Paper Group ANR 1416
Learning Everywhere: A Taxonomy for the Integration of Machine Learning and Simulations. A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion. SAIN: Self-Attentive Integration Network for Recommendation. Resilient Coverage: Exploring the Local-to-Global Trade-off. WeatherNet: Recognising weather and visual conditions from …
Learning Everywhere: A Taxonomy for the Integration of Machine Learning and Simulations
| Title | Learning Everywhere: A Taxonomy for the Integration of Machine Learning and Simulations |
| Authors | Geoffrey Fox, Shantenu Jha |
| Abstract | We present a taxonomy of research on Machine Learning (ML) applied to enhance simulations together with a catalog of some activities. We cover eight patterns for the link of ML to the simulations or systems plus three algorithmic areas: particle dynamics, agent-based models and partial differential equations. The patterns are further divided into three action areas: Improving simulation with Configurations and Integration of Data, Learn Structure, Theory and Model for Simulation, and Learn to make Surrogates. |
| Tasks | |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13340v2 |
| https://arxiv.org/pdf/1909.13340v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-everywhere-a-taxonomy-for-the |
| Repo | |
| Framework | |
A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion
| Title | A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion |
| Authors | Filip Hanzely, Jakub Konečný, Nicolas Loizou, Peter Richtárik, Dmitry Grishchenko |
| Abstract | In this work we present a randomized gossip algorithm for solving the average consensus problem while at the same time protecting the information about the initial private values stored at the nodes. We give iteration complexity bounds for the method and perform extensive numerical experiments. |
| Tasks | |
| Published | 2019-01-27 |
| URL | http://arxiv.org/abs/1901.09367v1 |
| http://arxiv.org/pdf/1901.09367v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-privacy-preserving-randomized-gossip |
| Repo | |
| Framework | |
SAIN: Self-Attentive Integration Network for Recommendation
| Title | SAIN: Self-Attentive Integration Network for Recommendation |
| Authors | Seoungjun Yun, Raehyun Kim, Miyoung Ko, Jaewoo Kang |
| Abstract | With the growing importance of personalized recommendation, numerous recommendation models have been proposed recently. Among them, Matrix Factorization (MF) based models are the most widely used in the recommendation field due to their high performance. However, MF based models suffer from cold start problems where user-item interactions are sparse. To deal with this problem, content based recommendation models which use the auxiliary attributes of users and items have been proposed. Since these models use auxiliary attributes, they are effective in cold start settings. However, most of the proposed models are either unable to capture complex feature interactions or not properly designed to combine user-item feedback information with content information. In this paper, we propose Self-Attentive Integration Network (SAIN) which is a model that effectively combines user-item feedback information and auxiliary information for recommendation task. In SAIN, a self-attention mechanism is used in the feature-level interaction layer to effectively consider interactions between multiple features, while the information integration layer adaptively combines content and feedback information. The experimental results on two public datasets show that our model outperforms the state-of-the-art models by 2.13% |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.13130v2 |
| https://arxiv.org/pdf/1905.13130v2.pdf | |
| PWC | https://paperswithcode.com/paper/sain-self-attentive-integration-network-for |
| Repo | |
| Framework | |
Resilient Coverage: Exploring the Local-to-Global Trade-off
| Title | Resilient Coverage: Exploring the Local-to-Global Trade-off |
| Authors | Ragesh K. Ramachandran, Lifeng Zhou, Gaurav S. Sukhatme |
| Abstract | We propose a centralized control framework to select suitable robots from a heterogeneous pool and place them at appropriate locations to monitor a region for events of interest. In the event of a robot failure, the framework repositions robots in a user-defined local neighborhood of the failed robot to compensate for the coverage loss. The central controller augments the team with additional robots from the robot pool when simply repositioning robots fails to attain a user-specified level of desired coverage. The size of the local neighborhood around the failed robot and the desired coverage over the region are two settings that can be manipulated to achieve a user-specified balance. We investigate the trade-off between the coverage compensation achieved through local repositioning and the computation required to plan the new robot locations. We also study the relationship between the size of the local neighborhood and the number of additional robots added to the team for a given user-specified level of desired coverage. The computational complexity of our resilient strategy (tunable resilient coordination), is quadratic in both neighborhood size and number of robots in the team. At first glance, it seems that any desired level of coverage can be efficiently achieved by augmenting the robot team with more robots while keeping the neighborhood size fixed. However, we show that to reach a high level of coverage in a neighborhood with a large robot population, it is more efficient to enlarge the neighborhood size, instead of adding additional robots and repositioning them. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01917v1 |
