July 30, 2019

3091 words 15 mins read

Paper Group AWR 72

Hidden Community Detection in Social Networks. Performance Analysis of Open Source Machine Learning Frameworks for Various Parameters in Single-Threaded and Multi-Threaded Modes. Learning Fashion Compatibility with Bidirectional LSTMs. Fast, Simple Calcium Imaging Segmentation with Fully Convolutional Networks. Emotion Recognition in the Wild using …


Title	Hidden Community Detection in Social Networks
Authors	Kun He, Yingru Li, Sucheta Soundarajan, John E. Hopcroft
Abstract	We introduce a new paradigm that is important for community detection in the realm of network analysis. Networks contain a set of strong, dominant communities, which interfere with the detection of weak, natural community structure. When most of the members of the weak communities also belong to stronger communities, they are extremely hard to be uncovered. We call the weak communities the hidden community structure. We present a novel approach called HICODE (HIdden COmmunity DEtection) that identifies the hidden community structure as well as the dominant community structure. By weakening the strength of the dominant structure, one can uncover the hidden structure beneath. Likewise, by reducing the strength of the hidden structure, one can more accurately identify the dominant structure. In this way, HICODE tackles both tasks simultaneously. Extensive experiments on real-world networks demonstrate that HICODE outperforms several state-of-the-art community detection methods in uncovering both the dominant and the hidden structure. In the Facebook university social networks, we find multiple non-redundant sets of communities that are strongly associated with residential hall, year of registration or career position of the faculties or students, while the state-of-the-art algorithms mainly locate the dominant ground truth category. In the Due to the difficulty of labeling all ground truth communities in real-world datasets, HICODE provides a promising approach to pinpoint the existing latent communities and uncover communities for which there is no ground truth. Finding this unknown structure is an extremely important community detection problem.
Tasks	Community Detection
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07462v1
PDF	http://arxiv.org/pdf/1702.07462v1.pdf
PWC	https://paperswithcode.com/paper/hidden-community-detection-in-social-networks
Repo	https://github.com/GamesResearchTUG/HiCode
Framework	none

Performance Analysis of Open Source Machine Learning Frameworks for Various Parameters in Single-Threaded and Multi-Threaded Modes


Title	Performance Analysis of Open Source Machine Learning Frameworks for Various Parameters in Single-Threaded and Multi-Threaded Modes
Authors	Yuriy Kochura, Sergii Stirenko, Oleg Alienin, Michail Novotarskiy, Yuri Gordienko
Abstract	The basic features of some of the most versatile and popular open source frameworks for machine learning (TensorFlow, Deep Learning4j, and H2O) are considered and compared. Their comparative analysis was performed and conclusions were made as to the advantages and disadvantages of these platforms. The performance tests for the de facto standard MNIST data set were carried out on H2O framework for deep learning algorithms designed for CPU and GPU platforms for single-threaded and multithreaded modes of operation Also, we present the results of testing neural networks architectures on H2O platform for various activation functions, stopping metrics, and other parameters of machine learning algorithm. It was demonstrated for the use case of MNIST database of handwritten digits in single-threaded mode that blind selection of these parameters can hugely increase (by 2-3 orders) the runtime without the significant increase of precision. This result can have crucial influence for optimization of available and new machine learning methods, especially for image recognition problems.
Tasks	Hyperparameter Optimization
Published	2017-08-29
URL	http://arxiv.org/abs/1708.08670v1
PDF	http://arxiv.org/pdf/1708.08670v1.pdf
PWC	https://paperswithcode.com/paper/performance-analysis-of-open-source-machine
Repo	https://github.com/h2oai/h2o-3
Framework	tf

