Paper Group ANR 153
Learning Heuristics over Large Graphs via Deep Reinforcement Learning. Optimal translational-rotational invariant dictionaries for images. Generative Model for Zero-Shot Sketch-Based Image Retrieval. Life is Random, Time is Not: Markov Decision Processes with Window Objectives. Energy Demand Prediction with Federated Learning for Electric Vehicle N …
Learning Heuristics over Large Graphs via Deep Reinforcement Learning
| Title | Learning Heuristics over Large Graphs via Deep Reinforcement Learning |
| Authors | Akash Mittal, Anuj Dhawan, Sahil Manchanda, Sourav Medya, Sayan Ranu, Ambuj Singh |
| Abstract | Combinatorial optimization problems on graphs are routinely solved in various domains. Recently, it has been shown that heuristics for solving combinatorial problems can be learned using a machine learning-based approach. While existing techniques have primarily focussed on obtaining high-quality solutions, the aspect of scalability to billion-sized graphs has not been adequately addressed. In this paper, we propose a deep reinforcement learning framework called GCOMB to learn algorithms that can solve combinatorial problems over graphs at scale. Besides considering the traditional NP-hard combinatorial problems, we apply our framework to the popular and challenging data mining problem of Influence Maximization. GCOMB utilizes Graph Convolutional Network (GCN) to generate node embeddings that predict potential solution nodes. These embeddings are next fed to a Q-learning framework, which learns the combinatorial nature of the problem and predicts the final solution set. Through extensive evaluation on several synthetic and billion-sized real networks, we establish that GCOMB is more than 100 times faster than the state of the art while retaining the same quality of the solution sets. |
| Tasks | Combinatorial Optimization, Q-Learning |
| Published | 2019-03-08 |
| URL | https://arxiv.org/abs/1903.03332v2 |
| https://arxiv.org/pdf/1903.03332v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-heuristics-over-large-graphs-via |
| Repo | |
| Framework | |
Optimal translational-rotational invariant dictionaries for images
| Title | Optimal translational-rotational invariant dictionaries for images |
| Authors | Davide Barbieri, Carlos Cabrelli, Eugenio Hernández, Ursula Molter |
| Abstract | We provide the construction of a set of square matrices whose translates and rotates provide a Parseval frame that is optimal for approximating a given dataset of images. Our approach is based on abstract harmonic analysis techniques. Optimality is considered with respect to the quadratic error of approximation of the images in the dataset with their projection onto a linear subspace that is invariant under translations and rotations. In addition, we provide an elementary and fully self-contained proof of optimality, and the numerical results from datasets of natural images. |
| Tasks | |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01887v1 |
| https://arxiv.org/pdf/1909.01887v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-translational-rotational-invariant |
| Repo | |
| Framework | |
Generative Model for Zero-Shot Sketch-Based Image Retrieval
| Title | Generative Model for Zero-Shot Sketch-Based Image Retrieval |
| Authors | Vinay Kumar Verma, Aakansha Mishra, Ashish Mishra, Piyush Rai |
| Abstract | We present a probabilistic model for Sketch-Based Image Retrieval (SBIR) where, at retrieval time, we are given sketches from novel classes, that were not present at training time. Existing SBIR methods, most of which rely on learning class-wise correspondences between sketches and images, typically work well only for previously seen sketch classes, and result in poor retrieval performance on novel classes. To address this, we propose a generative model that learns to generate images, conditioned on a given novel class sketch. This enables us to reduce the SBIR problem to a standard image-to-image search problem. Our model is based on an inverse auto-regressive flow based variational autoencoder, with a feedback mechanism to ensure robust image generation. We evaluate our model on two very challenging datasets, Sketchy, and TU Berlin, with novel train-test split. The proposed approach significantly outperforms various baselines on both the datasets. |
| Tasks | Image Generation, Image Retrieval, Sketch-Based Image Retrieval |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08542v1 |
| http://arxiv.org/pdf/1904.08542v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-model-for-zero-shot-sketch-based |
| Repo | |
| Framework | |
Life is Random, Time is Not: Markov Decision Processes with Window Objectives
| Title | Life is Random, Time is Not: Markov Decision Processes with Window Objectives |
| Authors | Thomas Brihaye, Florent Delgrange, Youssouf Oualhadj, Mickael Randour |
