Paper Group ANR 560
Independent Component Analysis based on multiple data-weighting. Efficient candidate screening under multiple tests and implications for fairness. Unsupervised Features Learning for Sampled Vector Fields. Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning. Adversarial Initialization – when your netw …
Independent Component Analysis based on multiple data-weighting
| Title | Independent Component Analysis based on multiple data-weighting |
| Authors | Andrzej Bedychaj, Przemysław Spurek, Łukasz Struskim, Jacek Tabor |
| Abstract | Independent Component Analysis (ICA) - one of the basic tools in data analysis - aims to find a coordinate system in which the components of the data are independent. In this paper we present Multiple-weighted Independent Component Analysis (MWeICA) algorithm, a new ICA method which is based on approximate diagonalization of weighted covariance matrices. Our idea is based on theoretical result, which says that linear independence of weighted data (for gaussian weights) guarantees independence. Experiments show that MWeICA achieves better results to most state-of-the-art ICA methods, with similar computational time. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1906.00028v1 |
| https://arxiv.org/pdf/1906.00028v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600028 |
| Repo | |
| Framework | |
Efficient candidate screening under multiple tests and implications for fairness
| Title | Efficient candidate screening under multiple tests and implications for fairness |
| Authors | Lee Cohen, Zachary C. Lipton, Yishay Mansour |
| Abstract | When recruiting job candidates, employers rarely observe their underlying skill level directly. Instead, they must administer a series of interviews and/or collate other noisy signals in order to estimate the worker’s skill. Traditional economics papers address screening models where employers access worker skill via a single noisy signal. In this paper, we extend this theoretical analysis to a multi-test setting, considering both Bernoulli and Gaussian models. We analyze the optimal employer policy both when the employer sets a fixed number of tests per candidate and when the employer can set a dynamic policy, assigning further tests adaptively based on results from the previous tests. To start, we characterize the optimal policy when employees constitute a single group, demonstrating some interesting trade-offs. Subsequently, we address the multi-group setting, demonstrating that when the noise levels vary across groups, a fundamental impossibility emerges whereby we cannot administer the same number of tests, subject candidates to the same decision rule, and yet realize the same outcomes in both groups. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11361v1 |
| https://arxiv.org/pdf/1905.11361v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-candidate-screening-under-multiple |
| Repo | |
| Framework | |
Unsupervised Features Learning for Sampled Vector Fields
| Title | Unsupervised Features Learning for Sampled Vector Fields |
| Authors | Mateusz Juda |
| Abstract | In this paper we introduce a new approach to computing hidden features of sampled vector fields. The basic idea is to convert the vector field data to a graph structure and use tools designed for automatic, unsupervised analysis of graphs. Using a few data sets we show that the collected features of the vector fields are correlated with the dynamics known for analytic models which generates the data. In particular the method may be useful in analysis of data sets where the analytic model is poorly understood or not known. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.10023v1 |
| https://arxiv.org/pdf/1911.10023v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-features-learning-for-sampled |
| Repo | |
| Framework | |
Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
| Title | Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning |
| Authors | Shuai Zheng, Zhenfeng Zhu, Xingxing Zhang, Zhizhe Liu, Jian Cheng, Yao Zhao |
| Abstract | Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks. However, most existing algorithms ignore the existence of inherent data distribution and even noises. This may significantly increase the phenomenon of over-fitting and deteriorate the testing accuracy. In this paper, we propose a Distribution-induced Bidirectional Generative Adversarial Network (named DBGAN) for graph representation learning. Instead of the widely used normal distribution assumption, the prior distribution of latent representation in our DBGAN is estimated in a structure-aware way, which implicitly bridges the graph and feature spaces by prototype learning. Thus discriminative and robust representations are generated for all nodes. Furthermore, to improve their generalization ability while preserving representation ability, the sample-level and distribution-level consistency is well balanced via a bidirectional adversarial learning framework. An extensive group of experiments are then carefully designed and presented, demonstrating that our DBGAN obtains remarkably more favorable trade-off between representation and robustness, and meanwhile is dimension-efficient, over currently available alternatives in various tasks. |
| Tasks | Graph Representation Learning, Representation Learning |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01899v2 |
| https://arxiv.org/pdf/1912.01899v2.pdf | |
| PWC | https://paperswithcode.com/paper/distribution-induced-bidirectional-generative |