Learning Fashion Compatibility with Bidirectional LSTMs


Title	Learning Fashion Compatibility with Bidirectional LSTMs
Authors	Xintong Han, Zuxuan Wu, Yu-Gang Jiang, Larry S. Davis
Abstract	The ubiquity of online fashion shopping demands effective recommendation services for customers. In this paper, we study two types of fashion recommendation: (i) suggesting an item that matches existing components in a set to form a stylish outfit (a collection of fashion items), and (ii) generating an outfit with multimodal (images/text) specifications from a user. To this end, we propose to jointly learn a visual-semantic embedding and the compatibility relationships among fashion items in an end-to-end fashion. More specifically, we consider a fashion outfit to be a sequence (usually from top to bottom and then accessories) and each item in the outfit as a time step. Given the fashion items in an outfit, we train a bidirectional LSTM (Bi-LSTM) model to sequentially predict the next item conditioned on previous ones to learn their compatibility relationships. Further, we learn a visual-semantic space by regressing image features to their semantic representations aiming to inject attribute and category information as a regularization for training the LSTM. The trained network can not only perform the aforementioned recommendations effectively but also predict the compatibility of a given outfit. We conduct extensive experiments on our newly collected Polyvore dataset, and the results provide strong qualitative and quantitative evidence that our framework outperforms alternative methods.
Tasks
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05691v1
PDF	http://arxiv.org/pdf/1707.05691v1.pdf
PWC	https://paperswithcode.com/paper/learning-fashion-compatibility-with
Repo	https://github.com/xthan/polyvore-dataset
Framework	none

Fast, Simple Calcium Imaging Segmentation with Fully Convolutional Networks


Title	Fast, Simple Calcium Imaging Segmentation with Fully Convolutional Networks
Authors	Aleksander Klibisz, Derek Rose, Matthew Eicholtz, Jay Blundon, Stanislav Zakharenko
Abstract	Calcium imaging is a technique for observing neuron activity as a series of images showing indicator fluorescence over time. Manually segmenting neurons is time-consuming, leading to research on automated calcium imaging segmentation (ACIS). We evaluated several deep learning models for ACIS on the Neurofinder competition datasets and report our best model: U-Net2DS, a fully convolutional network that operates on 2D mean summary images. U-Net2DS requires minimal domain-specific pre/post-processing and parameter adjustment, and predictions are made on full $512\times512$ images at $\approx$9K images per minute. It ranks third in the Neurofinder competition ($F_1=0.569$) and is the best model to exclusively use deep learning. We also demonstrate useful segmentations on data from outside the competition. The model’s simplicity, speed, and quality results make it a practical choice for ACIS and a strong baseline for more complex models in the future.
Tasks
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06314v1
PDF	http://arxiv.org/pdf/1707.06314v1.pdf
PWC	https://paperswithcode.com/paper/fast-simple-calcium-imaging-segmentation-with
Repo	https://github.com/ankit-vaghela30/Cilia-Segmentation
Framework	none

Emotion Recognition in the Wild using Deep Neural Networks and Bayesian Classifiers


Title	Emotion Recognition in the Wild using Deep Neural Networks and Bayesian Classifiers
Authors	Luca Surace, Massimiliano Patacchiola, Elena Battini Sönmez, William Spataro, Angelo Cangelosi
Abstract	Group emotion recognition in the wild is a challenging problem, due to the unstructured environments in which everyday life pictures are taken. Some of the obstacles for an effective classification are occlusions, variable lighting conditions, and image quality. In this work we present a solution based on a novel combination of deep neural networks and Bayesian classifiers. The neural network works on a bottom-up approach, analyzing emotions expressed by isolated faces. The Bayesian classifier estimates a global emotion integrating top-down features obtained through a scene descriptor. In order to validate the system we tested the framework on the dataset released for the Emotion Recognition in the Wild Challenge 2017. Our method achieved an accuracy of 64.68% on the test set, significantly outperforming the 53.62% competition baseline.
Tasks	Emotion Recognition
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03820v1
PDF	http://arxiv.org/pdf/1709.03820v1.pdf
PWC	https://paperswithcode.com/paper/emotion-recognition-in-the-wild-using-deep
Repo	https://github.com/lukeoverride/deemotions
Framework	tf

