Paper Group ANR 298
Properly-weighted graph Laplacian for semi-supervised learning. Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework. Guided Policy Exploration for Markov Decision Processes using an Uncertainty-Based Value-of-Information Criterion. Analysis of the Effect of Unexpected Outliers in the Classification of Spectroscopy Data. Hiera …
Properly-weighted graph Laplacian for semi-supervised learning
Title | Properly-weighted graph Laplacian for semi-supervised learning |
Authors | Jeff Calder, Dejan Slepcev |
Abstract | The performance of traditional graph Laplacian methods for semi-supervised learning degrades substantially as the ratio of labeled to unlabeled data decreases, due to a degeneracy in the graph Laplacian. Several approaches have been proposed recently to address this, however we show that some of them remain ill-posed in the large-data limit. In this paper, we show a way to correctly set the weights in Laplacian regularization so that the estimator remains well posed and stable in the large-sample limit. We prove that our semi-supervised learning algorithm converges, in the infinite sample size limit, to the smooth solution of a continuum variational problem that attains the labeled values continuously. Our method is fast and easy to implement. |
Tasks | |
Published | 2018-10-10 |
URL | http://arxiv.org/abs/1810.04351v2 |
http://arxiv.org/pdf/1810.04351v2.pdf | |
PWC | https://paperswithcode.com/paper/properly-weighted-graph-laplacian-for-semi |
Repo | |
Framework | |
Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
Title | Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework |
Authors | Jie Chen, Junhui Hou, Lap-Pui Chau |
Abstract | Light field (LF) cameras provide perspective information of scenes by taking directional measurements of the focusing light rays. The raw outputs are usually dark with additive camera noise, which impedes subsequent processing and applications. We propose a novel LF denoising framework based on anisotropic parallax analysis (APA). Two convolutional neural networks are jointly designed for the task: first, the structural parallax synthesis network predicts the parallax details for the entire LF based on a set of anisotropic parallax features. These novel features can efficiently capture the high frequency perspective components of a LF from noisy observations. Second, the view-dependent detail compensation network restores non-Lambertian variation to each LF view by involving view-specific spatial energies. Extensive experiments show that the proposed APA LF denoiser provides a much better denoising performance than state-of-the-art methods in terms of visual quality and in preservation of parallax details. |
Tasks | Denoising |
Published | 2018-05-31 |
URL | http://arxiv.org/abs/1805.12358v2 |
http://arxiv.org/pdf/1805.12358v2.pdf | |
PWC | https://paperswithcode.com/paper/light-field-denoising-via-anisotropic |
Repo | |
Framework | |
Guided Policy Exploration for Markov Decision Processes using an Uncertainty-Based Value-of-Information Criterion
Title | Guided Policy Exploration for Markov Decision Processes using an Uncertainty-Based Value-of-Information Criterion |
Authors | Isaac J. Sledge, Matthew S. Emigh, Jose C. Principe |
Abstract | Reinforcement learning in environments with many action-state pairs is challenging. At issue is the number of episodes needed to thoroughly search the policy space. Most conventional heuristics address this search problem in a stochastic manner. This can leave large portions of the policy space unvisited during the early training stages. In this paper, we propose an uncertainty-based, information-theoretic approach for performing guided stochastic searches that more effectively cover the policy space. Our approach is based on the value of information, a criterion that provides the optimal trade-off between expected costs and the granularity of the search process. The value of information yields a stochastic routine for choosing actions during learning that can explore the policy space in a coarse to fine manner. We augment this criterion with a state-transition uncertainty factor, which guides the search process into previously unexplored regions of the policy space. |
Tasks | |
Published | 2018-02-05 |
URL | http://arxiv.org/abs/1802.01518v1 |
http://arxiv.org/pdf/1802.01518v1.pdf | |
PWC | https://paperswithcode.com/paper/guided-policy-exploration-for-markov-decision |
Repo | |
Framework | |
Analysis of the Effect of Unexpected Outliers in the Classification of Spectroscopy Data
Title | Analysis of the Effect of Unexpected Outliers in the Classification of Spectroscopy Data |
Authors | Frank G. Glavin, Michael G. Madden |
