January 31, 2020

2987 words 15 mins read

Paper Group ANR 114

A Review of Modularization Techniques in Artificial Neural Networks. DIViS: Domain Invariant Visual Servoing for Collision-Free Goal Reaching. Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition. Multi-Adversarial Variational Autoencoder Networks. End-to-End Learned Ran …

A Review of Modularization Techniques in Artificial Neural Networks


Title	A Review of Modularization Techniques in Artificial Neural Networks
Authors	Mohammed Amer, Tomás Maul
Abstract	Artificial neural networks (ANNs) have achieved significant success in tackling classical and modern machine learning problems. As learning problems grow in scale and complexity, and expand into multi-disciplinary territory, a more modular approach for scaling ANNs will be needed. Modular neural networks (MNNs) are neural networks that embody the concepts and principles of modularity. MNNs adopt a large number of different techniques for achieving modularization. Previous surveys of modularization techniques are relatively scarce in their systematic analysis of MNNs, focusing mostly on empirical comparisons and lacking an extensive taxonomical framework. In this review, we aim to establish a solid taxonomy that captures the essential properties and relationships of the different variants of MNNs. Based on an investigation of the different levels at which modularization techniques act, we attempt to provide a universal and systematic framework for theorists studying MNNs, also trying along the way to emphasise the strengths and weaknesses of different modularization approaches in order to highlight good practices for neural network practitioners.
Tasks
Published	2019-04-29
URL	http://arxiv.org/abs/1904.12770v1
PDF	http://arxiv.org/pdf/1904.12770v1.pdf
PWC	https://paperswithcode.com/paper/a-review-of-modularization-techniques-in
Repo
Framework

DIViS: Domain Invariant Visual Servoing for Collision-Free Goal Reaching


Title	DIViS: Domain Invariant Visual Servoing for Collision-Free Goal Reaching
Authors	Fereshteh Sadeghi
Abstract	Robots should understand both semantics and physics to be functional in the real world. While robot platforms provide means for interacting with the physical world they cannot autonomously acquire object-level semantics without needing human. In this paper, we investigate how to minimize human effort and intervention to teach robots perform real world tasks that incorporate semantics. We study this question in the context of visual servoing of mobile robots and propose DIViS, a Domain Invariant policy learning approach for collision free Visual Servoing. DIViS incorporates high level semantics from previously collected static human-labeled datasets and learns collision free servoing entirely in simulation and without any real robot data. However, DIViS can directly be deployed on a real robot and is capable of servoing to the user-specified object categories while avoiding collisions in the real world. DIViS is not constrained to be queried by the final view of goal but rather is robust to servo to image goals taken from initial robot view with high occlusions without this impairing its ability to maintain a collision free path. We show the generalization capability of DIViS on real mobile robots in more than 90 real world test scenarios with various unseen object goals in unstructured environments. DIViS is compared to prior approaches via real world experiments and rigorous tests in simulation. For supplementary videos, see: \href{https://fsadeghi.github.io/DIViS}{https://fsadeghi.github.io/DIViS}
Tasks
Published	2019-02-18
URL	http://arxiv.org/abs/1902.05947v1
PDF	http://arxiv.org/pdf/1902.05947v1.pdf
PWC	https://paperswithcode.com/paper/divis-domain-invariant-visual-servoing-for
Repo
Framework

Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition


Title	Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition
Authors	Konstantinos Papadopoulos, Enjie Ghorbel, Djamila Aouada, Björn Ottersten
Abstract	This paper extends the Spatial-Temporal Graph Convolutional Network (ST-GCN) for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN). On the one hand, the GVFE module learns appropriate vertex features for action recognition by encoding raw skeleton data into a new feature space. On the other hand, the DH-TCN module is capable of capturing both short-term and long-term temporal dependencies using a hierarchical dilated convolutional network. Experiments have been conducted on the challenging NTU RGB-D-60 and NTU RGB-D 120 datasets. The obtained results show that our method competes with state-of-the-art approaches while using a smaller number of layers and parameters; thus reducing the required training time and memory.
Tasks	Action Recognition In Videos, Skeleton Based Action Recognition
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09745v1
PDF	https://arxiv.org/pdf/1912.09745v1.pdf
PWC	https://paperswithcode.com/paper/vertex-feature-encoding-and-hierarchical
Repo
Framework