An Interactive Greedy Approach to Group Sparsity in High Dimensions


Title	An Interactive Greedy Approach to Group Sparsity in High Dimensions
Authors	Wei Qian, Wending Li, Yasuhiro Sogawa, Ryohei Fujimaki, Xitong Yang, Ji Liu
Abstract	Sparsity learning with known grouping structure has received considerable attention due to wide modern applications in high-dimensional data analysis. Although advantages of using group information have been well-studied by shrinkage-based approaches, benefits of group sparsity have not been well-documented for greedy-type methods, which much limits our understanding and use of this important class of methods. In this paper, generalizing from a popular forward-backward greedy approach, we propose a new interactive greedy algorithm for group sparsity learning and prove that the proposed greedy-type algorithm attains the desired benefits of group sparsity under high dimensional settings. An estimation error bound refining other existing methods and a guarantee for group support recovery are also established simultaneously. In addition, we incorporate a general M-estimation framework and introduce an interactive feature to allow extra algorithm flexibility without compromise in theoretical properties. The promising use of our proposal is demonstrated through numerical evaluations including a real industrial application in human activity recognition at home. Supplementary materials for this article are available online.
Tasks	Activity Recognition, Human Activity Recognition
Published	2017-07-10
URL	http://arxiv.org/abs/1707.02963v5
PDF	http://arxiv.org/pdf/1707.02963v5.pdf
PWC	https://paperswithcode.com/paper/an-interactive-greedy-approach-to-group
Repo	https://github.com/weiqian1/IGA
Framework	none

Graph Convolutional Matrix Completion


Title	Graph Convolutional Matrix Completion
Authors	Rianne van den Berg, Thomas N. Kipf, Max Welling
Abstract	We consider matrix completion for recommender systems from the point of view of link prediction on graphs. Interaction data such as movie ratings can be represented by a bipartite user-item graph with labeled edges denoting observed ratings. Building on recent progress in deep learning on graph-structured data, we propose a graph auto-encoder framework based on differentiable message passing on the bipartite interaction graph. Our model shows competitive performance on standard collaborative filtering benchmarks. In settings where complimentary feature information or structured data such as a social network is available, our framework outperforms recent state-of-the-art methods.
Tasks	Link Prediction, Matrix Completion, Recommendation Systems
Published	2017-06-07
URL	http://arxiv.org/abs/1706.02263v2
PDF	http://arxiv.org/pdf/1706.02263v2.pdf
PWC	https://paperswithcode.com/paper/graph-convolutional-matrix-completion
Repo	https://github.com/riannevdberg/gc-mc
Framework	tf

Adversarial Dropout for Supervised and Semi-supervised Learning


Title	Adversarial Dropout for Supervised and Semi-supervised Learning
Authors	Sungrae Park, Jun-Keon Park, Su-Jin Shin, Il-Chul Moon
Abstract	Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually biased inputs to enhance the generality, this paper introduces adversarial dropout, which is a minimal set of dropouts that maximize the divergence between the outputs from the network with the dropouts and the training supervisions. The identified adversarial dropout are used to reconfigure the neural network to train, and we demonstrated that training on the reconfigured sub-network improves the generalization performance of supervised and semi-supervised learning tasks on MNIST and CIFAR-10. We analyzed the trained model to reason the performance improvement, and we found that adversarial dropout increases the sparsity of neural networks more than the standard dropout does.
Tasks
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03631v2
PDF	http://arxiv.org/pdf/1707.03631v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-dropout-for-supervised-and-semi
Repo	https://github.com/tiff-wang/adversarial-dropout-reproducibility-challenge
Framework	tf

CLBlast: A Tuned OpenCL BLAS Library


Title	CLBlast: A Tuned OpenCL BLAS Library
Authors	Cedric Nugteren
Abstract	This work introduces CLBlast, an open-source BLAS library providing optimized OpenCL routines to accelerate dense linear algebra for a wide variety of devices. It is targeted at machine learning and HPC applications and thus provides a fast matrix-multiplication routine (GEMM) to accelerate the core of many applications (e.g. deep learning, iterative solvers, astrophysics, computational fluid dynamics, quantum chemistry). CLBlast has five main advantages over other OpenCL BLAS libraries: 1) it is optimized for and tested on a large variety of OpenCL devices including less commonly used devices such as embedded and low-power GPUs, 2) it can be explicitly tuned for specific problem-sizes on specific hardware platforms, 3) it can perform operations in half-precision floating-point FP16 saving bandwidth, time and energy, 4) it has an optional CUDA back-end, 5) and it can combine multiple operations in a single batched routine, accelerating smaller problems significantly. This paper describes the library and demonstrates the advantages of CLBlast experimentally for different use-cases on a wide variety of OpenCL hardware.
Tasks
Published	2017-05-12
URL	http://arxiv.org/abs/1705.05249v2
PDF	http://arxiv.org/pdf/1705.05249v2.pdf
PWC	https://paperswithcode.com/paper/clblast-a-tuned-opencl-blas-library
Repo	https://github.com/CNugteren/CLBlast
Framework	none

Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics


Title	Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
Authors	Ken Kansky, Tom Silver, David A. Mély, Mohamed Eldawy, Miguel Lázaro-Gredilla, Xinghua Lou, Nimrod Dorfman, Szymon Sidor, Scott Phoenix, Dileep George
Abstract	The recent adaptation of deep neural network-based methods to reinforcement learning and planning domains has yielded remarkable progress on individual tasks. Nonetheless, progress on task-to-task transfer remains limited. In pursuit of efficient and robust generalization, we introduce the Schema Network, an object-oriented generative physics simulator capable of disentangling multiple causes of events and reasoning backward through causes to achieve goals. The richly structured architecture of the Schema Network can learn the dynamics of an environment directly from data. We compare Schema Networks with Asynchronous Advantage Actor-Critic and Progressive Networks on a suite of Breakout variations, reporting results on training efficiency and zero-shot generalization, consistently demonstrating faster, more robust learning and better transfer. We argue that generalizing from limited data and learning causal relationships are essential abilities on the path toward generally intelligent systems.
Tasks
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04317v2
PDF	http://arxiv.org/pdf/1706.04317v2.pdf
PWC	https://paperswithcode.com/paper/schema-networks-zero-shot-transfer-with-a
Repo	https://github.com/mzhao98/DeepQLearning_CrossyRoad
Framework	tf

Pixels to Graphs by Associative Embedding


Title	Pixels to Graphs by Associative Embedding
Authors	Alejandro Newell, Jia Deng
Abstract	Graphs are a useful abstraction of image content. Not only can graphs represent details about individual objects in a scene but they can capture the interactions between pairs of objects. We present a method for training a convolutional neural network such that it takes in an input image and produces a full graph definition. This is done end-to-end in a single stage with the use of associative embeddings. The network learns to simultaneously identify all of the elements that make up a graph and piece them together. We benchmark on the Visual Genome dataset, and demonstrate state-of-the-art performance on the challenging task of scene graph generation.
Tasks	Graph Generation, Scene Graph Generation
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07365v2
PDF	http://arxiv.org/pdf/1706.07365v2.pdf
PWC	https://paperswithcode.com/paper/pixels-to-graphs-by-associative-embedding
Repo	https://github.com/roytseng-tw/px2graph_lab
Framework	tf

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs


Title	Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
Authors	Loic Landrieu, Martin Simonovsky
Abstract	We propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of large-scale point clouds of millions of points. We argue that the organization of 3D point clouds can be efficiently captured by a structure called superpoint graph (SPG), derived from a partition of the scanned scene into geometrically homogeneous elements. SPGs offer a compact yet rich representation of contextual relationships between object parts, which is then exploited by a graph convolutional network. Our framework sets a new state of the art for segmenting outdoor LiDAR scans (+11.9 and +8.8 mIoU points for both Semantic3D test sets), as well as indoor scans (+12.4 mIoU points for the S3DIS dataset).
Tasks	Semantic Segmentation
Published	2017-11-27
URL	http://arxiv.org/abs/1711.09869v2
PDF	http://arxiv.org/pdf/1711.09869v2.pdf
PWC	https://paperswithcode.com/paper/large-scale-point-cloud-semantic-segmentation
Repo	https://github.com/loicland/superpoint_graph
Framework	pytorch