Abstract | Multi-class classification algorithms are very widely used, but we argue that they are not always ideal from a theoretical perspective, because they assume all classes are characterized by the data, whereas in many applications, training data for some classes may be entirely absent, rare, or statistically unrepresentative. We evaluate one-sided classifiers as an alternative, since they assume that only one class (the target) is well characterized. We consider a task of identifying whether a substance contains a chlorinated solvent, based on its chemical spectrum. For this application, it is not really feasible to collect a statistically representative set of outliers, since that group may contain \emph{anything} apart from the target chlorinated solvents. Using a new one-sided classification toolkit, we compare a One-Sided k-NN algorithm with two well-known binary classification algorithms, and conclude that the one-sided classifier is more robust to unexpected outliers. |
Tasks | |
Published | 2018-06-14 |
URL | http://arxiv.org/abs/1806.05455v1 |
http://arxiv.org/pdf/1806.05455v1.pdf | |
PWC | https://paperswithcode.com/paper/analysis-of-the-effect-of-unexpected-outliers |
Repo | |
Framework | |
Hierarchical Modeling and Shrinkage for User Session Length Prediction in Media Streaming
Title | Hierarchical Modeling and Shrinkage for User Session Length Prediction in Media Streaming |
Authors | Antoine Dedieu, Rahul Mazumder, Zhen Zhu, Hossein Vahabi |
Abstract | An important metric of users’ satisfaction and engagement within on-line streaming services is the user session length, i.e. the amount of time they spend on a service continuously without interruption. Being able to predict this value directly benefits the recommendation and ad pacing contexts in music and video streaming services. Recent research has shown that predicting the exact amount of time spent is highly nontrivial due to many external factors for which a user can end a session, and the lack of predictive covariates. Most of the other related literature on duration based user engagement has focused on dwell time for websites, for search and display ads, mainly for post-click satisfaction prediction or ad ranking. In this work we present a novel framework inspired by hierarchical Bayesian modeling to predict, at the moment of login, the amount of time a user will spend in the streaming service. The time spent by a user on a platform depends upon user-specific latent variables which are learned via hierarchical shrinkage. Our framework enjoys theoretical guarantees and naturally incorporates flexible parametric/nonparametric models on the covariates, including models robust to outliers. Our proposal is found to outperform state-of- the-art estimators in terms of efficiency and predictive performance on real world public and private datasets. |
Tasks | |
Published | 2018-03-04 |
URL | http://arxiv.org/abs/1803.01440v2 |
http://arxiv.org/pdf/1803.01440v2.pdf | |
PWC | https://paperswithcode.com/paper/hierarchical-modeling-and-shrinkage-for-user |
Repo | |
Framework | |
Studying Invariances of Trained Convolutional Neural Networks
Title | Studying Invariances of Trained Convolutional Neural Networks |
Authors | Charlotte Bunne, Lukas Rahmann, Thomas Wolf |
Abstract | Convolutional Neural Networks (CNNs) define an exceptionally powerful class of models for image classification, but the theoretical background and the understanding of how invariances to certain transformations are learned is limited. In a large scale screening with images modified by different affine and nonaffine transformations of varying magnitude, we analyzed the behavior of the CNN architectures AlexNet and ResNet. If the magnitude of different transformations does not exceed a class- and transformation dependent threshold, both architectures show invariant behavior. In this work we furthermore introduce a new learnable module, the Invariant Transformer Net, which enables us to learn differentiable parameters for a set of affine transformations. This allows us to extract the space of transformations to which the CNN is invariant and its class prediction robust. |
Tasks | Image Classification |
Published | 2018-03-15 |
URL | http://arxiv.org/abs/1803.05963v1 |
http://arxiv.org/pdf/1803.05963v1.pdf | |
PWC | https://paperswithcode.com/paper/studying-invariances-of-trained-convolutional |
Repo | |
Framework | |
CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis
Title | CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis |
Authors | Mengting Hu, Shiwan Zhao, Li Zhang, Keke Cai, Zhong Su, Renhong Cheng, Xiaowei Shen |
