Paper Group ANR 206
ExEm: Expert Embedding using dominating set theory with deep learning approaches. Classifying Images with Few Spikes per Neuron. Image Inpainting by Multiscale Spline Interpolation. Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach. Robust Q-learning. Disentangling Adaptive Gradient Methods from Le …
ExEm: Expert Embedding using dominating set theory with deep learning approaches
| Title | ExEm: Expert Embedding using dominating set theory with deep learning approaches |
| Authors | N. Nikzad-Khasmakhi, M. A. Balafar, M. Reza Feizi-Derakhshi, Cina Motamed |
| Abstract | A collaborative network is a social network that is comprised of experts who cooperate with each other to fulfill a special goal. Analyzing the graph of this network yields meaningful information about the expertise of these experts and their subject areas. To perform the analysis, graph embedding techniques have emerged as a promising tool. Graph embedding attempts to represent graph nodes as low-dimensional vectors. In this paper, we propose a graph embedding method, called ExEm, which using dominating-set theory and deep learning approaches. In the proposed method, the dominating set theory is applied to the collaborative network and dominating nodes of this network are found. After that, a set of random walks is created which starts from dominating nodes (experts). The main condition for constricting these random walks is the existence of another dominating node. After making the walks that satisfy the stated conditions, they are stored as a sequence in a corpus. In the next step, the corpus is fed to the SKIP-GRAM neural network model. Word2vec, fastText and their combination are employed to train the neural network of the SKIP-GRAM model. Finally, the result is the low dimensional vectors of experts, called expert embeddings. Expert embeddings can be used for various purposes including accurately modeling experts’ expertise or computing experts’ scores in expert recommendation systems. Hence, we also introduce a novel strategy to calculate experts’ scores by using the extracted expert embedding vectors. The effectiveness of ExEm is validated through assessing its performance on multi-label classification, link prediction, and recommendation tasks. We conduct extensive experiments on common datasets. Moreover in this study, we present data related to a co-author network formed by crawling the vast author profiles from Scopus. |
| Tasks | Graph Embedding, Link Prediction, Multi-Label Classification, Recommendation Systems |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.08503v1 |
| https://arxiv.org/pdf/2001.08503v1.pdf | |
| PWC | https://paperswithcode.com/paper/exem-expert-embedding-using-dominating-set |
| Repo | |
| Framework | |
Classifying Images with Few Spikes per Neuron
| Title | Classifying Images with Few Spikes per Neuron |
| Authors | Christoph Stöckl, Wolfgang Maass |
| Abstract | Spiking neural networks (SNNs) promise to provide AI implementations with a drastically reduced energy budget in comparison with standard artificial neural networks (ANNs). Besides recurrent SNN modules that can be efficiently trained on-chip, many AI applications require the use of feedforward convolutional neural networks (CNNs) as preprocessors for visual or other sensory inputs. The standard solution has been to train a CNN consisting of non-spiking neurons, typically using the rectified linear ReLU function as activation function, and then to translate these CNNs with ReLU neurons via rate coding into SNNs. However this produces SNNs with long latency and small throughput, since the number of spikes that a neuron has to emit is on the order of the number N of output values of the corresponding CNN gate which subsequent layers need to be able to distinguish. We introduce a new ANN-SNN conversion - called FS-conversion - that needs only log N many time steps for that, which is optimal from the perspective of information theory. This can be achieved with a simple variation of the spiking neuron model that has no membrane leak but an exponentially decreasing firing threshold. We show that for the classification of images from ImageNet and CIFAR10 this new conversion reduces latency and drastically increases the throughput compared with rate-based conversion, while achieving almost the same classification performance as the ANN. |
| Tasks | |
| Published | 2020-01-31 |
| URL | https://arxiv.org/abs/2002.00860v1 |
| https://arxiv.org/pdf/2002.00860v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-images-with-few-spikes-per-neuron |
| Repo | |
| Framework | |
Image Inpainting by Multiscale Spline Interpolation
| Title | Image Inpainting by Multiscale Spline Interpolation |
