April 1, 2020

3456 words 17 mins read

Paper Group ANR 392

Learn to Generate Time Series Conditioned Graphs with Generative Adversarial Nets. From Route Instructions to Landmark Graphs. A hemodynamic decomposition model for detecting cognitive load using functional near-infrared spectroscopy. Autoencoders as Weight Initialization of Deep Classification Networks for Cancer versus Cancer Studies. Acceleratin …

Learn to Generate Time Series Conditioned Graphs with Generative Adversarial Nets


Title	Learn to Generate Time Series Conditioned Graphs with Generative Adversarial Nets
Authors	Shanchao Yang, Jing Liu, Kai Wu, Mingming Li
Abstract	Deep learning based approaches have been utilized to model and generate graphs subjected to different distributions recently. However, they are typically unsupervised learning based and unconditioned generative models or simply conditioned on the graph-level contexts, which are not associated with rich semantic node-level contexts. Differently, in this paper, we are interested in a novel problem named Time Series Conditioned Graph Generation: given an input multivariate time series, we aim to infer a target relation graph modeling the underlying interrelationships between time series with each node corresponding to each time series. For example, we can study the interrelationships between genes in a gene regulatory network of a certain disease conditioned on their gene expression data recorded as time series. To achieve this, we propose a novel Time Series conditioned Graph Generation-Generative Adversarial Networks (TSGG-GAN) to handle challenges of rich node-level context structures conditioning and measuring similarities directly between graphs and time series. Extensive experiments on synthetic and real-word gene regulatory networks datasets demonstrate the effectiveness and generalizability of the proposed TSGG-GAN.
Tasks	Graph Generation, Time Series
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01436v1
PDF	https://arxiv.org/pdf/2003.01436v1.pdf
PWC	https://paperswithcode.com/paper/learn-to-generate-time-series-conditioned
Repo
Framework

From Route Instructions to Landmark Graphs


Title	From Route Instructions to Landmark Graphs
Authors	Christopher M Cervantes
Abstract	Landmarks are central to how people navigate, but most navigation technologies do not incorporate them into their representations. We propose the landmark graph generation task (creating landmark-based spatial representations from natural language) and introduce a fully end-to-end neural approach to generate these graphs. We evaluate our models on the SAIL route instruction dataset, as well as on a small set of real-world delivery instructions that we collected, and we show that our approach yields high quality results on both our task and the related robotic navigation task.
Tasks	Graph Generation
Published	2020-02-05
URL	https://arxiv.org/abs/2002.02012v1
PDF	https://arxiv.org/pdf/2002.02012v1.pdf
PWC	https://paperswithcode.com/paper/from-route-instructions-to-landmark-graphs
Repo
Framework

A hemodynamic decomposition model for detecting cognitive load using functional near-infrared spectroscopy


Title	A hemodynamic decomposition model for detecting cognitive load using functional near-infrared spectroscopy
Authors	Marco A. Pinto-Orellana, Diego C. Nascimento, Peyman Mirtaheri, Rune Jonassen, Anis Yazidi, Hugo L. Hammer
Abstract	In the current paper, we introduce a parametric data-driven model for functional near-infrared spectroscopy that decomposes a signal into a series of independent, rescaled, time-shifted, hemodynamic basis functions. Each decomposed waveform retains relevant biological information about the expected hemodynamic behavior. The model is also presented along with an efficient iterative estimation method to improve the computational speed. Our hemodynamic decomposition model (HDM) extends the canonical model for instances when a) the external stimuli are unknown, or b) when the assumption of a direct relationship between the experimental stimuli and the hemodynamic responses cannot hold. We also argue that the proposed approach can be potentially adopted as a feature transformation method for machine learning purposes. By virtue of applying our devised HDM to a cognitive load classification task on fNIRS signals, we have achieved an accuracy of 86.20%+-2.56% using six channels in the frontal cortex, and 86.34%+-2.81% utilizing only the AFpz channel also located in the frontal area. In comparison, state-of-the-art time-spectral transformations only yield 64.61%+-3.03% and 37.8%+-2.96% under identical experimental settings.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08579v1
PDF	https://arxiv.org/pdf/2001.08579v1.pdf
PWC	https://paperswithcode.com/paper/a-hemodynamic-decomposition-model-for
Repo
Framework

Autoencoders as Weight Initialization of Deep Classification Networks for Cancer versus Cancer Studies