| https://arxiv.org/pdf/1910.01917v1.pdf | |
| PWC | https://paperswithcode.com/paper/resilient-coverage-exploring-the-local-to |
| Repo | |
| Framework | |
WeatherNet: Recognising weather and visual conditions from street-level images using deep residual learning
| Title | WeatherNet: Recognising weather and visual conditions from street-level images using deep residual learning |
| Authors | Mohamed R. Ibrahim, James Haworth, Tao Cheng |
| Abstract | Extracting information related to weather and visual conditions at a given time and space is indispensable for scene awareness, which strongly impacts our behaviours, from simply walking in a city to riding a bike, driving a car, or autonomous drive-assistance. Despite the significance of this subject, it is still not been fully addressed by the machine intelligence relying on deep learning and computer vision to detect the multi-labels of weather and visual conditions with a unified method that can be easily used for practice. What has been achieved to-date is rather sectorial models that address limited number of labels that do not cover the wide spectrum of weather and visual conditions. Nonetheless, weather and visual conditions are often addressed individually. In this paper, we introduce a novel framework to automatically extract this information from street-level images relying on deep learning and computer vision using a unified method without any pre-defined constraints in the processed images. A pipeline of four deep Convolutional Neural Network (CNN) models, so-called the WeatherNet, is trained, relying on residual learning using ResNet50 architecture, to extract various weather and visual conditions such as Dawn/dusk, day and night for time detection, and glare for lighting conditions, and clear, rainy, snowy, and foggy for weather conditions. The WeatherNet shows strong performance in extracting this information from user-defined images or video streams that can be used not limited to: autonomous vehicles and drive-assistance systems, tracking behaviours, safety-related research, or even for better understanding cities through images for policy-makers. |
| Tasks | Autonomous Vehicles |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09910v1 |
| https://arxiv.org/pdf/1910.09910v1.pdf | |
| PWC | https://paperswithcode.com/paper/weathernet-recognising-weather-and-visual |
| Repo | |
| Framework | |
Neural Random Forest Imitation
| Title | Neural Random Forest Imitation |
| Authors | Christoph Reinders, Bodo Rosenhahn |
| Abstract | We present Neural Random Forest Imitation - a novel approach for transforming random forests into neural networks. Existing methods produce very inefficient architectures and do not scale. In this paper, we introduce a new method for generating data from a random forest and learning a neural network that imitates it. Without any additional training data, this transformation creates very efficient neural networks that learn the decision boundaries of a random forest. The generated model is fully differentiable and can be combined with the feature extraction in a single pipeline enabling further end-to-end processing. Experiments on several real-world benchmark datasets demonstrate outstanding performance in terms of scalability, accuracy, and learning with very few training examples. Compared to state-of-the-art mappings, we significantly reduce the network size while achieving the same or even improved accuracy due to better generalization. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10829v1 |
| https://arxiv.org/pdf/1911.10829v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-random-forest-imitation |
| Repo | |
| Framework | |
Multimodal Ensemble Approach to Incorporate Various Types of Clinical Notes for Predicting Readmission
| Title | Multimodal Ensemble Approach to Incorporate Various Types of Clinical Notes for Predicting Readmission |
| Authors | Bonggun Shin, Julien Hogan, Andrew B. Adams, Raymond J. Lynch, Rachel E. Patzer, Jinho D. Choi |
| Abstract | Electronic Health Records (EHRs) have been heavily used to predict various downstream clinical tasks such as readmission or mortality. One of the modalities in EHRs, clinical notes, has not been fully explored for these tasks due to its unstructured and inexplicable nature. Although recent advances in deep learning (DL) enables models to extract interpretable features from unstructured data, they often require a large amount of training data. However, many tasks in medical domains inherently consist of small sample data with lengthy documents; for a kidney transplant as an example, data from only a few thousand of patients are available and each patient’s document consists of a couple of millions of words in major hospitals. Thus, complex DL methods cannot be applied to these kinds of domains. In this paper, we present a comprehensive ensemble model using vector space modeling and topic modeling. Our proposed model is evaluated on the readmission task of kidney transplant patients and improves 0.0211 in terms of c-statistics from the previous state-of-the-art approach using structured data, while typical DL methods fail to beat this approach. The proposed architecture provides the interpretable score for each feature from both modalities, structured and unstructured data, which is shown to be meaningful through a physician’s evaluation. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1906.01498v1 |