| Abstract | The window mechanism was introduced by Chatterjee et al. [1] to strengthen classical game objectives with time bounds. It permits to synthesize system controllers that exhibit acceptable behaviors within a configurable time frame, all along their infinite execution, in contrast to the traditional objectives that only require correctness of behaviors in the limit. The window concept has proved its interest in a variety of two-player zero-sum games, thanks to the ability to reason about such time bounds in system specifications, but also the increased tractability that it usually yields. In this work, we extend the window framework to stochastic environments by considering the fundamental threshold probability problem in Markov decision processes for window objectives. That is, given such an objective, we want to synthesize strategies that guarantee satisfying runs with a given probability. We solve this problem for the usual variants of window objectives, where either the time frame is set as a parameter, or we ask if such a time frame exists. We develop a generic approach for window-based objectives and instantiate it for the classical mean-payoff and parity objectives, already considered in games. Our work paves the way to a wide use of the window mechanism in stochastic models. [1] Krishnendu Chatterjee, Laurent Doyen, Mickael Randour, and Jean-Fran\c{c}ois Raskin. Looking at mean-payoff and total-payoff through windows. Inf. Comput., 242:25-52, 2015. |
| Tasks | |
| Published | 2019-01-11 |
| URL | https://arxiv.org/abs/1901.03571v3 |
| https://arxiv.org/pdf/1901.03571v3.pdf | |
| PWC | https://paperswithcode.com/paper/life-is-random-time-is-not-markov-decision |
| Repo | |
| Framework | |
Energy Demand Prediction with Federated Learning for Electric Vehicle Networks
| Title | Energy Demand Prediction with Federated Learning for Electric Vehicle Networks |
| Authors | Yuris Mulya Saputra, Dinh Thai Hoang, Diep N. Nguyen, Eryk Dutkiewicz, Markus Dominik Mueck, Srikathyayani Srikanteswara |
| Abstract | In this paper, we propose novel approaches using state-of-the-art machine learning techniques, aiming at predicting energy demand for electric vehicle (EV) networks. These methods can learn and find the correlation of complex hidden features to improve the prediction accuracy. First, we propose an energy demand learning (EDL)-based prediction solution in which a charging station provider (CSP) gathers information from all charging stations (CSs) and then performs the EDL algorithm to predict the energy demand for the considered area. However, this approach requires frequent data sharing between the CSs and the CSP, thereby driving communication overhead and privacy issues for the EVs and CSs. To address this problem, we propose a federated energy demand learning (FEDL) approach which allows the CSs sharing their information without revealing real datasets. Specifically, the CSs only need to send their trained models to the CSP for processing. In this case, we can significantly reduce the communication overhead and effectively protect data privacy for the EV users. To further improve the effectiveness of the FEDL, we then introduce a novel clustering-based EDL approach for EV networks by grouping the CSs into clusters before applying the EDL algorithms. Through experimental results, we show that our proposed approaches can improve the accuracy of energy demand prediction up to 24.63% and decrease communication overhead by 83.4% compared with other baseline machine learning algorithms. |
| Tasks | |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.00907v1 |
| https://arxiv.org/pdf/1909.00907v1.pdf | |
| PWC | https://paperswithcode.com/paper/energy-demand-prediction-with-federated |
| Repo | |
| Framework | |
Equilibrium Characterization for Data Acquisition Games
| Title | Equilibrium Characterization for Data Acquisition Games |
| Authors | Jinshuo Dong, Hadi Elzayn, Shahin Jabbari, Michael Kearns, Zachary Schutzman |
| Abstract | We study a game between two firms in which each provide a service based on machine learning. The firms are presented with the opportunity to purchase a new corpus of data, which will allow them to potentially improve the quality of their products. The firms can decide whether or not they want to buy the data, as well as which learning model to build with that data. We demonstrate a reduction from this potentially complicated action space to a one-shot, two-action game in which each firm only decides whether or not to buy the data. The game admits several regimes which depend on the relative strength of the two firms at the outset and the price at which the data is being offered. We analyze the game’s Nash equilibria in all parameter regimes and demonstrate that, in expectation, the outcome of the game is that the initially stronger firm’s market position weakens whereas the initially weaker firm’s market position becomes stronger. Finally, we consider the perspective of the users of the service and demonstrate that the expected outcome at equilibrium is not the one which maximizes the welfare of the consumers. |