Title	Autoencoders as Weight Initialization of Deep Classification Networks for Cancer versus Cancer Studies
Authors	Mafalda Falcao Ferreira, Rui Camacho, Luis F. Teixeira
Abstract	Cancer is still one of the most devastating diseases of our time. One way of automatically classifying tumor samples is by analyzing its derived molecular information (i.e., its genes expression signatures). In this work, we aim to distinguish three different types of cancer: thyroid, skin, and stomach. For that, we compare the performance of a Denoising Autoencoder (DAE) used as weight initialization of a deep neural network. Although we address a different domain problem in this work, we have adopted the same methodology of Ferreira et al.. In our experiments, we assess two different approaches when training the classification model: (a) fixing the weights, after pre-training the DAE, and (b) allowing fine-tuning of the entire classification network. Additionally, we apply two different strategies for embedding the DAE into the classification network: (1) by only importing the encoding layers, and (2) by inserting the complete autoencoder. Our best result was the combination of unsupervised feature learning through a DAE, followed by its full import into the classification network, and subsequent fine-tuning through supervised training, achieving an F1 score of 98.04% +/- 1.09 when identifying cancerous thyroid samples.
Tasks	Denoising
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05253v1
PDF	https://arxiv.org/pdf/2001.05253v1.pdf
PWC	https://paperswithcode.com/paper/autoencoders-as-weight-initialization-of-deep
Repo
Framework

Accelerating Quantum Approximate Optimization Algorithm using Machine Learning


Title	Accelerating Quantum Approximate Optimization Algorithm using Machine Learning
Authors	Mahabubul Alam, Abdullah Ash-Saki, Swaroop Ghosh
Abstract	We propose a machine learning based approach to accelerate quantum approximate optimization algorithm (QAOA) implementation which is a promising quantum-classical hybrid algorithm to prove the so-called quantum supremacy. In QAOA, a parametric quantum circuit and a classical optimizer iterates in a closed loop to solve hard combinatorial optimization problems. The performance of QAOA improves with increasing number of stages (depth) in the quantum circuit. However, two new parameters are introduced with each added stage for the classical optimizer increasing the number of optimization loop iterations. We note a correlation among parameters of the lower-depth and the higher-depth QAOA implementations and, exploit it by developing a machine learning model to predict the gate parameters close to the optimal values. As a result, the optimization loop converges in a fewer number of iterations. We choose graph MaxCut problem as a prototype to solve using QAOA. We perform a feature extraction routine using 100 different QAOA instances and develop a training data-set with 13,860 optimal parameters. We present our analysis for 4 flavors of regression models and 4 flavors of classical optimizers. Finally, we show that the proposed approach can curtail the number of optimization iterations by on average 44.9% (up to 65.7%) from an analysis performed with 264 flavors of graphs.
Tasks	Combinatorial Optimization
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01089v1
PDF	https://arxiv.org/pdf/2002.01089v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-quantum-approximate-optimization
Repo
Framework

Neural encoding and interpretation for high-level visual cortices based on fMRI using image caption features


Title	Neural encoding and interpretation for high-level visual cortices based on fMRI using image caption features
Authors	Kai Qiao, Chi Zhang, Jian Chen, Linyuan Wang, Li Tong, Bin Yan
Abstract	On basis of functional magnetic resonance imaging (fMRI), researchers are devoted to designing visual encoding models to predict the neuron activity of human in response to presented image stimuli and analyze inner mechanism of human visual cortices. Deep network structure composed of hierarchical processing layers forms deep network models by learning features of data on specific task through big dataset. Deep network models have powerful and hierarchical representation of data, and have brought about breakthroughs for visual encoding, while revealing hierarchical structural similarity with the manner of information processing in human visual cortices. However, previous studies almost used image features of those deep network models pre-trained on classification task to construct visual encoding models. Except for deep network structure, the task or corresponding big dataset is also important for deep network models, but neglected by previous studies. Because image classification is a relatively fundamental task, it is difficult to guide deep network models to master high-level semantic representations of data, which causes into that encoding performance for high-level visual cortices is limited. In this study, we introduced one higher-level vision task: image caption (IC) task and proposed the visual encoding model based on IC features (ICFVEM) to encode voxels of high-level visual cortices. Experiment demonstrated that ICFVEM obtained better encoding performance than previous deep network models pre-trained on classification task. In addition, the interpretation of voxels was realized to explore the detailed characteristics of voxels based on the visualization of semantic words, and comparative analysis implied that high-level visual cortices behaved the correlative representation of image content.
Tasks	Image Classification
Published	2020-03-26
URL	https://arxiv.org/abs/2003.11797v1
PDF	https://arxiv.org/pdf/2003.11797v1.pdf
PWC	https://paperswithcode.com/paper/neural-encoding-and-interpretation-for-high
Repo
Framework