| https://arxiv.org/pdf/1906.01498v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-ensemble-approach-to-incorporate |
| Repo | |
| Framework | |
A Short Remark on Analogical Reasoning
| Title | A Short Remark on Analogical Reasoning |
| Authors | Karl Schlechta |
| Abstract | We discuss the problem of defining a logic for analogical reasoning, and sketch a solution in the style of the semantics for Counterfactual Conditionals, Preferential Structures, etc. |
| Tasks | |
| Published | 2019-10-06 |
| URL | https://arxiv.org/abs/1910.02453v1 |
| https://arxiv.org/pdf/1910.02453v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-short-remark-on-analogical-reasoning |
| Repo | |
| Framework | |
Speech Driven Backchannel Generation using Deep Q-Network for Enhancing Engagement in Human-Robot Interaction
| Title | Speech Driven Backchannel Generation using Deep Q-Network for Enhancing Engagement in Human-Robot Interaction |
| Authors | Nusrah Hussain, Engin Erzin, T. Metin Sezgin, Yucel Yemez |
| Abstract | We present a novel method for training a social robot to generate backchannels during human-robot interaction. We address the problem within an off-policy reinforcement learning framework, and show how a robot may learn to produce non-verbal backchannels like laughs, when trained to maximize the engagement and attention of the user. A major contribution of this work is the formulation of the problem as a Markov decision process (MDP) with states defined by the speech activity of the user and rewards generated by quantified engagement levels. The problem that we address falls into the class of applications where unlimited interaction with the environment is not possible (our environment being a human) because it may be time-consuming, costly, impracticable or even dangerous in case a bad policy is executed. Therefore, we introduce deep Q-network (DQN) in a batch reinforcement learning framework, where an optimal policy is learned from a batch data collected using a more controlled policy. We suggest the use of human-to-human dyadic interaction datasets as a batch of trajectories to train an agent for engaging interactions. Our experiments demonstrate the potential of our method to train a robot for engaging behaviors in an offline manner. |
| Tasks | |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01618v1 |
| https://arxiv.org/pdf/1908.01618v1.pdf | |
| PWC | https://paperswithcode.com/paper/speech-driven-backchannel-generation-using |
| Repo | |
| Framework | |
Neuromodulated Goal-Driven Perception in Uncertain Domains
| Title | Neuromodulated Goal-Driven Perception in Uncertain Domains |
| Authors | Xinyun Zou, Soheil Kolouri, Praveen K. Pilly, Jeffrey L. Krichmar |
| Abstract | In uncertain domains, the goals are often unknown and need to be predicted by the organism or system. In this paper, contrastive excitation backprop (c-EB) was used in a goal-driven perception task with pairs of noisy MNIST digits, where the system had to increase attention to one of the two digits corresponding to a goal (i.e., even, odd, low value, or high value) and decrease attention to the distractor digit or noisy background pixels. Because the valid goal was unknown, an online learning model based on the cholinergic and noradrenergic neuromodulatory systems was used to predict a noisy goal (expected uncertainty) and re-adapt when the goal changed (unexpected uncertainty). This neurobiologically plausible model demonstrates how neuromodulatory systems can predict goals in uncertain domains and how attentional mechanisms can enhance the perception of that goal. |
| Tasks | |
| Published | 2019-02-16 |
| URL | http://arxiv.org/abs/1903.00068v1 |
| http://arxiv.org/pdf/1903.00068v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuromodulated-goal-driven-perception-in |
| Repo | |
| Framework | |
Prediction with Expert Advice: a PDE Perspective
| Title | Prediction with Expert Advice: a PDE Perspective |
| Authors | Nadejda Drenska, Robert V. Kohn |
| Abstract | This work addresses a classic problem of online prediction with expert advice. We assume an adversarial opponent, and we consider both the finite-horizon and random-stopping versions of this zero-sum, two-person game. Focusing on an appropriate continuum limit and using methods from optimal control, we characterize the value of the game as the viscosity solution of a certain nonlinear partial differential equation. The analysis also reveals the predictor’s and the opponent’s minimax optimal strategies. Our work provides, in particular, a continuum perspective on recent work of Gravin, Peres, and Sivan (Proc SODA 2016). Our techniques are similar to those of Kohn and Serfaty (Comm Pure Appl Math 2010), where scaling limits of some two-person games led to elliptic or parabolic PDEs. |
| Tasks | |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11401v1 |
| http://arxiv.org/pdf/1904.11401v1.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-with-expert-advice-a-pde |
| Repo | |
| Framework | |
A Projectional Ansatz to Reconstruction
| Title | A Projectional Ansatz to Reconstruction |
| Authors | Sören Dittmer, Peter Maass |