| Tasks | |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.08909v2 |
| https://arxiv.org/pdf/1905.08909v2.pdf | |
| PWC | https://paperswithcode.com/paper/equilibrium-characterization-for-data |
| Repo | |
| Framework | |
Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
| Title | Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding |
| Authors | Junyi Li, Wayne Xin Zhao, Ji-Rong Wen, Yang Song |
| Abstract | Generating long and informative review text is a challenging natural language generation task. Previous work focuses on word-level generation, neglecting the importance of topical and syntactic characteristics from natural languages. In this paper, we propose a novel review generation model by characterizing an elaborately designed aspect-aware coarse-to-fine generation process. First, we model the aspect transitions to capture the overall content flow. Then, to generate a sentence, an aspect-aware sketch will be predicted using an aspect-aware decoder. Finally, another decoder fills in the semantic slots by generating corresponding words. Our approach is able to jointly utilize aspect semantics, syntactic sketch, and context information. Extensive experiments results have demonstrated the effectiveness of the proposed model. |
| Tasks | Text Generation |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.05667v1 |
| https://arxiv.org/pdf/1906.05667v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-long-and-informative-reviews-with |
| Repo | |
| Framework | |
Fast Hyperparameter Tuning using Bayesian Optimization with Directional Derivatives
| Title | Fast Hyperparameter Tuning using Bayesian Optimization with Directional Derivatives |
| Authors | Tinu Theckel Joy, Santu Rana, Sunil Gupta, Svetha Venkatesh |
| Abstract | In this paper we develop a Bayesian optimization based hyperparameter tuning framework inspired by statistical learning theory for classifiers. We utilize two key facts from PAC learning theory; the generalization bound will be higher for a small subset of data compared to the whole, and the highest accuracy for a small subset of data can be achieved with a simple model. We initially tune the hyperparameters on a small subset of training data using Bayesian optimization. While tuning the hyperparameters on the whole training data, we leverage the insights from the learning theory to seek more complex models. We realize this by using directional derivative signs strategically placed in the hyperparameter search space to seek a more complex model than the one obtained with small data. We demonstrate the performance of our method on the tasks of tuning the hyperparameters of several machine learning algorithms. |
| Tasks | |
| Published | 2019-02-06 |
| URL | http://arxiv.org/abs/1902.02416v1 |
| http://arxiv.org/pdf/1902.02416v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-hyperparameter-tuning-using-bayesian |
| Repo | |
| Framework | |
Can a Humanoid Robot be part of the Organizational Workforce? A User Study Leveraging Sentiment Analysis
| Title | Can a Humanoid Robot be part of the Organizational Workforce? A User Study Leveraging Sentiment Analysis |
| Authors | Nidhi Mishra, Manoj Ramanathan, Ranjan Satapathy, Erik Cambria, Nadia Magnenat-Thalmann |
| Abstract | Hiring robots for the workplaces is a challenging task as robots have to cater to customer demands, follow organizational protocols and behave with social etiquette. In this study, we propose to have a humanoid social robot, Nadine, as a customer service agent in an open social work environment. The objective of this study is to analyze the effects of humanoid robots on customers at work environment, and see if it can handle social scenarios. We propose to evaluate these objectives through two modes, namely, survey questionnaire and customer feedback. We also propose a novel approach to analyze customer feedback data (text) using sentic computing methods. Specifically, we employ aspect extraction and sentiment analysis to analyze the data. From our framework, we detect sentiment associated to the aspects that mainly concerned the customers during their interaction. This allows us to understand customers expectations and current limitations of robots as employees. |
| Tasks | Aspect Extraction, Sentiment Analysis |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.08937v2 |
| https://arxiv.org/pdf/1905.08937v2.pdf | |
| PWC | https://paperswithcode.com/paper/can-a-humanoid-robot-be-part-of |
| Repo | |
| Framework | |
Proactive Optimization with Unsupervised Learning
| Title | Proactive Optimization with Unsupervised Learning |
| Authors | Jiajun Wu, Chengjian Sun, Chenyang Yang |
