January 28, 2020

2899 words 14 mins read

Paper Group ANR 930

Heart Segmentation From MRI Scans Using Convolutional Neural Network. How Much Can We See? A Note on Quantifying Explainability of Machine Learning Models. Learning Graph Embedding with Adversarial Training Methods. Localizing Unseen Activities in Video via Image Query. Deep Learning-Based Constellation Optimization for Physical Network Coding in T …

Heart Segmentation From MRI Scans Using Convolutional Neural Network


Title	Heart Segmentation From MRI Scans Using Convolutional Neural Network
Authors	Shakeel Muhammad Ibrahim, Muhammad Sohail Ibrahim, Muhammad Usman, Imran Naseem, Muhammad Moinuddin
Abstract	Heart is one of the vital organs of human body. A minor dysfunction of heart even for a short time interval can be fatal, therefore, efficient monitoring of its physiological state is essential for the patients with cardiovascular diseases. In the recent past, various computer assisted medical imaging systems have been proposed for the segmentation of the organ of interest. However, for the segmentation of heart using MRI, only few methods have been proposed each with its own merits and demerits. For further advancement in this area of research, we analyze automated heart segmentation methods for magnetic resonance images. The analysis are based on deep learning methods that processes a full MR scan in a slice by slice fashion to predict desired mask for heart region. We design two encoder decoder type fully convolutional neural network models
Tasks
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09332v1
PDF	https://arxiv.org/pdf/1911.09332v1.pdf
PWC	https://paperswithcode.com/paper/heart-segmentation-from-mri-scans-using
Repo
Framework

How Much Can We See? A Note on Quantifying Explainability of Machine Learning Models


Title	How Much Can We See? A Note on Quantifying Explainability of Machine Learning Models
Authors	Gero Szepannek
Abstract	One of the most popular approaches to understanding feature effects of modern black box machine learning models are partial dependence plots (PDP). These plots are easy to understand but only able to visualize low order dependencies. The paper is about the question ‘How much can we see?': A framework is developed to quantify the explainability of arbitrary machine learning models, i.e. up to what degree the visualization as given by a PDP is able to explain the predictions of the model. The result allows for a judgement whether an attempt to explain a black box model is sufficient or not.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13376v2
PDF	https://arxiv.org/pdf/1910.13376v2.pdf
PWC	https://paperswithcode.com/paper/191013376
Repo
Framework

Learning Graph Embedding with Adversarial Training Methods


Title	Learning Graph Embedding with Adversarial Training Methods
Authors	Shirui Pan, Ruiqi Hu, Sai-fu Fung, Guodong Long, Jing Jiang, Chengqi Zhang
Abstract	Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes, which unfortunately may lead to inferior representation in many cases. In this paper, we present a novel adversarially regularized framework for graph embedding. By employing the graph convolutional network as an encoder, our framework embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph. The adversarial training principle is applied to enforce our latent codes to match a prior Gaussian or Uniform distribution. Based on this framework, we derive two variants of adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively. We also exploit other potential variations of ARGA and ARVGA to get a deeper understanding on our designs. Experimental results compared among twelve algorithms for link prediction and twenty algorithms for graph clustering validate our solutions.
Tasks	Graph Clustering, Graph Embedding, Link Prediction
Published	2019-01-04
URL	https://arxiv.org/abs/1901.01250v2
PDF	https://arxiv.org/pdf/1901.01250v2.pdf
PWC	https://paperswithcode.com/paper/learning-graph-embedding-with-adversarial
Repo
Framework

Localizing Unseen Activities in Video via Image Query


Title	Localizing Unseen Activities in Video via Image Query
Authors	Zhu Zhang, Zhou Zhao, Zhijie Lin, Jingkuan Song, Deng Cai
Abstract	Action localization in untrimmed videos is an important topic in the field of video understanding. However, existing action localization methods are restricted to a pre-defined set of actions and cannot localize unseen activities. Thus, we consider a new task to localize unseen activities in videos via image queries, named Image-Based Activity Localization. This task faces three inherent challenges: (1) how to eliminate the influence of semantically inessential contents in image queries; (2) how to deal with the fuzzy localization of inaccurate image queries; (3) how to determine the precise boundaries of target segments. We then propose a novel self-attention interaction localizer to retrieve unseen activities in an end-to-end fashion. Specifically, we first devise a region self-attention method with relative position encoding to learn fine-grained image region representations. Then, we employ a local transformer encoder to build multi-step fusion and reasoning of image and video contents. We next adopt an order-sensitive localizer to directly retrieve the target segment. Furthermore, we construct a new dataset ActivityIBAL by reorganizing the ActivityNet dataset. The extensive experiments show the effectiveness of our method.
Tasks	Action Localization, Video Understanding
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12165v1
PDF	https://arxiv.org/pdf/1906.12165v1.pdf
PWC	https://paperswithcode.com/paper/localizing-unseen-activities-in-video-via
Repo
Framework