Synergic Adversarial Label Learning with DR and AMD for Retinal Image Grading


Title	Synergic Adversarial Label Learning with DR and AMD for Retinal Image Grading
Authors	Lie Ju, Xin Wang, Xin Zhao, Paul Bonnington, Zongyuan Ge
Abstract	The need for comprehensive and automated screening methods for retinal image classification has long been recognized. Well-qualified doctors annotated images are very expensive and only a limited amount of data is available for various retinal diseases such as age-related macular degeneration (AMD) and diabetic retinopathy (DR). Some studies show that AMD and DR share some common features like hemorrhagic points and exudation but most classification algorithms only train those disease models independently. Inspired by knowledge distillation where additional monitoring signals from various sources is beneficial to train a robust model with much fewer data. We propose a method called synergic adversarial label learning (SALL) which leverages relevant retinal disease labels in both semantic and feature space as additional signals and train the model in a collaborative manner. Our experiments on DR and AMD fundus image classification task demonstrate that the proposed method can significantly improve the accuracy of the model for grading diseases. In addition, we conduct additional experiments to show the effectiveness of SALL from the aspects of reliability and interpretability in the context of medical imaging application.
Tasks	Image Classification
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10607v2
PDF	https://arxiv.org/pdf/2003.10607v2.pdf
PWC	https://paperswithcode.com/paper/synergic-adversarial-label-learning-with-dr
Repo
Framework

Finding Input Characterizations for Output Properties in ReLU Neural Networks


Title	Finding Input Characterizations for Output Properties in ReLU Neural Networks
Authors	Saket Dingliwal, Divyansh Pareek, Jatin Arora
Abstract	Deep Neural Networks (DNNs) have emerged as a powerful mechanism and are being increasingly deployed in real-world safety-critical domains. Despite the widespread success, their complex architecture makes proving any formal guarantees about them difficult. Identifying how logical notions of high-level correctness relate to the complex low-level network architecture is a significant challenge. In this project, we extend the ideas presented in and introduce a way to bridge the gap between the architecture and the high-level specifications. Our key insight is that instead of directly proving the safety properties that are required, we first prove properties that relate closely to the structure of the neural net and use them to reason about the safety properties. We build theoretical foundations for our approach, and empirically evaluate the performance through various experiments, achieving promising results than the existing approach by identifying a larger region of input space that guarantees a certain property on the output.
Tasks
Published	2020-03-09
URL	https://arxiv.org/abs/2003.04273v1
PDF	https://arxiv.org/pdf/2003.04273v1.pdf
PWC	https://paperswithcode.com/paper/finding-input-characterizations-for-output
Repo
Framework

Reinforcement Learning-based Autoscaling of Workflows in the Cloud: A Survey


Title	Reinforcement Learning-based Autoscaling of Workflows in the Cloud: A Survey
Authors	Yisel Garí, David A. Monge, Elina Pacini, Cristian Mateos, Carlos García Garino
Abstract	Reinforcement Learning (RL) has demonstrated a great potential for automatically solving decision making problems in complex uncertain environments. Basically, RL proposes a computational approach that allows learning through interaction in an environment of stochastic behavior, with agents taking actions to maximize some cumulative short-term and long-term rewards. Some of the most impressive results have been shown in Game Theory where agents exhibited super-human performance in games like Go or Starcraft 2, which led to its adoption in many other domains including Cloud Computing. Particularly, workflow autoscaling exploits the Cloud elasticity to optimize the execution of workflows according to a given optimization criteria. This is a decision-making problem in which it is necessary to establish when and how to scale-up/down computational resources; and how to assign them to the upcoming processing workload. Such actions have to be taken considering some optimization criteria in the Cloud, a dynamic and uncertain environment. Motivated by this, many works apply RL to the autoscaling problem in Cloud. In this work we survey exhaustively those proposals from major venues, and uniformly compare them based on a set of proposed taxonomies. We also discuss open problems and provide a prospective of future research in the area.
Tasks	Decision Making, Starcraft
Published	2020-01-27
URL	https://arxiv.org/abs/2001.09957v1
PDF	https://arxiv.org/pdf/2001.09957v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-based-autoscaling-of
Repo
Framework