| Repo | |
| Framework | |
Adversarial Initialization – when your network performs the way I want
| Title | Adversarial Initialization – when your network performs the way I want |
| Authors | Kathrin Grosse, Thomas A. Trost, Marius Mosbach, Michael Backes, Dietrich Klakow |
| Abstract | The increase in computational power and available data has fueled a wide deployment of deep learning in production environments. Despite their successes, deep architectures are still poorly understood and costly to train. We demonstrate in this paper how a simple recipe enables a market player to harm or delay the development of a competing product. Such a threat model is novel and has not been considered so far. We derive the corresponding attacks and show their efficacy both formally and empirically. These attacks only require access to the initial, untrained weights of a network. No knowledge of the problem domain and the data used by the victim is needed. On the initial weights, a mere permutation is sufficient to limit the achieved accuracy to for example 50% on the MNIST dataset or double the needed training time. While we can show straightforward ways to mitigate the attacks, the respective steps are not part of the standard procedure taken by developers so far. |
| Tasks | |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.03020v1 |
| http://arxiv.org/pdf/1902.03020v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-initialization-when-your-network |
| Repo | |
| Framework | |
Duration-of-Stay Storage Assignment under Uncertainty
| Title | Duration-of-Stay Storage Assignment under Uncertainty |
| Authors | Michael Lingzhi Li, Elliott Wolf, Daniel Wintz |
| Abstract | Optimizing storage assignment is a central problem in warehousing. Past literature has shown the superiority of the Duration-of-Stay (DoS) method in assigning pallets, but the methodology requires perfect prior knowledge of DoS for each pallet, which is unknown and uncertain under realistic conditions. The dynamic nature of a warehouse further complicates the validity of synthetic data testing that is often conducted for algorithms. In this paper, in collaboration with a large cold storage company, we release the first publicly available set of warehousing records to facilitate research into this central problem. We introduce a new framework for storage assignment that accounts for uncertainty in warehouses. Then, by utilizing a combination of convolutional and recurrent neural network models, ParallelNet, we show that it is able to predict future shipments well: it achieves up to 29% decrease in MAPE compared to CNN-LSTM on unseen future shipments, and suffers less performance decay over time. The framework is then integrated into a first-of-its-kind Storage Assignment system, which is being piloted in warehouses across the country, with initial results showing up to 19% in labor savings. |
| Tasks | |
| Published | 2019-03-12 |
| URL | https://arxiv.org/abs/1903.05063v3 |
| https://arxiv.org/pdf/1903.05063v3.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-duration-of-stay-storage |
| Repo | |
| Framework | |
Discovering Association with Copula Entropy
| Title | Discovering Association with Copula Entropy |
| Authors | Ma Jian |
| Abstract | Discovering associations is of central importance in scientific practices. Currently, most researches consider only linear association measured by correlation coefficient, which has its theoretical limitations. In this paper, we propose a new method for discovering association with copula entropy – a universal applicable association measure for not only linear cases, but nonlinear cases. The advantage of the method based on copula entropy over traditional method is demonstrated on the NHANES data by discovering more biomedical meaningful associations. |
| Tasks | |
| Published | 2019-07-29 |
| URL | https://arxiv.org/abs/1907.12268v1 |
| https://arxiv.org/pdf/1907.12268v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-association-with-copula-entropy |
| Repo | |
| Framework | |
Enabling Simulation-Based Optimization Through Machine Learning: A Case Study on Antenna Design
| Title | Enabling Simulation-Based Optimization Through Machine Learning: A Case Study on Antenna Design |
| Authors | Paolo Testolina, Mattia Lecci, Mattia Rebato, Alberto Testolin, Jonathan Gambini, Roberto Flamini, Christian Mazzucco, Michele Zorzi |
| Abstract | Complex phenomena are generally modeled with sophisticated simulators that, depending on their accuracy, can be very demanding in terms of computational resources and simulation time. Their time-consuming nature, together with a typically vast parameter space to be explored, make simulation-based optimization often infeasible. In this work, we present a method that enables the optimization of complex systems through Machine Learning (ML) techniques. We show how well-known learning algorithms are able to reliably emulate a complex simulator with a modest dataset obtained from it. The trained emulator is then able to yield values close to the simulated ones in virtually no time. Therefore, it is possible to perform a global numerical optimization over the vast multi-dimensional parameter space, in a fraction of the time that would be required by a simple brute-force search. As a testbed for the proposed methodology, we used a network simulator for next-generation mmWave cellular systems. After simulating several antenna configurations and collecting the resulting network-level statistics, we feed it into our framework. Results show that, even with few data points, extrapolating a continuous model makes it possible to estimate the global optimum configuration almost instantaneously. The very same tool can then be used to achieve any further optimization goal on the same input parameters in negligible time. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11225v1 |