Abstract | Aspect level sentiment classification is a fine-grained sentiment analysis task. To detect the sentiment towards a particular aspect in a sentence, previous studies have developed various attention-based methods for generating aspect-specific sentence representations. However, the attention may inherently introduce noise and downgrade the performance. In this paper, we propose constrained attention networks (CAN), a simple yet effective solution, to regularize the attention for multi-aspect sentiment analysis, which alleviates the drawback of the attention mechanism. Specifically, we introduce orthogonal regularization on multiple aspects and sparse regularization on each single aspect. Experimental results on two public datasets demonstrate the effectiveness of our approach. We further extend our approach to multi-task settings and outperform the state-of-the-art methods. |
Tasks | Sentiment Analysis |
Published | 2018-12-27 |
URL | https://arxiv.org/abs/1812.10735v2 |
https://arxiv.org/pdf/1812.10735v2.pdf | |
PWC | https://paperswithcode.com/paper/can-constrained-attention-networks-for-multi |
Repo | |
Framework | |
Faster Deep Q-learning using Neural Episodic Control
Title | Faster Deep Q-learning using Neural Episodic Control |
Authors | Daichi Nishio, Satoshi Yamane |
Abstract | The research on deep reinforcement learning which estimates Q-value by deep learning has been attracted the interest of researchers recently. In deep reinforcement learning, it is important to efficiently learn the experiences that an agent has collected by exploring environment. We propose NEC2DQN that improves learning speed of a poor sample efficiency algorithm such as DQN by using good one such as NEC at the beginning of learning. We show it is able to learn faster than Double DQN or N-step DQN in the experiments of Pong. |
Tasks | Q-Learning |
Published | 2018-01-06 |
URL | http://arxiv.org/abs/1801.01968v4 |
http://arxiv.org/pdf/1801.01968v4.pdf | |
PWC | https://paperswithcode.com/paper/faster-deep-q-learning-using-neural-episodic |
Repo | |
Framework | |
Inflo: News Categorization and Keyphrase Extraction for Implementation in an Aggregation System
Title | Inflo: News Categorization and Keyphrase Extraction for Implementation in an Aggregation System |
Authors | Pranav A, Nick Sukiennik, Pan Hui |
Abstract | The work herein describes a system for automatic news category and keyphrase labeling, presented in the context of our motivation to improve the speed at which a user can find relevant and interesting content within an aggregation platform. A set of 12 discrete categories were applied to over 500,000 news articles for training a neural network, to be used to facilitate the more in-depth task of extracting the most significant keyphrases. The latter was done using three methods: statistical, graphical and numerical, using the pre-identified category label to improve relevance of extracted phrases. The results are presented in a demo in which the articles are pre-populated via News API, and upon being selected, the category and keyphrase labels will be computed via the methods explained herein. |
Tasks | |
Published | 2018-12-10 |
URL | http://arxiv.org/abs/1812.03781v1 |
http://arxiv.org/pdf/1812.03781v1.pdf | |
PWC | https://paperswithcode.com/paper/inflo-news-categorization-and-keyphrase |
Repo | |
Framework | |
Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition
Title | Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition |
Authors | Xikun Zhang, Chang Xu, Xinmei Tian, Dacheng Tao |
Abstract | This paper investigates body bones from skeleton data for skeleton based action recognition. Body joints, as the direct result of mature pose estimation technologies, are always the key concerns of traditional action recognition methods. However, instead of joints, we humans naturally identify how the human body moves according to shapes, lengths and places of bones, which are more obvious and stable for observation. Hence given graphs generated from skeleton data, we propose to develop convolutions over graph edges that correspond to bones in human skeleton. We describe an edge by integrating its spatial neighboring edges to explore the cooperation between different bones, as well as its temporal neighboring edges to address the consistency of movements in an action. A graph edge convolutional neural network is then designed for skeleton based action recognition. Considering the complementarity between graph node convolution and graph edge convolution, we additionally construct two hybrid neural networks to combine graph node convolutional neural network and graph edge convolutional neural network using shared intermediate layers. Experimental results on Kinetics and NTU-RGB+D datasets demonstrate that our graph edge convolution is effective to capture characteristic of actions and our graph edge convolutional neural network significantly outperforms existing state-of-art skeleton based action recognition methods. Additionally, more performance improvements can be achieved by the hybrid networks. |