A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs


Title	A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
Authors	Stefania Fresca, Luca Dede, Andrea Manzoni
Abstract	Traditional reduced order modeling techniques such as the reduced basis (RB) method (relying, e.g., on proper orthogonal decomposition (POD)) suffer from severe limitations when dealing with nonlinear time-dependent parametrized PDEs, because of the fundamental assumption of linear superimposition of modes they are based on. For this reason, in the case of problems featuring coherent structures that propagate over time such as transport, wave, or convection-dominated phenomena, the RB method usually yields inefficient reduced order models (ROMs) if one aims at obtaining reduced order approximations sufficiently accurate compared to the high-fidelity, full order model (FOM) solution. To overcome these limitations, in this work, we propose a new nonlinear approach to set reduced order models by exploiting deep learning (DL) algorithms. In the resulting nonlinear ROM, which we refer to as DL-ROM, both the nonlinear trial manifold (corresponding to the set of basis functions in a linear ROM) as well as the nonlinear reduced dynamics (corresponding to the projection stage in a linear ROM) are learned in a non-intrusive way by relying on DL algorithms; the latter are trained on a set of FOM solutions obtained for different parameter values. In this paper, we show how to construct a DL-ROM for both linear and nonlinear time-dependent parametrized PDEs; moreover, we assess its accuracy on test cases featuring different parametrized PDE problems. Numerical results indicate that DL-ROMs whose dimension is equal to the intrinsic dimensionality of the PDE solutions manifold are able to approximate the solution of parametrized PDEs in situations where a huge number of POD modes would be necessary to achieve the same degree of accuracy.
Tasks
Published	2020-01-12
URL	https://arxiv.org/abs/2001.04001v1
PDF	https://arxiv.org/pdf/2001.04001v1.pdf
PWC	https://paperswithcode.com/paper/a-comprehensive-deep-learning-based-approach
Repo
Framework

Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images


Title	Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images
Authors	Kumar Abhishek, Ghassan Hamarneh, Mark S. Drew
Abstract	The semantic segmentation of skin lesions is an important and common initial task in the computer aided diagnosis of dermoscopic images. Although deep learning-based approaches have considerably improved the segmentation accuracy, there is still room for improvement by addressing the major challenges, such as variations in lesion shape, size, color and varying levels of contrast. In this work, we propose the first deep semantic segmentation framework for dermoscopic images which incorporates, along with the original RGB images, information extracted using the physics of skin illumination and imaging. In particular, we incorporate information from specific color bands, illumination invariant grayscale images, and shading-attenuated images. We evaluate our method on three datasets: the ISBI ISIC 2017 Skin Lesion Segmentation Challenge dataset, the DermoFit Image Library, and the PH2 dataset and observe improvements of 12.02%, 4.30%, and 8.86% respectively in the mean Jaccard index over a baseline model trained only with RGB images.
Tasks	Lesion Segmentation, Semantic Segmentation
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10111v1
PDF	https://arxiv.org/pdf/2003.10111v1.pdf
PWC	https://paperswithcode.com/paper/illumination-based-transformations-improve
Repo
Framework

Automatic Lesion Detection System (ALDS) for Skin Cancer Classification Using SVM and Neural Classifiers


Title	Automatic Lesion Detection System (ALDS) for Skin Cancer Classification Using SVM and Neural Classifiers
Authors	Muhammad Ali Farooq, Muhammad Aatif Mobeen Azhar, Rana Hammad Raza
Abstract	Technology aided platforms provide reliable tools in almost every field these days. These tools being supported by computational power are significant for applications that need sensitive and precise data analysis. One such important application in the medical field is Automatic Lesion Detection System (ALDS) for skin cancer classification. Computer aided diagnosis helps physicians and dermatologists to obtain a second opinion for proper analysis and treatment of skin cancer. Precise segmentation of the cancerous mole along with surrounding area is essential for proper analysis and diagnosis. This paper is focused towards the development of improved ALDS framework based on probabilistic approach that initially utilizes active contours and watershed merged mask for segmenting out the mole and later SVM and Neural Classifier are applied for the classification of the segmented mole. After lesion segmentation, the selected features are classified to ascertain that whether the case under consideration is melanoma or non-melanoma. The approach is tested for varying datasets and comparative analysis is performed that reflects the effectiveness of the proposed system.
Tasks	Lesion Segmentation, Skin Cancer Classification
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06276v1
PDF	https://arxiv.org/pdf/2003.06276v1.pdf
PWC	https://paperswithcode.com/paper/automatic-lesion-detection-system-alds-for
Repo
Framework