| Authors | Ghazale Ghorbanzade, Zahra Nabizadeh, Nader Karimi, Shadrokh Samavi |
| Abstract | Recovering the missing regions of an image is a task that is called image inpainting. Depending on the shape of missing areas, different methods are presented in the literature. One of the challenges of this problem is extracting features that lead to better results. Experimental results show that both global and local features are useful for this purpose. In this paper, we propose a multi-scale image inpainting method that utilizes both local and global features. The first step of this method is to determine how many scales we need to use, which depends on the width of the lines in the map of the missing region. Then we apply adaptive image inpainting to the damaged areas of the image, and the lost pixels are predicted. Each scale is inpainted and the result is resized to the original size. Then a voting process produces the final result. The proposed method is tested on damaged images with scratches and creases. The metric that we use to evaluate our approach is PSNR. On average, we achieved 1.2 dB improvement over some existing inpainting approaches. |
| Tasks | Image Inpainting |
| Published | 2020-01-10 |
| URL | https://arxiv.org/abs/2001.03270v1 |
| https://arxiv.org/pdf/2001.03270v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-inpainting-by-multiscale-spline |
| Repo | |
| Framework | |
Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach
| Title | Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach |
| Authors | Ke Zhang, Meng Li, Zhengchao Zhang, Xi Lin, Fang He |
| Abstract | Multi-vehicle routing problem with soft time windows (MVRPSTW) is an indispensable constituent in urban logistics distribution system. In the last decade, numerous methods for MVRPSTW have sprung up, but most of them are based on heuristic rules which require huge computation time. With the rapid increasing of logistics demand, traditional methods incur the dilemma of computation efficiency. To efficiently solve the problem, we propose a novel reinforcement learning algorithm named Multi-Agent Attention Model in this paper. Specifically, the vehicle routing problem is regarded as a vehicle tour generation process, and an encoder-decoder framework with attention layers is proposed to generate tours of multiple vehicles iteratively. Furthermore, a multi-agent reinforcement learning method with an unsupervised auxiliary network is developed for model training. By evaluated on three synthetic networks with different scale, the results demonstrate that the proposed method consistently outperforms traditional methods with little computation time. In addition, we validate the extensibility of the well-trained model by varying the number of customers and capacity of vehicles. Finally, the impact of parameters settings on the algorithmic performance are investigated. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2020-02-13 |
| URL | https://arxiv.org/abs/2002.05513v1 |
| https://arxiv.org/pdf/2002.05513v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-vehicle-routing-problems-with-soft-time |
| Repo | |
| Framework | |
Robust Q-learning
| Title | Robust Q-learning |
| Authors | Ashkan Ertefaie, James R. McKay, David Oslin, Robert L. Strawderman |
| Abstract | Q-learning is a regression-based approach that is widely used to formalize the development of an optimal dynamic treatment strategy. Finite dimensional working models are typically used to estimate certain nuisance parameters, and misspecification of these working models can result in residual confounding and/or efficiency loss. We propose a robust Q-learning approach which allows estimating such nuisance parameters using data-adaptive techniques. We study the asymptotic behavior of our estimators and provide simulation studies that highlight the need for and usefulness of the proposed method in practice. We use the data from the “Extending Treatment Effectiveness of Naltrexone” multi-stage randomized trial to illustrate our proposed methods. |
| Tasks | Q-Learning |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12427v1 |
| https://arxiv.org/pdf/2003.12427v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-q-learning |
| Repo | |
| Framework | |
Disentangling Adaptive Gradient Methods from Learning Rates
| Title | Disentangling Adaptive Gradient Methods from Learning Rates |
| Authors | Naman Agarwal, Rohan Anil, Elad Hazan, Tomer Koren, Cyril Zhang |