| Abstract | Recently the field of inverse problems has seen a growing usage of mathematically only partially understood learned and non-learned priors. Based on first principles, we develop a projectional approach to inverse problems that addresses the incorporation of these priors, while still guaranteeing data consistency. We implement this projectional method (PM) on the one hand via very general Plug-and-Play priors and on the other hand, via an end-to-end training approach. To this end, we introduce a novel alternating neural architecture, allowing for the incorporation of highly customized priors from data in a principled manner. We also show how the recent success of Regularization by Denoising (RED) can, at least to some extent, be explained as an approximation of the PM. Furthermore, we demonstrate how the idea can be applied to stop the degradation of Deep Image Prior (DIP) reconstructions over time. |
| Tasks | Denoising |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04675v2 |
| https://arxiv.org/pdf/1907.04675v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-projectional-ansatz-to-reconstruction |
| Repo | |
| Framework | |
Global Collaboration through Local Interaction in Competitive Learning
| Title | Global Collaboration through Local Interaction in Competitive Learning |
| Authors | Abbas Siddiqui, Dionysios Georgiadis |
| Abstract | Feature maps, that preserve the global topology of arbitrary datasets, can be formed by self-organizing competing agents. So far, it has been presumed that global interaction of agents is necessary for this process. We establish that this is not the case, and that global topology can be uncovered through strictly local interactions. Enforcing uniformity of map quality across all agents, results in an algorithm that is able to consistently uncover the global topology of diversely challenging datasets.The applicability and scalability of this approach is further tested on a large point cloud dataset, revealing a linear relation between map training time and size. The presented work not only reduces algorithmic complexity but also constitutes first step towards a distributed self organizing map. |
| Tasks | |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.03856v1 |
| http://arxiv.org/pdf/1902.03856v1.pdf | |
| PWC | https://paperswithcode.com/paper/global-collaboration-through-local |
| Repo | |
| Framework | |
Enhanced Spatially Interleaved Techniques for Multi-View Distributed Video Coding
| Title | Enhanced Spatially Interleaved Techniques for Multi-View Distributed Video Coding |
| Authors | Nantheera Anantrasirichai, Dimitris Agrafiotis |
| Abstract | This paper presents a multi-view distributed video coding framework for independent camera encoding and centralized decoding. Spatio-temporal-view concealment methods are developed that exploit the interleaved nature of the employed hybrid KEY/Wyner-Ziv frames for block-wise generation of the side information (SI). We study a number of view concealment methods and develop a joint approach that exploits all available correlation for forming the side information. We apply a diversity technique for fusing multiple such predictions thereby achieving more reliable results. We additionally introduce systems enhancements for further improving the rate distortion performance through selective feedback, inter-view bitplane projection and frame subtraction. Results show a significant improvement in performance relative to H.264 intra coding of up to 25% reduction in bitrate or equivalently 2.5 dB increase in PSNR. |
| Tasks | |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.07854v1 |
| https://arxiv.org/pdf/1912.07854v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhanced-spatially-interleaved-techniques-for |
| Repo | |
| Framework | |
Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms
| Title | Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms |
| Authors | K S Sesh Kumar, Marc Peter Deisenroth |
| Abstract | Differential privacy is concerned about the prediction quality while measuring the privacy impact on individuals whose information is contained in the data. We consider differentially private risk minimization problems with regularizers that induce structured sparsity. These regularizers are known to be convex but they are often non-differentiable. We analyze the standard differentially private algorithms, such as output perturbation, Frank-Wolfe and objective perturbation. Output perturbation is a differentially private algorithm that is known to perform well for minimizing risks that are strongly convex. Previous works have derived excess risk bounds that are independent of the dimensionality. In this paper, we assume a particular class of convex but non-smooth regularizers that induce structured sparsity and loss functions for generalized linear models. We also consider differentially private Frank-Wolfe algorithms to optimize the dual of the risk minimization problem. We derive excess risk bounds for both these algorithms. Both the bounds depend on the Gaussian width of the unit ball of the dual norm. We also show that objective perturbation of the risk minimization problems is equivalent to the output perturbation of a dual optimization problem. This is the first work that analyzes the dual optimization problems of risk minimization problems in the context of differential privacy. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.04873v1 |
| https://arxiv.org/pdf/1905.04873v1.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-empirical-risk-4 |
| Repo | |
| Framework | |