| Abstract | Proactive resource allocation, say proactive caching at wireless edge, has shown promising gain in boosting network performance and improving user experience, by leveraging big data and machine learning. Earlier research efforts focus on optimizing proactive policies under the assumption that the future knowledge required for optimization is perfectly known. Recently, various machine learning techniques are proposed to predict the required knowledge such as file popularity, which is treated as the true value for the optimization. In this paper, we introduce a \emph{proactive optimization} framework for optimizing proactive resource allocation, where the future knowledge is implicitly predicted from historical observations by the optimization. To this end, we formulate a {proactive optimization} problem by taking proactive caching and bandwidth allocation as an example, where the objective function is the conditional expectation of successful offloading probability taken over the unknown popularity given the historically observed popularity. To solve such a problem that depends on the conditional distribution of future information given current and past information, we transform the problem equivalently to a problem depending on the joint distribution of future and historical popularity. Then, we resort to stochastic optimization to learn the joint distribution and resort to unsupervised learning with neural networks to learn the optimal policy. The neural networks can be trained off-line, or in an on-line manner to adapt to the dynamic environment. Simulation results using a real dataset validate that the proposed framework can indeed predict the file popularity implicitly by optimization. |
| Tasks | Stochastic Optimization |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13446v2 |
| https://arxiv.org/pdf/1910.13446v2.pdf | |
| PWC | https://paperswithcode.com/paper/proactive-optimization-with-unsupervised |
| Repo | |
| Framework | |
ALCNN: Attention-based Model for Fine-grained Demand Inference of Dock-less Shared Bike in New Cities
| Title | ALCNN: Attention-based Model for Fine-grained Demand Inference of Dock-less Shared Bike in New Cities |
| Authors | Chang Liu, Yanan Xu, Yanmin Zhu |
| Abstract | In recent years, dock-less shared bikes have been widely spread across many cities in China and facilitate people’s lives. However, at the same time, it also raises many problems about dock-less shared bike management due to the mismatching between demands and real distribution of bikes. Before deploying dock-less shared bikes in a city, companies need to make a plan for dispatching bikes from places having excessive bikes to locations with high demands for providing better services. In this paper, we study the problem of inferring fine-grained bike demands anywhere in a new city before the deployment of bikes. This problem is challenging because new city lacks training data and bike demands vary by both places and time. To solve the problem, we provide various methods to extract discriminative features from multi-source geographic data, such as POI, road networks and nighttime light, for each place. We utilize correlation Principle Component Analysis (coPCA) to deal with extracted features of both old city and new city to realize distribution adaption. Then, we adopt a discrete wavelet transform (DWT) based model to mine daily patterns for each place from fine-grained bike demand. We propose an attention based local CNN model, \textbf{ALCNN}, to infer the daily patterns with latent features from coPCA with multiple CNNs for modeling the influence of neighbor places. In addition, ALCNN merges latent features from multiple CNNs and can select a suitable size of influenced regions. The extensive experiments on real-life datasets show that the proposed approach outperforms competitive methods. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11760v1 |
| https://arxiv.org/pdf/1909.11760v1.pdf | |
| PWC | https://paperswithcode.com/paper/alcnn-attention-based-model-for-fine-grained |
| Repo | |
| Framework | |
Efficient Circle-Based Camera Pose Tracking Free of PnP
| Title | Efficient Circle-Based Camera Pose Tracking Free of PnP |
| Authors | Fulin Tang, Yihong Wu |
| Abstract | Camera pose tracking attracts much interest both from academic and industrial communities, of which the methods based on planar markers are easy to be implemented. However, most of the existing methods need to identify multiple points in the marker images for matching to space points. Then, PnP and RANSAC are used to compute the camera pose. If cameras move fast or are far away from markers, matching is easy to generate errors and even RANSAC cannot remove incorrect matching. Then, the result by PnP cannot have good performance. To solve this problem, we design circular markers and represent 6D camera pose analytically and unifiedly as very concise forms from each of the marker by projective invariance. Afterwards, the pose is further optimized by a proposed nonlinear cost function based on a polar-n-direction geometric distance. The method is from imaged circle edges and without PnP/RANSAC, making pose tracking robust and accurate. Experimental results show that the proposed method outperforms the state of the arts in terms of noise, blur, and distance from camera to marker. Simultaneously, it can still run at about 100 FPS on a consumer computer with only CPU. |