Multi-Adversarial Variational Autoencoder Networks


Title	Multi-Adversarial Variational Autoencoder Networks
Authors	Abdullah-Al-Zubaer Imran, Demetri Terzopoulos
Abstract	The unsupervised training of GANs and VAEs has enabled them to generate realistic images mimicking real-world distributions and perform image-based unsupervised clustering or semi-supervised classification. Combining the power of these two generative models, we introduce Multi-Adversarial Variational autoEncoder Networks (MAVENs), a novel network architecture that incorporates an ensemble of discriminators in a VAE-GAN network, with simultaneous adversarial learning and variational inference. We apply MAVENs to the generation of synthetic images and propose a new distribution measure to quantify the quality of the generated images. Our experimental results using datasets from the computer vision and medical imaging domains—Street View House Numbers, CIFAR-10, and Chest X-Ray datasets—demonstrate competitive performance against state-of-the-art semi-supervised models both in image generation and classification tasks.
Tasks	Image Generation
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06430v1
PDF	https://arxiv.org/pdf/1906.06430v1.pdf
PWC	https://paperswithcode.com/paper/multi-adversarial-variational-autoencoder
Repo
Framework

End-to-End Learned Random Walker for Seeded Image Segmentation


Title	End-to-End Learned Random Walker for Seeded Image Segmentation
Authors	Lorenzo Cerrone, Alexander Zeilmann, Fred A. Hamprecht
Abstract	We present an end-to-end learned algorithm for seeded segmentation. Our method is based on the Random Walker algorithm, where we predict the edge weights of the underlying graph using a convolutional neural network. This can be interpreted as learning context-dependent diffusivities for a linear diffusion process. Besides calculating the exact gradient for optimizing these diffusivities, we also propose simplifications that sparsely sample the gradient and still yield competitive results. The proposed method achieves the currently best results on a seeded version of the CREMI neuron segmentation challenge.
Tasks	Semantic Segmentation
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09045v1
PDF	https://arxiv.org/pdf/1905.09045v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-learned-random-walker-for-seeded-1
Repo
Framework

Better AI through Logical Scaffolding


Title	Better AI through Logical Scaffolding
Authors	Nikos Arechiga, Jonathan DeCastro, Soonho Kong, Karen Leung
Abstract	We describe the concept of logical scaffolds, which can be used to improve the quality of software that relies on AI components. We explain how some of the existing ideas on runtime monitors for perception systems can be seen as a specific instance of logical scaffolds. Furthermore, we describe how logical scaffolds may be useful for improving AI programs beyond perception systems, to include general prediction systems and agent behavior models.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.06965v1
PDF	https://arxiv.org/pdf/1909.06965v1.pdf
PWC	https://paperswithcode.com/paper/better-ai-through-logical-scaffolding
Repo
Framework

Monthly electricity consumption forecasting by the fruit fly optimization algorithm enhanced Holt-Winters smoothing method


Title	Monthly electricity consumption forecasting by the fruit fly optimization algorithm enhanced Holt-Winters smoothing method
Authors	Weiheng Jiang, Xiaogang Wu, Yi Gong, Wanxin Yu, Xinhui Zhong
Abstract	The electricity consumption forecasting is a critical component of the intelligent power system. And accurate monthly electricity consumption forecasting, as one of the the medium and long term electricity consumption forecasting problems, plays an important role in dispatching and management for electric power systems. Although there are many studies for this problem, large sample data set is generally required to obtain higher prediction accuracy, and the prediction performance become worse when only a little data is available. However, in practical, mostly we experience the problem of insufficient sample data and how to accurately forecast the monthly electricity consumption with limited sample data is a challenge task. The Holt-Winters exponential smoothing method often used to forecast periodic series due to low demand for training data and high accuracy for forecasting. In this paper, based on Holt-Winters exponential smoothing method, we propose a hybrid forecasting model named FOA-MHW. The main idea is that, we use fruit fly optimization algorithm to select smoothing parameters for Holt-Winters exponential smoothing method. Besides, electricity consumption data of a city in China is used to comprehensively evaluate the forecasting performance of the proposed model. The results indicate that our model can significantly improve the accuracy of monthly electricity consumption forecasting even in the case that only a small number of training data is available.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.06836v1
PDF	https://arxiv.org/pdf/1908.06836v1.pdf
PWC	https://paperswithcode.com/paper/monthly-electricity-consumption-forecasting
Repo
Framework