Tasks | Pose Estimation, Skeleton Based Action Recognition, Temporal Action Localization |
Published | 2018-05-16 |
URL | http://arxiv.org/abs/1805.06184v2 |
http://arxiv.org/pdf/1805.06184v2.pdf | |
PWC | https://paperswithcode.com/paper/graph-edge-convolutional-neural-networks-for |
Repo | |
Framework | |
Constructing Locally Dense Point Clouds Using OpenSfM and ORB-SLAM2
Title | Constructing Locally Dense Point Clouds Using OpenSfM and ORB-SLAM2 |
Authors | Fouad Amer, Zixu Zhao, Siwei Tang, Wilfredo Torres |
Abstract | This paper aims at finding a method to register two different point clouds constructed by ORB-SLAM2 and OpenSfM. To do this, we post some tags with unique textures in the scene and take videos and photos of that area. Then we take short videos of only the tags to extract their features. By matching the ORB feature of the tags with their corresponding features in the scene, it is then possible to localize the position of these tags both in point clouds constructed by ORB-SLAM2 and OpenSfM. Thus, the best transformation matrix between two point clouds can be calculated, and the two point clouds can be aligned. |
Tasks | |
Published | 2018-04-23 |
URL | http://arxiv.org/abs/1804.08243v1 |
http://arxiv.org/pdf/1804.08243v1.pdf | |
PWC | https://paperswithcode.com/paper/constructing-locally-dense-point-clouds-using |
Repo | |
Framework | |
Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
Title | Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework |
Authors | Yanzhi Wang, Caiwen Ding, Zhe Li, Geng Yuan, Siyu Liao, Xiaolong Ma, Bo Yuan, Xuehai Qian, Jian Tang, Qinru Qiu, Xue Lin |
Abstract | Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and performance for hardware implementations of deep neural networks (DNNs). An algorithm-hardware co-optimization framework is developed, which is applicable to different DNN types, sizes, and application scenarios. The algorithm part adopts the general block-circulant matrices to achieve a fine-grained tradeoff between accuracy and compression ratio. It applies to both fully-connected and convolutional layers and contains a mathematically rigorous proof of the effectiveness of the method. The proposed algorithm reduces computational complexity per layer from O($n^2$) to O($n\log n$) and storage complexity from O($n^2$) to O($n$), both for training and inference. The hardware part consists of highly efficient Field Programmable Gate Array (FPGA)-based implementations using effective reconfiguration, batch processing, deep pipelining, resource re-using, and hierarchical control. Experimental results demonstrate that the proposed framework achieves at least 152X speedup and 71X energy efficiency gain compared with IBM TrueNorth processor under the same test accuracy. It achieves at least 31X energy efficiency gain compared with the reference FPGA-based work. |
Tasks | |
Published | 2018-02-18 |
URL | http://arxiv.org/abs/1802.06402v1 |
http://arxiv.org/pdf/1802.06402v1.pdf | |
PWC | https://paperswithcode.com/paper/towards-ultra-high-performance-and-energy |
Repo | |
Framework | |
On the Minimax Misclassification Ratio of Hypergraph Community Detection
Title | On the Minimax Misclassification Ratio of Hypergraph Community Detection |
Authors | I Chien, Chung-Yi Lin, I-Hsiang Wang |
Abstract | Community detection in hypergraphs is explored. Under a generative hypergraph model called “d-wise hypergraph stochastic block model” (d-hSBM) which naturally extends the Stochastic Block Model from graphs to d-uniform hypergraphs, the asymptotic minimax mismatch ratio is characterized. For proving the achievability, we propose a two-step polynomial time algorithm that achieves the fundamental limit. The first step of the algorithm is a hypergraph spectral clustering method which achieves partial recovery to a certain precision level. The second step is a local refinement method which leverages the underlying probabilistic model along with parameter estimation from the outcome of the first step. To characterize the asymptotic performance of the proposed algorithm, we first derive a sufficient condition for attaining weak consistency in the hypergraph spectral clustering step. Then, under the guarantee of weak consistency in the first step, we upper bound the worst-case risk attained in the local refinement step by an