| Abstract | We investigate several confounding factors in the evaluation of optimization algorithms for deep learning. Primarily, we take a deeper look at how adaptive gradient methods interact with the learning rate schedule, a notoriously difficult-to-tune hyperparameter which has dramatic effects on the convergence and generalization of neural network training. We introduce a “grafting” experiment which decouples an update’s magnitude from its direction, finding that many existing beliefs in the literature may have arisen from insufficient isolation of the implicit schedule of step sizes. Alongside this contribution, we present some empirical and theoretical retrospectives on the generalization of adaptive gradient methods, aimed at bringing more clarity to this space. |
| Tasks | |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11803v1 |
| https://arxiv.org/pdf/2002.11803v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangling-adaptive-gradient-methods-from |
| Repo | |
| Framework | |
A Tracking System For Baseball Game Reconstruction
| Title | A Tracking System For Baseball Game Reconstruction |
| Authors | Nina Wiedemann, Carlos Dietrich, Claudio T. Silva |
| Abstract | The baseball game is often seen as many contests that are performed between individuals. The duel between the pitcher and the batter, for example, is considered the engine that drives the sport. The pitchers use a variety of strategies to gain competitive advantage against the batter, who does his best to figure out the ball trajectory and react in time for a hit. In this work, we propose a system that captures the movements of the pitcher, the batter, and the ball in a high level of detail, and discuss several ways how this information may be processed to compute interesting statistics. We demonstrate on a large database of videos that our methods achieve comparable results as previous systems, while operating solely on video material. In addition, state-of-the-art AI techniques are incorporated to augment the amount of information that is made available for players, coaches, teams, and fans. |
| Tasks | |
| Published | 2020-03-08 |
| URL | https://arxiv.org/abs/2003.03856v1 |
| https://arxiv.org/pdf/2003.03856v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-tracking-system-for-baseball-game |
| Repo | |
| Framework | |
Multipurpose Intelligent Process Automation via Conversational Assistant
| Title | Multipurpose Intelligent Process Automation via Conversational Assistant |
| Authors | Alena Moiseeva, Dietrich Trautmann, Hinrich Schütze |
| Abstract | Intelligent Process Automation (IPA) is an emerging technology with a primary goal to assist the knowledge worker by taking care of repetitive, routine and low-cognitive tasks. Conversational agents that can interact with users in a natural language are potential application for IPA systems. Such intelligent agents can assist the user by answering specific questions and executing routine tasks that are ordinarily performed in a natural language (i.e., customer support). In this work, we tackle a challenge of implementing an IPA conversational assistant in a real-world industrial setting with a lack of structured training data. Our proposed system brings two significant benefits: First, it reduces repetitive and time-consuming activities and, therefore, allows workers to focus on more intelligent processes. Second, by interacting with users, it augments the resources with structured and to some extent labeled training data. We showcase the usage of the latter by re-implementing several components of our system with Transfer Learning (TL) methods. |
| Tasks | Transfer Learning |
| Published | 2020-01-07 |
| URL | https://arxiv.org/abs/2001.02284v1 |
| https://arxiv.org/pdf/2001.02284v1.pdf | |
| PWC | https://paperswithcode.com/paper/multipurpose-intelligent-process-automation |
| Repo | |
| Framework | |
Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
| Title | Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach |
| Authors | Yi Liu, James J. Q. Yu, Jiawen Kang, Dusit Niyato, Shuyu Zhang |
| Abstract | Existing traffic flow forecasting approaches by deep learning models achieve excellent success based on a large volume of datasets gathered by governments and organizations. However, these datasets may contain lots of user’s private data, which is challenging the current prediction approaches as user privacy is calling for the public concern in recent years. Therefore, how to develop accurate traffic prediction while preserving privacy is a significant problem to be solved, and there is a trade-off between these two objectives. To address this challenge, we introduce a privacy-preserving machine learning technique named federated learning and propose a Federated Learning-based Gated Recurrent Unit neural network algorithm (FedGRU) for traffic flow prediction. FedGRU differs from current centralized learning methods and updates universal learning models through a secure parameter aggregation mechanism rather than directly sharing