, Yang Wang, Hongzhi Yin, Meng Wang, Ling Shao
Abstract	Video-based person re-identification (re-ID) refers to matching people across camera views from arbitrary unaligned video footages. Existing methods rely on supervision signals to optimise a projected space under which the distances between inter/intra-videos are maximised/minimised. However, this demands exhaustively labelling people across camera views, rendering them unable to be scaled in large networked cameras. Also, it is noticed that learning effective video representations with view invariance is not explicitly addressed for which features exhibit different distributions otherwise. Thus, matching videos for person re-ID demands flexible models to capture the dynamics in time-series observations and learn view-invariant representations with access to limited labeled training samples. In this paper, we propose a novel few-shot deep learning approach to video-based person re-ID, to learn comparable representations that are discriminative and view-invariant. The proposed method is developed on the variational recurrent neural networks (VRNNs) and trained adversarially to produce latent variables with temporal dependencies that are highly discriminative yet view-invariant in matching persons. Through extensive experiments conducted on three benchmark datasets, we empirically show the capability of our method in creating view-invariant temporal features and state-of-the-art performance achieved by our method.
Tasks	Person Re-Identification, Time Series, Video-Based Person Re-Identification
Published	2019-03-29
URL	https://arxiv.org/abs/1903.12395v3
PDF	https://arxiv.org/pdf/1903.12395v3.pdf
PWC	https://paperswithcode.com/paper/few-shot-deep-adversarial-learning-for-video
Repo
Framework

Minimal Variance Sampling in Stochastic Gradient Boosting


Title	Minimal Variance Sampling in Stochastic Gradient Boosting
Authors	Bulat Ibragimov, Gleb Gusev
Abstract	Stochastic Gradient Boosting (SGB) is a widely used approach to regularization of boosting models based on decision trees. It was shown that, in many cases, random sampling at each iteration can lead to better generalization performance of the model and can also decrease the learning time. Different sampling approaches were proposed, where probabilities are not uniform, and it is not currently clear which approach is the most effective. In this paper, we formulate the problem of randomization in SGB in terms of optimization of sampling probabilities to maximize the estimation accuracy of split scoring used to train decision trees. This optimization problem has a closed-form nearly optimal solution, and it leads to a new sampling technique, which we call Minimal Variance Sampling (MVS). The method both decreases the number of examples needed for each iteration of boosting and increases the quality of the model significantly as compared to the state-of-the art sampling methods. The superiority of the algorithm was confirmed by introducing MVS as a new default option for subsampling in CatBoost, a gradient boosting library achieving state-of-the-art quality on various machine learning tasks.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13204v1
PDF	https://arxiv.org/pdf/1910.13204v1.pdf
PWC	https://paperswithcode.com/paper/191013204
Repo
Framework

AV Speech Enhancement Challenge using a Real Noisy Corpus


Title	AV Speech Enhancement Challenge using a Real Noisy Corpus
Authors	Mandar Gogate, Ahsan Adeel, Kia Dashtipour, Peter Derleth, Amir Hussain
Abstract	This paper presents, a first of its kind, audio-visual (AV) speech enhacement challenge in real-noisy settings. A detailed description of the AV challenge, a novel real noisy AV corpus (ASPIRE), benchmark speech enhancement task, and baseline performance results are outlined. The latter are based on training a deep neural architecture on a synthetic mixture of Grid corpus and ChiME3 noises (consisting of bus, pedestrian, cafe, and street noises) and testing on the ASPIRE corpus. Subjective evaluations of five different speech enhancement algorithms (including SEAGN, spectrum subtraction (SS) , log-minimum mean-square error (LMMSE), audio-only CochleaNet, and AV CochleaNet) are presented as baseline results. The aim of the multi-modal challenge is to provide a timely opportunity for comprehensive evaluation of novel AV speech enhancement algorithms, using our new benchmark, real-noisy AV corpus and specified performance metrics. This will promote AV speech processing research globally, stimulate new ground-breaking multi-modal approaches, and attract interest from companies, academics and researchers working in AV speech technologies and applications. We encourage participants (through a challenge website sign-up) from both the speech and hearing research communities, to benefit from their complementary approaches to AV speech in noise processing.
Tasks	Speech Enhancement
Published	2019-09-30
URL	https://arxiv.org/abs/1910.00424v1
PDF	https://arxiv.org/pdf/1910.00424v1.pdf
PWC	https://paperswithcode.com/paper/av-speech-enhancement-challenge-using-a-real
Repo
Framework

Learning Multiparametric Biomarkers for Assessing MR-Guided Focused Ultrasound Treatments Using Volume-Conserving Registration


Title	Learning Multiparametric Biomarkers for Assessing MR-Guided Focused Ultrasound Treatments Using Volume-Conserving Registration
Authors	Blake Zimmerman, Sara Johnson, Henrik Odéen, Jill Shea, Markus Foote, Nicole Winkler, Sarang Joshi, Allison Payne
Abstract	Noninvasive MR-guided focused ultrasound (MRgFUS) treatments are promising alternatives to the surgical removal of malignant tumors. A significant challenge is assessing the treated tissue immediately after MRgFUS procedures. Although current clinical assessment uses the immediate nonperfused volume (NPV) biomarker derived from contrast enhanced imaging, the use of contrast agent prevents continuing MRgFUS treatment if margins are not adequate. In addition, the NPV has been shown to provide variable accuracy for the true treatment outcome as evaluated by follow-up biomarkers. This work presents a novel, noncontrast, learned multiparametric MR biomarker that is conducive for intratreatment assessment. MRgFUS ablations were performed in a rabbit VX2 tumor model. Multiparametric MRI was obtained both during and immediately after the MRgFUS ablation, as well as during follow-up imaging. Segmentation of the NPV obtained during follow-up imaging was used to train a neural network on noncontrast multiparametric MR images. The NPV follow-up segmentation was registered to treatment-day images using a novel volume-conserving registration algorithm, allowing a voxel-wise correlation between imaging sessions. Contrasted with state-of-the-art registration algorithms that change the average volume by 16.8%, the presented volume-conserving registration algorithm changes the average volume by only 0.28%. After registration, the learned multiparametric MR biomarker predicted the follow-up NPV with an average DICE coefficient of 0.71, outperforming the DICE coefficient of 0.53 from the current standard of NPV obtained immediately after the ablation treatment. Noncontrast multiparametric MR imaging can provide a more accurate prediction of treated tissue immediately after treatment. Noncontrast assessment of MRgFUS procedures will potentially lead to more efficacious MRgFUS ablation treatments.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10769v1
PDF	https://arxiv.org/pdf/1910.10769v1.pdf
PWC	https://paperswithcode.com/paper/learning-multiparametric-biomarkers-for
Repo
Framework