| Tasks | Pose Tracking |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10219v1 |
| https://arxiv.org/pdf/1907.10219v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-circle-based-camera-pose-tracking |
| Repo | |
| Framework | |
FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
| Title | FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks |
| Authors | Jiabin Zhang, Zheng Zhu, Wei Zou, Peng Li, Yanwei Li, Hu Su, Guan Huang |
| Abstract | Both accuracy and efficiency are significant for pose estimation and tracking in videos. State-of-the-art performance is dominated by two-stages top-down methods. Despite the leading results, these methods are impractical for real-world applications due to their separated architectures and complicated calculation. This paper addresses the task of articulated multi-person pose estimation and tracking towards real-time speed. An end-to-end multi-task network (MTN) is designed to perform human detection, pose estimation, and person re-identification (Re-ID) tasks simultaneously. To alleviate the performance bottleneck caused by scale variation problem, a paradigm which exploits scale-normalized image and feature pyramids (SIFP) is proposed to boost both performance and speed. Given the results of MTN, we adopt an occlusion-aware Re-ID feature strategy in the pose tracking module, where pose information is utilized to infer the occlusion state to make better use of Re-ID feature. In experiments, we demonstrate that the pose estimation and tracking performance improves steadily utilizing SIFP through different backbones. Using ResNet-18 and ResNet-50 as backbones, the overall pose tracking framework achieves competitive performance with 29.4 FPS and 12.2 FPS, respectively. Additionally, occlusion-aware Re-ID feature decreases the identification switches by 37% in the pose tracking process. |
| Tasks | Human Detection, Multi-Person Pose Estimation, Multi-Person Pose Estimation and Tracking, Person Re-Identification, Pose Estimation, Pose Tracking |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05593v1 |
| https://arxiv.org/pdf/1908.05593v1.pdf | |
| PWC | https://paperswithcode.com/paper/fastpose-towards-real-time-pose-estimation |
| Repo | |
| Framework | |
Large-scale mammography CAD with Deformable Conv-Nets
| Title | Large-scale mammography CAD with Deformable Conv-Nets |
| Authors | Stephen Morrell, Zbigniew Wojna, Can Son Khoo, Sebastien Ourselin, Juan Eugenio Iglesias |
| Abstract | State-of-the-art deep learning methods for image processing are evolving into increasingly complex meta-architectures with a growing number of modules. Among them, region-based fully convolutional networks (R-FCN) and deformable convolutional nets (DCN) can improve CAD for mammography: R-FCN optimizes for speed and low consumption of memory, which is crucial for processing the high resolutions of to 50 micrometers used by radiologists. Deformable convolution and pooling can model a wide range of mammographic findings of different morphology and scales, thanks to their versatility. In this study, we present a neural net architecture based on R-FCN / DCN, that we have adapted from the natural image domain to suit mammograms – particularly their larger image size – without compromising resolution. We trained the network on a large, recently released dataset (Optimam) including 6,500 cancerous mammograms. By combining our modern architecture with such a rich dataset, we achieved an area under the ROC curve of 0.879 for breast-wise detection in the DREAMS challenge (130,000 withheld images), which surpassed all other submissions in the competitive phase. |
| Tasks | |
| Published | 2019-02-19 |
| URL | http://arxiv.org/abs/1902.07323v1 |
| http://arxiv.org/pdf/1902.07323v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-mammography-cad-with-deformable |
| Repo | |
| Framework | |
Adaptive Sampling Quasi-Newton Methods for Derivative-Free Stochastic Optimization
| Title | Adaptive Sampling Quasi-Newton Methods for Derivative-Free Stochastic Optimization |
| Authors | Raghu Bollapragada, Stefan M. Wild |
| Abstract | We consider stochastic zero-order optimization problems, which arise in settings from simulation optimization to reinforcement learning. We propose an adaptive sampling quasi-Newton method where we estimate the gradients of a stochastic function using finite differences within a common random number framework. We employ modified versions of a norm test and an inner product quasi-Newton test to control the sample sizes used in the stochastic approximations. We provide preliminary numerical experiments to illustrate potential performance benefits of the proposed method. |
| Tasks | Stochastic Optimization |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13516v1 |
| https://arxiv.org/pdf/1910.13516v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-sampling-quasi-newton-methods-for |
| Repo | |
| Framework | |