raw data among organizations. In the secure parameter aggregation mechanism, we adopt a Federated Averaging algorithm to reduce the communication overhead during the model parameter transmission process. Furthermore, we design a Joint Announcement Protocol to improve the scalability of FedGRU. We also propose an ensemble clustering-based scheme for traffic flow prediction by grouping the organizations into clusters before applying FedGRU algorithm. Through extensive case studies on a real-world dataset, it is shown that FedGRU’s prediction accuracy is 90.96% higher than the advanced deep learning models, which confirm that FedGRU can achieve accurate and timely traffic prediction without compromising the privacy and security of raw data. |
| Tasks | Traffic Prediction |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08725v1 |
| https://arxiv.org/pdf/2003.08725v1.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-traffic-flow-prediction-a |
| Repo | |
| Framework | |
Machine Learning for Predictive Deployment of UAVs with Multiple Access
| Title | Machine Learning for Predictive Deployment of UAVs with Multiple Access |
| Authors | Linyan Lu, Zhaohui Yang, Mingzhe Chen, Zelin Zang, and Mohammad Shikh-Bahaei |
| Abstract | In this paper, a machine learning based deployment framework of unmanned aerial vehicles (UAVs) is studied. In the considered model, UAVs are deployed as flying base stations (BS) to offload heavy traffic from ground BSs. Due to time-varying traffic distribution, a long short-term memory (LSTM) based prediction algorithm is introduced to predict the future cellular traffic. To predict the user service distribution, a KEG algorithm, which is a joint K-means and expectation maximization (EM) algorithm based on Gaussian mixture model (GMM), is proposed for determining the service area of each UAV. Based on the predicted traffic, the optimal UAV positions are derived and three multi-access techniques are compared so as to minimize the total transmit power. Simulation results show that the proposed method can reduce up to 24% of the total power consumption compared to the conventional method without traffic prediction. Besides, rate splitting multiple access (RSMA) has the lower required transmit power compared to frequency domain multiple access (FDMA) and time domain multiple access (TDMA). |
| Tasks | Traffic Prediction |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.02631v1 |
| https://arxiv.org/pdf/2003.02631v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-predictive-deployment-of |
| Repo | |
| Framework | |
Robot Mindreading and the Problem of Trust
| Title | Robot Mindreading and the Problem of Trust |
| Authors | Andrés Páez |
| Abstract | This paper raises three questions regarding the attribution of beliefs, desires, and intentions to robots. The first one is whether humans in fact engage in robot mindreading. If they do, this raises a second question: does robot mindreading foster trust towards robots? Both of these questions are empirical, and I show that the available evidence is insufficient to answer them. Now, if we assume that the answer to both questions is affirmative, a third and more important question arises: should developers and engineers promote robot mindreading in view of their stated goal of enhancing transparency? My worry here is that by attempting to make robots more mind-readable, they are abandoning the project of understanding automatic decision processes. Features that enhance mind-readability are prone to make the factors that determine automatic decisions even more opaque than they already are. And current strategies to eliminate opacity do not enhance mind-readability. The last part of the paper discusses different ways to analyze this apparent trade-off and suggests that a possible solution must adopt tolerable degrees of opacity that depend on pragmatic factors connected to the level of trust required for the intended uses of the robot. |
| Tasks | |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.01238v1 |
| https://arxiv.org/pdf/2003.01238v1.pdf | |
| PWC | https://paperswithcode.com/paper/robot-mindreading-and-the-problem-of-trust |
| Repo | |
| Framework | |
Inferential Induction: Joint Bayesian Estimation of MDPs and Value Functions
| Title | Inferential Induction: Joint Bayesian Estimation of MDPs and Value Functions |
| Authors | Christos Dimitrakakis, Hannes Eriksson, Emilio Jorge, Divya Grover, Debabrota Basu |