New Techniques for Graph Edit Distance Computation


Title	New Techniques for Graph Edit Distance Computation
Authors	David B. Blumenthal
Abstract	Due to their capacity to encode rich structural information, labeled graphs are often used for modeling various kinds of objects such as images, molecules, and chemical compounds. If pattern recognition problems such as clustering and classification are to be solved on these domains, a (dis-)similarity measure for labeled graphs has to be defined. A widely used measure is the graph edit distance (GED), which, intuitively, is defined as the minimum amount of distortion that has to be applied to a source graph in order to transform it into a target graph. The main advantage of GED is its flexibility and sensitivity to small differences between the input graphs. Its main drawback is that it is hard to compute. In this thesis, new results and techniques for several aspects of computing GED are presented. Firstly, theoretical aspects are discussed: competing definitions of GED are harmonized, the problem of computing GED is characterized in terms of complexity, and several reductions from GED to the quadratic assignment problem (QAP) are presented. Secondly, solvers for the linear sum assignment problem with error-correction (LSAPE) are discussed. LSAPE is a generalization of the well-known linear sum assignment problem (LSAP), and has to be solved as a subproblem by many GED algorithms. In particular, a new solver is presented that efficiently reduces LSAPE to LSAP. Thirdly, exact algorithms for computing GED are presented in a systematic way, and improvements of existing algorithms as well as a new mixed integer programming (MIP) based approach are introduced. Fourthly, a detailed overview of heuristic algorithms that approximate GED via upper and lower bounds is provided, and eight new heuristics are described. Finally, a new easily extensible C++ library for exactly or approximately computing GED is presented.
Tasks
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00265v1
PDF	https://arxiv.org/pdf/1908.00265v1.pdf
PWC	https://paperswithcode.com/paper/new-techniques-for-graph-edit-distance
Repo
Framework


Title	I Know You’ll Be Back: Interpretable New User Clustering and Churn Prediction on a Mobile Social Application
Authors	Carl Yang, Xiaolin Shi, Jie Luo, Jiawei Han
Abstract	As online platforms are striving to get more users, a critical challenge is user churn, which is especially concerning for new users. In this paper, by taking the anonymous large-scale real-world data from Snapchat as an example, we develop \textit{ClusChurn}, a systematic two-step framework for interpretable new user clustering and churn prediction, based on the intuition that proper user clustering can help understand and predict user churn. Therefore, \textit{ClusChurn} firstly groups new users into interpretable typical clusters, based on their activities on the platform and ego-network structures. Then we design a novel deep learning pipeline based on LSTM and attention to accurately predict user churn with very limited initial behavior data, by leveraging the correlations among users’ multi-dimensional activities and the underlying user types. \textit{ClusChurn} is also able to predict user types, which enables rapid reactions to different types of user churn. Extensive data analysis and experiments show that \textit{ClusChurn} provides valuable insight into user behaviors, and achieves state-of-the-art churn prediction performance. The whole framework is deployed as a data analysis pipeline, delivering real-time data analysis and prediction results to multiple relevant teams for business intelligence uses. It is also general enough to be readily adopted by any online systems with user behavior data.
Tasks
Published	2019-09-29
URL	https://arxiv.org/abs/1910.01447v1
PDF	https://arxiv.org/pdf/1910.01447v1.pdf
PWC	https://paperswithcode.com/paper/i-know-youll-be-back-interpretable-new-user
Repo
Framework

Semi-Implicit Graph Variational Auto-Encoders


Title	Semi-Implicit Graph Variational Auto-Encoders
Authors	Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Krishna R. Narayanan, Mingyuan Zhou, Xiaoning Qian
Abstract	Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierarchical variational framework to enable neighboring node sharing for better generative modeling of graph dependency structure, together with a Bernoulli-Poisson link decoder. Not only does this hierarchical construction provide a more flexible generative graph model to better capture real-world graph properties, but also does SIG-VAE naturally lead to semi-implicit hierarchical variational inference that allows faithful modeling of implicit posteriors of given graph data, which may exhibit heavy tails, multiple modes, skewness, and rich dependency structures. Compared to VGAE, the derived graph latent representations by SIG-VAE are more interpretable, due to more expressive generative model and more faithful inference enabled by the flexible semi-implicit construction. Extensive experiments with a variety of graph data show that SIG-VAE significantly outperforms state-of-the-art methods on several different graph analytic tasks.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.07078v3
PDF	https://arxiv.org/pdf/1908.07078v3.pdf
PWC	https://paperswithcode.com/paper/semi-implicit-graph-variational-auto-encoders
Repo
Framework

Hierarchical Federated Learning Across Heterogeneous Cellular Networks


Title	Hierarchical Federated Learning Across Heterogeneous Cellular Networks
Authors	Mehdi Salehi Heydar Abad, Emre Ozfatura, Deniz Gunduz, Ozgur Ercetin
Abstract	We study collaborative machine learning (ML) across wireless devices, each with its own local dataset. Offloading these datasets to a cloud or an edge server to implement powerful ML solutions is often not feasible due to latency, bandwidth and privacy constraints. Instead, we consider federated edge learning (FEEL), where the devices share local updates on the model parameters rather than their datasets. We consider a heterogeneous cellular network (HCN), where small cell base stations (SBSs) orchestrate FL among the mobile users (MUs) within their cells, and periodically exchange model updates with the macro base station (MBS) for global consensus. We employ gradient sparsification and periodic averaging to increase the communication efficiency of this hierarchical federated learning (FL) framework. We then show using CIFAR-10 dataset that the proposed hierarchical learning solution can significantly reduce the communication latency without sacrificing the model accuracy.
Tasks
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02362v1
PDF	https://arxiv.org/pdf/1909.02362v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-federated-learning-across
Repo
Framework