Deep Learning-Based Constellation Optimization for Physical Network Coding in Two-Way Relay Networks


Title	Deep Learning-Based Constellation Optimization for Physical Network Coding in Two-Way Relay Networks
Authors	Toshiki Matsumine, Toshiaki Koike-Akino, Ye Wang
Abstract	This paper studies a new application of deep learning (DL) for optimizing constellations in two-way relaying with physical-layer network coding (PNC), where deep neural network (DNN)-based modulation and demodulation are employed at each terminal and relay node. We train DNNs such that the cross entropy loss is directly minimized, and thus it maximizes the likelihood, rather than considering the Euclidean distance of the constellations. The proposed scheme can be extended to higher level constellations with slight modification of the DNN structure. Simulation results demonstrate a significant performance gain in terms of the achievable sum rate over conventional relaying schemes. Furthermore, since our DNN demodulator directly outputs bit-wise probabilities, it is straightforward to concatenate with soft-decision channel decoding.
Tasks
Published	2019-03-09
URL	http://arxiv.org/abs/1903.03713v1
PDF	http://arxiv.org/pdf/1903.03713v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-constellation
Repo
Framework

ASAP: Architecture Search, Anneal and Prune


Title	ASAP: Architecture Search, Anneal and Prune
Authors	Asaf Noy, Niv Nayman, Tal Ridnik, Nadav Zamir, Sivan Doveh, Itamar Friedman, Raja Giryes, Lihi Zelnik-Manor
Abstract	Automatic methods for Neural Architecture Search (NAS) have been shown to produce state-of-the-art network models. Yet, their main drawback is the computational complexity of the search process. As some primal methods optimized over a discrete search space, thousands of days of GPU were required for convergence. A recent approach is based on constructing a differentiable search space that enables gradient-based optimization, which reduces the search time to a few days. While successful, it still includes some noncontinuous steps, e.g., the pruning of many weak connections at once. In this paper, we propose a differentiable search space that allows the annealing of architecture weights, while gradually pruning inferior operations. In this way, the search converges to a single output network in a continuous manner. Experiments on several vision datasets demonstrate the effectiveness of our method with respect to the search cost and accuracy of the achieved model. Specifically, with $0.2$ GPU search days we achieve an error rate of $1.68%$ on CIFAR-10.
Tasks	Neural Architecture Search
Published	2019-04-08
URL	https://arxiv.org/abs/1904.04123v2
PDF	https://arxiv.org/pdf/1904.04123v2.pdf
PWC	https://paperswithcode.com/paper/asap-architecture-search-anneal-and-prune
Repo
Framework

Spatial Sparse subspace clustering for Compressive Spectral imaging


Title	Spatial Sparse subspace clustering for Compressive Spectral imaging
Authors	Jianchen Zhu, Tong Zhang, Shengjie Zhao, Carlos Hinojosa, Zengli Liu, Gonzalo R. Arce
Abstract	This paper aims at developing a clustering approach with spectral images directly from CASSI compressive measurements. The proposed clustering method first assumes that compressed measurements lie in the union of multiple low-dimensional subspaces. Therefore, sparse subspace clustering (SSC) is an unsupervised method that assigns compressed measurements to their respective subspaces. In addition, a 3D spatial regularizer is added into the SSC problem, thus taking full advantages of the spatial information contained in spectral images. The performance of the proposed spectral image clustering approach is improved by taking optimal CASSI measurements obtained when optimal coded apertures are used in CASSI system. Simulation with one real dataset illustrates the accuracy of the proposed spectral image clustering approach.
Tasks	Image Clustering
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01671v1
PDF	https://arxiv.org/pdf/1911.01671v1.pdf
PWC	https://paperswithcode.com/paper/spatial-sparse-subspace-clustering-for
Repo
Framework

Face Identification using Local Ternary Tree Pattern based Spatial Structural Components