exponentially decaying function of the size of the hypergraph and characterize the decaying rate. For proving the converse, the lower bound of the minimax mismatch ratio is set by finding a smaller parameter space which contains the most dominant error events, inspired by the analysis in the achievability part. It turns out that the minimax mismatch ratio decays exponentially fast to zero as the number of nodes tends to infinity, and the rate function is a weighted combination of several divergence terms, each of which is the Renyi divergence of order 1/2 between two Bernoulli’s. The Bernoulli’s involved in the characterization of the rate function are those governing the random instantiation of hyperedges in d-hSBM. Experimental results on synthetic data validate our theoretical finding that the refinement step is critical in achieving the optimal statistical limit. |
Tasks | Community Detection |
Published | 2018-02-03 |
URL | http://arxiv.org/abs/1802.00926v1 |
http://arxiv.org/pdf/1802.00926v1.pdf | |
PWC | https://paperswithcode.com/paper/on-the-minimax-misclassification-ratio-of |
Repo | |
Framework | |
Functional Generative Design: An Evolutionary Approach to 3D-Printing
Title | Functional Generative Design: An Evolutionary Approach to 3D-Printing |
Authors | Cem C. Tutum, Supawit Chockchowwat, Etienne Vouga, Risto Miikkulainen |
Abstract | Consumer-grade printers are widely available, but their ability to print complex objects is limited. Therefore, new designs need to be discovered that serve the same function, but are printable. A representative such problem is to produce a working, reliable mechanical spring. The proposed methodology for discovering solutions to this problem consists of three components: First, an effective search space is learned through a variational autoencoder (VAE); second, a surrogate model for functional designs is built; and third, a genetic algorithm is used to simultaneously update the hyperparameters of the surrogate and to optimize the designs using the updated surrogate. Using a car-launcher mechanism as a test domain, spring designs were 3D-printed and evaluated to update the surrogate model. Two experiments were then performed: First, the initial set of designs for the surrogate-based optimizer was selected randomly from the training set that was used for training the VAE model, which resulted in an exploitative search behavior. On the other hand, in the second experiment, the initial set was composed of more uniformly selected designs from the same training set and a more explorative search behavior was observed. Both of the experiments showed that the methodology generates interesting, successful, and reliable spring geometries robust to the noise inherent in the 3D printing process. The methodology can be generalized to other functional design problems, thus making consumer-grade 3D printing more versatile. |
Tasks | |
Published | 2018-04-19 |
URL | http://arxiv.org/abs/1804.07284v1 |
http://arxiv.org/pdf/1804.07284v1.pdf | |
PWC | https://paperswithcode.com/paper/functional-generative-design-an-evolutionary |
Repo | |
Framework | |
Low-Latency Video Semantic Segmentation
Title | Low-Latency Video Semantic Segmentation |
Authors | Yule Li, Jianping Shi, Dahua Lin |
Abstract | Recent years have seen remarkable progress in semantic segmentation. Yet, it remains a challenging task to apply segmentation techniques to video-based applications. Specifically, the high throughput of video streams, the sheer cost of running fully convolutional networks, together with the low-latency requirements in many real-world applications, e.g. autonomous driving, present a significant challenge to the design of the video segmentation framework. To tackle this combined challenge, we develop a framework for video semantic segmentation, which incorporates two novel components: (1) a feature propagation module that adaptively fuses features over time via spatially variant convolution, thus reducing the cost of per-frame computation; and (2) an adaptive scheduler that dynamically allocate computation based on accuracy prediction. Both components work together to ensure low latency while maintaining high segmentation quality. On both Cityscapes and CamVid, the proposed framework obtained competitive performance compared to the state of the art, while substantially reducing the latency, from 360 ms to 119 ms. |
Tasks | Autonomous Driving, Semantic Segmentation, Video Semantic Segmentation |
Published | 2018-04-02 |
URL | http://arxiv.org/abs/1804.00389v1 |
http://arxiv.org/pdf/1804.00389v1.pdf | |
PWC | https://paperswithcode.com/paper/low-latency-video-semantic-segmentation |
Repo | |
Framework | |