| https://arxiv.org/pdf/1908.11225v1.pdf | |
| PWC | https://paperswithcode.com/paper/enabling-simulation-based-optimization |
| Repo | |
| Framework | |
GraLSP: Graph Neural Networks with Local Structural Patterns
| Title | GraLSP: Graph Neural Networks with Local Structural Patterns |
| Authors | Yilun Jin, Guojie Song, Chuan Shi |
| Abstract | It is not until recently that graph neural networks (GNNs) are adopted to perform graph representation learning, among which, those based on the aggregation of features within the neighborhood of a node achieved great success. However, despite such achievements, GNNs illustrate defects in identifying some common structural patterns which, unfortunately, play significant roles in various network phenomena. In this paper, we propose GraLSP, a GNN framework which explicitly incorporates local structural patterns into the neighborhood aggregation through random anonymous walks. Specifically, we capture local graph structures via random anonymous walks, powerful and flexible tools that represent structural patterns. The walks are then fed into the feature aggregation, where we design various mechanisms to address the impact of structural features, including adaptive receptive radius, attention and amplification. In addition, we design objectives that capture similarities between structures and are optimized jointly with node proximity objectives. With the adequate leverage of structural patterns, our model is able to outperform competitive counterparts in various prediction tasks in multiple datasets. |
| Tasks | Graph Representation Learning, Representation Learning |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07675v2 |
| https://arxiv.org/pdf/1911.07675v2.pdf | |
| PWC | https://paperswithcode.com/paper/gralsp-graph-neural-networks-with-local |
| Repo | |
| Framework | |
Smart Cloud: Scalable Cloud Robotic Architecture for Web-powered Multi-Robot Applications
| Title | Smart Cloud: Scalable Cloud Robotic Architecture for Web-powered Multi-Robot Applications |
| Authors | Manoj Penmetcha, Shyam Sundar Kannan, Byung-Cheol Min |
| Abstract | Robots have inherently limited onboard processing, storage, and power capabilities. Cloud computing resources have the potential to provide significant advantages for robots in many applications. However, to make use of these resources, frameworks must be developed that facilitate robot interactions with cloud services. In this paper, we propose a cloud-based architecture called Smart Cloud that intends to overcome the physical limitations of single- or multi-robot systems through massively parallel computation, provided on demand by cloud services. Smart Cloud is implemented on Amazon Web Services (AWS) and available for robots running on the Robot Operating System (ROS) and on non-ROS systems. Smart Cloud features a first-of-its-kind architecture that incorporates JavaScript-based libraries to run various robotic applications related to machine learning and other methods. This paper presents the architecture and its performance in terms of CPU power usage, latency, and security, and finally validates it for navigation and machine learning applications. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.02927v2 |
| https://arxiv.org/pdf/1912.02927v2.pdf | |
| PWC | https://paperswithcode.com/paper/smart-cloud-scalable-cloud-robotic |
| Repo | |
| Framework | |
AI in the media and creative industries
| Title | AI in the media and creative industries |
| Authors | Giuseppe Amato, Malte Behrmann, Frédéric Bimbot, Baptiste Caramiaux, Fabrizio Falchi, Ander Garcia, Joost Geurts, Jaume Gibert, Guillaume Gravier, Hadmut Holken, Hartmut Koenitz, Sylvain Lefebvre, Antoine Liutkus, Fabien Lotte, Andrew Perkis, Rafael Redondo, Enrico Turrin, Thierry Vieville, Emmanuel Vincent |
| Abstract | Thanks to the Big Data revolution and increasing computing capacities, Artificial Intelligence (AI) has made an impressive revival over the past few years and is now omnipresent in both research and industry. The creative sectors have always been early adopters of AI technologies and this continues to be the case. As a matter of fact, recent technological developments keep pushing the boundaries of intelligent systems in creative applications: the critically acclaimed movie “Sunspring”, released in 2016, was entirely written by AI technology, and the first-ever Music Album, called “Hello World”, produced using AI has been released this year. Simultaneously, the exploratory nature of the creative process is raising important technical challenges for AI such as the ability for AI-powered techniques to be accurate under limited data resources, as opposed to the conventional “Big Data” approach, or the ability to process, analyse and match data from multiple modalities (text, sound, images, etc.) at the same time. The purpose of this white paper is to understand future technological advances in AI and their growing impact on creative industries. This paper addresses the following questions: Where does AI operate in creative Industries? What is its operative role? How will AI transform creative industries in the next ten years? This white paper aims to provide a realistic perspective of the scope of AI actions in creative industries, proposes a vision of how this technology could contribute to research and development works in such context, and identifies research and development challenges. |