Title	Face Identification using Local Ternary Tree Pattern based Spatial Structural Components
Authors	Rinku Datta Rakshit, Dakshina Ranjan Kisku, Massimo Tistarelli, Phalguni Gupta
Abstract	This paper reports groundbreaking results of a face identification system which makes use of a novel local descriptor called Local Ternary Tree Pattern. Devising deft and feasible local descriptors for a face image plays an emergent preface in face identification task when the system performs in presence of lots of variety of face images including constrained, unconstrained and plastic surgery images. The LTTP has been proposed to extract robust and discriminatory spatial features from a face image as this descriptor can be used to best describe the various structural components of a face. To extract the most useful features, a ternary tree is formed for each pixel with its eight neighbors. LTTP pattern can be generated in four ways: LTTP Left Depth, LTTP Left Breadth, LTTP Right Depth and LTTP Right Breadth. The encoding schemes of these four patterns generation are very simple and efficient in terms of computational complexity as well as time complexity. The proposed face identification system is tested on six face databases, namely, the UMIST, the JAFFE, the extended Yale face B, the Plastic Surgery, the LFW and the UFI. The experimental evaluation demonstrates the most outstanding results which will have long term impact in designing face identification systems considering a variety of faces captured under different environments.
Tasks	Face Identification
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00693v1
PDF	https://arxiv.org/pdf/1905.00693v1.pdf
PWC	https://paperswithcode.com/paper/face-identification-using-local-ternary-tree
Repo
Framework

Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations


Title	Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations
Authors	Cong Fang, Hanze Dong, Tong Zhang
Abstract	Recently, over-parameterized neural networks have been extensively analyzed in the literature. However, the previous studies cannot satisfactorily explain why fully trained neural networks are successful in practice. In this paper, we present a new theoretical framework for analyzing over-parameterized neural networks which we call neural feature repopulation. Our analysis can satisfactorily explain the empirical success of two level neural networks that are trained by standard learning algorithms. Our key theoretical result is that in the limit of infinite number of hidden neurons, over-parameterized two-level neural networks trained via the standard (noisy) gradient descent learns a well-defined feature distribution (population), and the limiting feature distribution is nearly optimal for the underlying learning task under certain conditions. Empirical studies confirm that predictions of our theory are consistent with the results observed in real practice.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11508v1
PDF	https://arxiv.org/pdf/1910.11508v1.pdf
PWC	https://paperswithcode.com/paper/over-parameterized-two-level-neural-networks
Repo
Framework

Learning scalable and transferable multi-robot/machine sequential assignment planning via graph embedding


Title	Learning scalable and transferable multi-robot/machine sequential assignment planning via graph embedding
Authors	Hyunwook Kang, Aydar Mynbay, James R. Morrison, Jinkyoo Park
Abstract	Can the success of reinforcement learning methods for simple combinatorial optimization problems be extended to multi-robot sequential assignment planning? In addition to the challenge of achieving near-optimal performance in large problems, transferability to an unseen number of robots and tasks is another key challenge for real-world applications. In this paper, we suggest a method that achieves the first success in both challenges for robot/machine scheduling problems. Our method comprises of three components. First, we show a robot scheduling problem can be expressed as a random probabilistic graphical model (PGM). We develop a mean-field inference method for random PGM and use it for Q-function inference. Second, we show that transferability can be achieved by carefully designing two-step sequential encoding of problem state. Third, we resolve the computational scalability issue of fitted Q-iteration by suggesting a heuristic auction-based Q-iteration fitting method enabled by transferability we achieved. We apply our method to discrete-time, discrete space problems (Multi-Robot Reward Collection (MRRC)) and scalably achieve 97% optimality with transferability. This optimality is maintained under stochastic contexts. By extending our method to continuous time, continuous space formulation, we claim to be the first learning-based method with scalable performance among multi-machine scheduling problems; our method scalability achieves comparable performance to popular metaheuristics in Identical parallel machine scheduling (IPMS) problems.
Tasks	Combinatorial Optimization, Graph Embedding
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12204v3
PDF	https://arxiv.org/pdf/1905.12204v3.pdf
PWC	https://paperswithcode.com/paper/scalable-and-transferable-learning-of
Repo
Framework

An Abstraction-Based Framework for Neural Network Verification


Title	An Abstraction-Based Framework for Neural Network Verification
Authors	Yizhak Yisrael Elboher, Justin Gottschlich, Guy Katz
Abstract	Deep neural networks are increasingly being used as controllers for safety-critical systems. Because neural networks are opaque, certifying their correctness is a significant challenge. To address this issue, several approaches have recently been proposed to formally verify them. However, network size is often a bottleneck for such approaches and it can be difficult to apply them to large networks. In this paper, we propose a framework that can enhance neural network verification techniques by using over-approximation to reduce the size of the network - thus making it more amenable to verification. We perform the approximation such that if the property holds for the smaller (abstract) network, it holds for the original as well. The over-approximation may be too coarse, in which case the underlying verification tool might return a spurious counterexample. Under such conditions, we perform counterexample-guided refinement to adjust the approximation, and then repeat the process. Our approach is orthogonal to, and can be integrated with, many existing verification techniques. For evaluation purposes, we integrate it with the recently proposed Marabou framework, and observe a significant improvement in Marabou’s performance. Our experiments demonstrate the great potential of our approach for verifying larger neural networks.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14574v1
PDF	https://arxiv.org/pdf/1910.14574v1.pdf
PWC	https://paperswithcode.com/paper/an-abstraction-based-framework-for-neural
Repo
Framework