| Abstract | Bayesian reinforcement learning (BRL) offers a decision-theoretic solution to the problem of reinforcement learning. However, typical model-based BRL algorithms have focused either on ma intaining a posterior distribution on models or value functions and combining this with approx imate dynamic programming or tree search. This paper describes a novel backwards induction pri nciple for performing joint Bayesian estimation of models and value functions, from which many new BRL algorithms can be obtained. We demonstrate this idea with algorithms and experiments in discrete state spaces. |
| Tasks | |
| Published | 2020-02-08 |
| URL | https://arxiv.org/abs/2002.03098v1 |
| https://arxiv.org/pdf/2002.03098v1.pdf | |
| PWC | https://paperswithcode.com/paper/inferential-induction-joint-bayesian |
| Repo | |
| Framework | |
Deep Learning based Pedestrian Inertial Navigation: Methods, Dataset and On-Device Inference
| Title | Deep Learning based Pedestrian Inertial Navigation: Methods, Dataset and On-Device Inference |
| Authors | Changhao Chen, Peijun Zhao, Chris Xiaoxuan Lu, Wei Wang, Andrew Markham, Niki Trigoni |
| Abstract | Modern inertial measurements units (IMUs) are small, cheap, energy efficient, and widely employed in smart devices and mobile robots. Exploiting inertial data for accurate and reliable pedestrian navigation supports is a key component for emerging Internet-of-Things applications and services. Recently, there has been a growing interest in applying deep neural networks (DNNs) to motion sensing and location estimation. However, the lack of sufficient labelled data for training and evaluating architecture benchmarks has limited the adoption of DNNs in IMU-based tasks. In this paper, we present and release the Oxford Inertial Odometry Dataset (OxIOD), a first-of-its-kind public dataset for deep learning based inertial navigation research, with fine-grained ground-truth on all sequences. Furthermore, to enable more efficient inference at the edge, we propose a novel lightweight framework to learn and reconstruct pedestrian trajectories from raw IMU data. Extensive experiments show the effectiveness of our dataset and methods in achieving accurate data-driven pedestrian inertial navigation on resource-constrained devices. |
| Tasks | |
| Published | 2020-01-13 |
| URL | https://arxiv.org/abs/2001.04061v1 |
| https://arxiv.org/pdf/2001.04061v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-pedestrian-inertial |
| Repo | |
| Framework | |
Knowledge Federation: Hierarchy and Unification
| Title | Knowledge Federation: Hierarchy and Unification |
| Authors | Hongyu Li, Dan Meng, Xiaolin Li |
| Abstract | With the strengthening of data privacy and security, traditional data centralization for AI faces huge challenges. Moreover, isolated data existing in various industries and institutions is grossly underused and thus retards the advance of AI applications. We propose a possible solution to these problems: knowledge federation. Beyond the concepts of federated learning and secure multi-party computation, we introduce a comprehensive knowledge federation framework, which is a hierarchy with four-level federation. In terms of the occurrence time of federation, knowledge federation can be categorized into information level, model level, cognition level, and knowledge level. To facilitate widespread academic and commercial adoption of this concept, we provide definitions free from ambiguity for the knowledge federation framework. In addition, we clarify the relationship and differentiation between knowledge federation and other related research fields and conclude that knowledge federation is a unified framework for secure multi-party computation and learning. |
| Tasks | |
| Published | 2020-02-05 |
| URL | https://arxiv.org/abs/2002.01647v1 |
| https://arxiv.org/pdf/2002.01647v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-federation-hierarchy-and |
| Repo | |
| Framework | |
Placement Optimization with Deep Reinforcement Learning
| Title | Placement Optimization with Deep Reinforcement Learning |
| Authors | Anna Goldie, Azalia Mirhoseini |
| Abstract | Placement Optimization is an important problem in systems and chip design, which consists of mapping the nodes of a graph onto a limited set of resources to optimize for an objective, subject to constraints. In this paper, we start by motivating reinforcement learning as a solution to the placement problem. We then give an overview of what deep reinforcement learning is. We next formulate the placement problem as a reinforcement learning problem and show how this problem can be solved with policy gradient optimization. Finally, we describe lessons we have learned from training deep reinforcement learning policies across a variety of placement optimization problems. |
| Tasks | |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.08445v1 |
| https://arxiv.org/pdf/2003.08445v1.pdf | |
| PWC | https://paperswithcode.com/paper/placement-optimization-with-deep |
| Repo | |
| Framework | |