Evolving Losses for Unsupervised Video Representation Learning


Title	Evolving Losses for Unsupervised Video Representation Learning
Authors	AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo
Abstract	We present a new method to learn video representations from large-scale unlabeled video data. Ideally, this representation will be generic and transferable, directly usable for new tasks such as action recognition and zero or few-shot learning. We formulate unsupervised representation learning as a multi-modal, multi-task learning problem, where the representations are shared across different modalities via distillation. Further, we introduce the concept of loss function evolution by using an evolutionary search algorithm to automatically find optimal combination of loss functions capturing many (self-supervised) tasks and modalities. Thirdly, we propose an unsupervised representation evaluation metric using distribution matching to a large unlabeled dataset as a prior constraint, based on Zipf’s law. This unsupervised constraint, which is not guided by any labeling, produces similar results to weakly-supervised, task-specific ones. The proposed unsupervised representation learning results in a single RGB network and outperforms previous methods. Notably, it is also more effective than several label-based methods (e.g., ImageNet), with the exception of large, fully labeled video datasets.
Tasks	Few-Shot Learning, Multi-Task Learning, Representation Learning, Unsupervised Representation Learning
Published	2020-02-26
URL	https://arxiv.org/abs/2002.12177v1
PDF	https://arxiv.org/pdf/2002.12177v1.pdf
PWC	https://paperswithcode.com/paper/evolving-losses-for-unsupervised-video
Repo
Framework

Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees


Title	Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
Authors	Sen Na, Yuwei Luo, Zhuoran Yang, Zhaoran Wang, Mladen Kolar
Abstract	Graph representation learning is a ubiquitous task in machine learning where the goal is to embed each vertex into a low-dimensional vector space. We consider the bipartite graph and formalize its representation learning problem as a statistical estimation problem of parameters in a semiparametric exponential family distribution. The bipartite graph is assumed to be generated by a semiparametric exponential family distribution, whose parametric component is given by the proximity of outputs of two one-layer neural networks, while nonparametric (nuisance) component is the base measure. Neural networks take high-dimensional features as inputs and output embedding vectors. In this setting, the representation learning problem is equivalent to recovering the weight matrices. The main challenges of estimation arise from the nonlinearity of activation functions and the nonparametric nuisance component of the distribution. To overcome these challenges, we propose a pseudo-likelihood objective based on the rank-order decomposition technique and focus on its local geometry. We show that the proposed objective is strongly convex in a neighborhood around the ground truth, so that a gradient descent-based method achieves linear convergence rate. Moreover, we prove that the sample complexity of the problem is linear in dimensions (up to logarithmic factors), which is consistent with parametric Gaussian models. However, our estimator is robust to any model misspecification within the exponential family, which is validated in extensive experiments.
Tasks	Graph Representation Learning, Representation Learning
Published	2020-03-02
URL	https://arxiv.org/abs/2003.01013v1
PDF	https://arxiv.org/pdf/2003.01013v1.pdf
PWC	https://paperswithcode.com/paper/semiparametric-nonlinear-bipartite-graph
Repo
Framework

Learning to Walk in the Real World with Minimal Human Effort


Title	Learning to Walk in the Real World with Minimal Human Effort
Authors	Sehoon Ha, Peng Xu, Zhenyu Tan, Sergey Levine, Jie Tan
Abstract	Reliable and stable locomotion has been one of the most fundamental challenges for legged robots. Deep reinforcement learning (deep RL) has emerged as a promising method for developing such control policies autonomously. In this paper, we develop a system for learning legged locomotion policies with deep RL in the real world with minimal human effort. The key difficulties for on-robot learning systems are automatic data collection and safety. We overcome these two challenges by developing a multi-task learning procedure, an automatic reset controller, and a safety-constrained RL framework. We tested our system on the task of learning to walk on three different terrains: flat ground, a soft mattress, and a doormat with crevices. Our system can automatically and efficiently learn locomotion skills on a Minitaur robot with little human intervention.
Tasks	Legged Robots, Multi-Task Learning
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08550v2
PDF	https://arxiv.org/pdf/2002.08550v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-walk-in-the-real-world-with
Repo
Framework