Sequential Edge Clustering in Temporal Multigraphs


Title	Sequential Edge Clustering in Temporal Multigraphs
Authors	Elahe Ghalebi, Hamidreza Mahyar, Radu Grosu, Graham W. Taylor, Sinead A. Williamson
Abstract	Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable models necessarily ignore temporal dynamics in the network. We propose a dynamic nonparametric model for interaction graphs that combine the sparsity of the exchangeable models with dynamic clustering patterns that tend to reinforce recent behavioral patterns. We show that our method yields improved held-out likelihood over stationary variants, and impressive predictive performance against a range of state-of-the-art dynamic interaction graph models.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11724v3
PDF	https://arxiv.org/pdf/1905.11724v3.pdf
PWC	https://paperswithcode.com/paper/dynamic-nonparametric-edge-clustering-model
Repo
Framework

Transportation Mode Classification from Smartphone Sensors via a Long-Short-Term-Memory Network


Title	Transportation Mode Classification from Smartphone Sensors via a Long-Short-Term-Memory Network
Authors	Björn Friedrich, Benjamin Cauchy, Andreas Hein, Sebastian Fudickar
Abstract	This article introduces the architecture of a Long-Short-Term Memory network for classifying transportation-modes via Smartphone data and evaluates its accuracy. By using a Long-Short-Term-Memory Network with common preprocessing steps such as normalisation for classification tasks a F1-Score accuracy of 63.68% was achieved with an internal test dataset. We participated as Team ‘GanbareAM’ in the ‘SHL recognition challenge’.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04739v1
PDF	https://arxiv.org/pdf/1910.04739v1.pdf
PWC	https://paperswithcode.com/paper/transportation-mode-classification-from
Repo
Framework

Sparse Neural Attentive Knowledge-based Models for Grade Prediction


Title	Sparse Neural Attentive Knowledge-based Models for Grade Prediction
Authors	Sara Morsy, George Karypis
Abstract	Grade prediction for future courses not yet taken by students is important as it can help them and their advisers during the process of course selection as well as for designing personalized degree plans and modifying them based on their performance. One of the successful approaches for accurately predicting a student’s grades in future courses is Cumulative Knowledge-based Regression Models (CKRM). CKRM learns shallow linear models that predict a student’s grades as the similarity between his/her knowledge state and the target course. A student’s knowledge state is built by linearly accumulating the learned provided knowledge components of the courses he/she has taken in the past, weighted by his/her grades in them. However, not all the prior courses contribute equally to the target course. In this paper, we propose a novel Neural Attentive Knowledge-based model (NAK) that learns the importance of each historical course in predicting the grade of a target course. Compared to CKRM and other competing approaches, our experiments on a large real-world dataset consisting of $\sim$1.5 grades show the effectiveness of the proposed NAK model in accurately predicting the students’ grades. Moreover, the attention weights learned by the model can be helpful in better designing their degree plans.
Tasks
Published	2019-04-22
URL	http://arxiv.org/abs/1904.11858v1
PDF	http://arxiv.org/pdf/1904.11858v1.pdf
PWC	https://paperswithcode.com/paper/sparse-neural-attentive-knowledge-based
Repo
Framework

Network reconstruction and community detection from dynamics


Title	Network reconstruction and community detection from dynamics
Authors	Tiago P. Peixoto
Abstract	We present a scalable nonparametric Bayesian method to perform network reconstruction from observed functional behavior that at the same time infers the communities present in the network. We show that the joint reconstruction with community detection has a synergistic effect, where the edge correlations used to inform the existence of communities are also inherently used to improve the accuracy of the reconstruction which, in turn, can better inform the uncovering of communities. We illustrate the use of our method with observations arising from epidemic models and the Ising model, both on synthetic and empirical networks, as well as on data containing only functional information.
Tasks	Community Detection
Published	2019-03-26
URL	https://arxiv.org/abs/1903.10833v2
PDF	https://arxiv.org/pdf/1903.10833v2.pdf
PWC	https://paperswithcode.com/paper/network-reconstruction-and-community
Repo
Framework