| Tasks | |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.04175v1 |
| https://arxiv.org/pdf/1905.04175v1.pdf | |
| PWC | https://paperswithcode.com/paper/ai-in-the-media-and-creative-industries |
| Repo | |
| Framework | |
Graph Representation Learning via Multi-task Knowledge Distillation
| Title | Graph Representation Learning via Multi-task Knowledge Distillation |
| Authors | Jiaqi Ma, Qiaozhu Mei |
| Abstract | Machine learning on graph structured data has attracted much research interest due to its ubiquity in real world data. However, how to efficiently represent graph data in a general way is still an open problem. Traditional methods use handcraft graph features in a tabular form but suffer from the defects of domain expertise requirement and information loss. Graph representation learning overcomes these defects by automatically learning the continuous representations from graph structures, but they require abundant training labels, which are often hard to fulfill for graph-level prediction problems. In this work, we demonstrate that, if available, the domain expertise used for designing handcraft graph features can improve the graph-level representation learning when training labels are scarce. Specifically, we proposed a multi-task knowledge distillation method. By incorporating network-theory-based graph metrics as auxiliary tasks, we show on both synthetic and real datasets that the proposed multi-task learning method can improve the prediction performance of the original learning task, especially when the training data size is small. |
| Tasks | Graph Representation Learning, Multi-Task Learning, Representation Learning |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.05700v1 |
| https://arxiv.org/pdf/1911.05700v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-representation-learning-via-multi-task |
| Repo | |
| Framework | |
Anytime Tail Averaging
| Title | Anytime Tail Averaging |
| Authors | Nicolas Le Roux |
| Abstract | Tail averaging consists in averaging the last examples in a stream. Common techniques either have a memory requirement which grows with the number of samples to average, are not available at every timestep or do not accomodate growing windows. We propose two techniques with a low constant memory cost that perform tail averaging with access to the average at every time step. We also show how one can improve the accuracy of that average at the cost of increased memory consumption. |
| Tasks | |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.05083v2 |
| http://arxiv.org/pdf/1902.05083v2.pdf | |
| PWC | https://paperswithcode.com/paper/anytime-tail-averaging |
| Repo | |
| Framework | |
Reducing selfish routing inefficiencies using traffic lights
| Title | Reducing selfish routing inefficiencies using traffic lights |
| Authors | Charlotte Roman, Paolo Turrini |
| Abstract | Traffic congestion games abstract away from the costs of junctions in transport networks, yet, in urban environments, these often impact journey times significantly. In this paper we equip congestion games with traffic lights, modelled as junction-based waiting cycles, therefore enabling more realistic route planning strategies. Using the SUMO simulator, we show that our modelling choices coincide with realistic routing behaviours, in particular, that drivers’ decisions about route choices are based on the proportion of red light time for their direction of travel. Drawing upon the experimental results, we show that the effects of the notorious Braess’ paradox can be avoided in theory and significantly reduced in practice, by allocating the appropriate traffic light cycles along a transport network. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06513v1 |
| https://arxiv.org/pdf/1912.06513v1.pdf | |
| PWC | https://paperswithcode.com/paper/reducing-selfish-routing-inefficiencies-using |
| Repo | |
| Framework | |
An Experiment on Measurement of Pavement Roughness via Android-Based Smartphones
| Title | An Experiment on Measurement of Pavement Roughness via Android-Based Smartphones |
| Authors | Piyasak Thiandee, Boonsap Witchayangkoon, Sayan Sirimontree, Ponlathep Lertworawanich |
| Abstract | The study focuses on the experiment of using three different smartphones to collect acceleration data from vibration for the road roughness detection. The Android operating system is used in the application. The study takes place on asphaltic pavement of the expressway system of Thailand, with 9 km distance. The run vehicle has an inertial profiler with laser line sensors to record road roughness according to the IRI. The RMS and Machine Learning (ML) methods are used in this study. There is different ability of each smartphone to detect the vibration, thus different detected values are obtained. The results are compared to the IRI observation. ML method gives better result compared to RMS. This study finds little relationship between IRI and acceleration data from vibration collected from smartphones. |
| Tasks | |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.13120v1 |
| https://arxiv.org/pdf/1907.13120v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-experiment-on-measurement-of-pavement |
| Repo | |
| Framework | |