Continuous DR-submodular Maximization: Structure and Algorithms


Title	Continuous DR-submodular Maximization: Structure and Algorithms
Authors	An Bian, Kfir Y. Levy, Andreas Krause, Joachim M. Buhmann
Abstract	DR-submodular continuous functions are important objectives with wide real-world applications spanning MAP inference in determinantal point processes (DPPs), and mean-field inference for probabilistic submodular models, amongst others. DR-submodularity captures a subclass of non-convex functions that enables both exact minimization and approximate maximization in polynomial time. In this work we study the problem of maximizing non-monotone DR-submodular continuous functions under general down-closed convex constraints. We start by investigating geometric properties that underlie such objectives, e.g., a strong relation between (approximately) stationary points and global optimum is proved. These properties are then used to devise two optimization algorithms with provable guarantees. Concretely, we first devise a “two-phase” algorithm with $1/4$ approximation guarantee. This algorithm allows the use of existing methods for finding (approximately) stationary points as a subroutine, thus, harnessing recent progress in non-convex optimization. Then we present a non-monotone Frank-Wolfe variant with $1/e$ approximation guarantee and sublinear convergence rate. Finally, we extend our approach to a broader class of generalized DR-submodular continuous functions, which captures a wider spectrum of applications. Our theoretical findings are validated on synthetic and real-world problem instances.
Tasks	Point Processes
Published	2017-11-04
URL	https://arxiv.org/abs/1711.02515v4
PDF	https://arxiv.org/pdf/1711.02515v4.pdf
PWC	https://paperswithcode.com/paper/continuous-dr-submodular-maximization
Repo	https://github.com/bianan/non-monotone-dr-submodular
Framework	none

Distributed deep learning on edge-devices: feasibility via adaptive compression


Title	Distributed deep learning on edge-devices: feasibility via adaptive compression
Authors	Corentin Hardy, Erwan Le Merrer, Bruno Sericola
Abstract	A large portion of data mining and analytic services use modern machine learning techniques, such as deep learning. The state-of-the-art results by deep learning come at the price of an intensive use of computing resources. The leading frameworks (e.g., TensorFlow) are executed on GPUs or on high-end servers in datacenters. On the other end, there is a proliferation of personal devices with possibly free CPU cycles; this can enable services to run in users’ homes, embedding machine learning operations. In this paper, we ask the following question: Is distributed deep learning computation on WAN connected devices feasible, in spite of the traffic caused by learning tasks? We show that such a setup rises some important challenges, most notably the ingress traffic that the servers hosting the up-to-date model have to sustain. In order to reduce this stress, we propose adaComp, a novel algorithm for compressing worker updates to the model on the server. Applicable to stochastic gradient descent based approaches, it combines efficient gradient selection and learning rate modulation. We then experiment and measure the impact of compression, device heterogeneity and reliability on the accuracy of learned models, with an emulator platform that embeds TensorFlow into Linux containers. We report a reduction of the total amount of data sent by workers to the server by two order of magnitude (e.g., 191-fold reduction for a convolutional network on the MNIST dataset), when compared to a standard asynchronous stochastic gradient descent, while preserving model accuracy.
Tasks
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04683v2
PDF	http://arxiv.org/pdf/1702.04683v2.pdf
PWC	https://paperswithcode.com/paper/distributed-deep-learning-on-edge-devices
Repo	https://github.com/Hardy-c/AdaComp
Framework	tf

Fast and Accurate Entity Recognition with Iterated Dilated Convolutions


Title	Fast and Accurate Entity Recognition with Iterated Dilated Convolutions
Authors	Emma Strubell, Patrick Verga, David Belanger, Andrew McCallum
Abstract	Today when many practitioners run basic NLP on the entire web and large-volume traffic, faster methods are paramount to saving time and energy costs. Recent advances in GPU hardware have led to the emergence of bi-directional LSTMs as a standard method for obtaining per-token vector representations serving as input to labeling tasks such as NER (often followed by prediction in a linear-chain CRF). Though expressive and accurate, these models fail to fully exploit GPU parallelism, limiting their computational efficiency. This paper proposes a faster alternative to Bi-LSTMs for NER: Iterated Dilated Convolutional Neural Networks (ID-CNNs), which have better capacity than traditional CNNs for large context and structured prediction. Unlike LSTMs whose sequential processing on sentences of length N requires O(N) time even in the face of parallelism, ID-CNNs permit fixed-depth convolutions to run in parallel across entire documents. We describe a distinct combination of network structure, parameter sharing and training procedures that enable dramatic 14-20x test-time speedups while retaining accuracy comparable to the Bi-LSTM-CRF. Moreover, ID-CNNs trained to aggregate context from the entire document are even more accurate while maintaining 8x faster test time speeds.
Tasks	Named Entity Recognition, Structured Prediction
Published	2017-02-07
URL	http://arxiv.org/abs/1702.02098v3
PDF	http://arxiv.org/pdf/1702.02098v3.pdf
PWC	https://paperswithcode.com/paper/fast-and-accurate-entity-recognition-with
Repo	https://github.com/zjuym/chinese_cws_ner
Framework	tf