Generative Image Inpainting with Submanifold Alignment


Title	Generative Image Inpainting with Submanifold Alignment
Authors	Ang Li, Jianzhong Qi, Rui Zhang, Xingjun Ma, Kotagiri Ramamohanarao
Abstract	Image inpainting aims at restoring missing regions of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based generative inpainting models do not explicitly exploit the structural or textural consistency between restored contents and their surrounding contexts.To address this limitation, we propose to enforce the alignment (or closeness) between the local data submanifolds (or subspaces) around restored images and those around the original (uncorrupted) images during the learning process of GAN-based inpainting models. We exploit Local Intrinsic Dimensionality (LID) to measure, in deep feature space, the alignment between data submanifolds learned by a GAN model and those of the original data, from a perspective of both images (denoted as iLID) and local patches (denoted as pLID) of images. We then apply iLID and pLID as regularizations for GAN-based inpainting models to encourage two levels of submanifold alignment: 1) an image-level alignment for improving structural consistency, and 2) a patch-level alignment for improving textural details. Experimental results on four benchmark datasets show that our proposed model can generate more accurate results than state-of-the-art models.
Tasks	Image Inpainting, Image Restoration
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00211v1
PDF	https://arxiv.org/pdf/1908.00211v1.pdf
PWC	https://paperswithcode.com/paper/generative-image-inpainting-with-submanifold
Repo
Framework

Weak Edge Identification Nets for Ocean Front Detection


Title	Weak Edge Identification Nets for Ocean Front Detection
Authors	Qingyang Li, Guoqiang Zhong, Cui Xie
Abstract	The ocean front has an important impact in many areas, it is meaningful to obtain accurate ocean front positioning, therefore, ocean front detection is a very important task. However, the traditional edge detection algorithm does not detect the weak edge information of the ocean front very well. In response to this problem, we collected relevant ocean front gradient images and found relevant experts to calibrate the ocean front data to obtain groundtruth, and proposed a weak edge identification nets(WEIN) for ocean front detection. Whether it is qualitative or quantitative, our methods perform best. The method uses a welltrained deep learning model to accurately extract the ocean front from the ocean front gradient image. The detection network is divided into multiple stages, and the final output is a multi-stage output image fusion. The method uses the stochastic gradient descent and the correlation loss function to obtain a good ocean front image output.
Tasks	Edge Detection
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07827v1
PDF	https://arxiv.org/pdf/1909.07827v1.pdf
PWC	https://paperswithcode.com/paper/weak-edge-identification-nets-for-ocean-front
Repo
Framework

Persistent entropy: a scale-invariant topological statistic for analyzing cell arrangements


Title	Persistent entropy: a scale-invariant topological statistic for analyzing cell arrangements
Authors	N. Atienza, L. M. Escudero, M. J. Jimenez, M. Soriano-Trigueros
Abstract	In this work, we develop a method for detecting differences in the topological distribution of cells forming epithelial tissues. In particular, we extract topological information from their images using persistent homology and a summary statistic called persistent entropy. This method is scale invariant,robust to noise and sensitive to global topological features of the tissue. We have found significant differences between chick neuroepithelium and epithelium of Drosophila wing discs in both, larva andprepupal stages. Besides, we have tested our method, with good results, with images of mathematical tesselations that model biological tissues.
Tasks
Published	2019-02-18
URL	https://arxiv.org/abs/1902.06467v4
PDF	https://arxiv.org/pdf/1902.06467v4.pdf
PWC	https://paperswithcode.com/paper/persistent-entropy-a-scale-invariant
Repo
Framework

Active Ordinal Querying for Tuplewise Similarity Learning


Title	Active Ordinal Querying for Tuplewise Similarity Learning
Authors	Gregory Canal, Stefano Fenu, Christopher Rozell
Abstract	Many machine learning tasks such as clustering, classification, and dataset search benefit from embedding data points in a space where distances reflect notions of relative similarity as perceived by humans. A common way to construct such an embedding is to request triplet similarity queries to an oracle, comparing two objects with respect to a reference. This work generalizes triplet queries to tuple queries of arbitrary size that ask an oracle to rank multiple objects against a reference, and introduces an efficient and robust adaptive selection method called InfoTuple that uses a novel approach to mutual information maximization. We show that the performance of InfoTuple at various tuple sizes exceeds that of the state-of-the-art adaptive triplet selection method on synthetic tests and new human response datasets, and empirically demonstrate the significant gains in efficiency and query consistency achieved by querying larger tuples instead of triplets.
Tasks
Published	2019-10-09
URL	https://arxiv.org/abs/1910.04115v3
PDF	https://arxiv.org/pdf/1910.04115v3.pdf
PWC	https://paperswithcode.com/paper/active-ordinal-tuplewise-querying-for
Repo
Framework