January 28, 2020

2938 words 14 mins read

Paper Group ANR 888

Predicting Brazilian court decisions. Response Transformation and Profit Decomposition for Revenue Uplift Modeling. Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach. Social Influence and Radicalization: A Social Data Analytics Study. Differentially Private Markov Chain Monte Carlo. Quasi-Newton Trust Region Policy Optimization. Qua …

Predicting Brazilian court decisions


Title	Predicting Brazilian court decisions
Authors	André Lage-Freitas, Héctor Allende-Cid, Orivaldo Santana, Lívia de Oliveira-Lage
Abstract	Predicting case outcomes is useful but still an extremely hard task for attorneys and other Law professionals. It is not easy to search case information to extract valuable information as this requires dealing with huge data sets and their complexity. For instance, the complexity of Brazil legal system along with the high litigation rates makes this problem even harder. This paper introduces an approach for predicting Brazilian court decisions which is also able to predict whether the decision will be unanimous. We developed a working prototype which performs 79% of accuracy (F1-score) on a data set composed of 4,043 cases from a Brazilian court. To our knowledge, this is the first study to forecast judge decisions in Brazil.
Tasks
Published	2019-04-20
URL	http://arxiv.org/abs/1905.10348v1
PDF	http://arxiv.org/pdf/1905.10348v1.pdf
PWC	https://paperswithcode.com/paper/190510348
Repo
Framework

Response Transformation and Profit Decomposition for Revenue Uplift Modeling


Title	Response Transformation and Profit Decomposition for Revenue Uplift Modeling
Authors	Robin M. Gubela, Stefan Lessmann, Szymon Jaroszewicz
Abstract	Uplift models support decision-making in marketing campaign planning. Estimating the causal effect of a marketing treatment, an uplift model facilitates targeting communication to responsive customers and efficient allocation of marketing budgets. Research into uplift models focuses on conversion models to maximize incremental sales. The paper introduces uplift modeling strategies for maximizing incremental revenues. If customers differ in their spending behavior, revenue maximization is a more plausible business objective compared to maximizing conversions. The proposed methodology entails a transformation of the prediction target, customer-level revenues, that facilitates implementing a causal uplift model using standard machine learning algorithms. The distribution of campaign revenues is typically zero-inflated because of many non-buyers. Remedies to this modeling challenge are incorporated in the proposed revenue uplift strategies in the form of two-stage models. Empirical experiments using real-world e-commerce data confirm the merits of the proposed revenue uplift strategy over relevant alternatives including uplift models for conver-sion and recently developed causal machine learning algorithms. To quantify the degree to which improved targeting decisions raise return on marketing, the paper develops a decomposition of campaign profit. Applying the decomposition to a digital coupon targeting campaign, the paper provides evidence that revenue uplift modeling, as well as causal machine learning, can improve cam-paign profit substantially.
Tasks	Decision Making
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08729v1
PDF	https://arxiv.org/pdf/1911.08729v1.pdf
PWC	https://paperswithcode.com/paper/response-transformation-and-profit
Repo
Framework

Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach


Title	Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach
Authors	Jun Wang, Hefu Zhang, Qi Liu, Zhen Pan, Hanqing Tao
Abstract	Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but is still under exploration. Existing studies either fit the fluctuations of time-series or employ regularization terms to constrain learned tendencies. However, few of them take into account the inherent decision-making process between investors and crowdfunding dynamics. To address the problem, in this paper, we propose a Trajectory-based Continuous Control for Crowdfunding (TC3) algorithm to predict the funding progress in crowdfunding. Specifically, actor-critic frameworks are employed to model the relationship between investors and campaigns, where all of the investors are viewed as an agent that could interact with the environment derived from the real dynamics of campaigns. Then, to further explore the in-depth implications of patterns (i.e., typical characters) in funding series, we propose to subdivide them into $\textit{fast-growing}$ and $\textit{slow-growing}$ ones. Moreover, for the purpose of switching from different kinds of patterns, the actor component of TC3 is extended with a structure of options, which comes to the TC3-Options. Finally, extensive experiments on the Indiegogo dataset not only demonstrate the effectiveness of our methods, but also validate our assumption that the entire pattern learned by TC3-Options is indeed the U-shaped one.
Tasks	Continuous Control, Decision Making, Time Series
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12016v1
PDF	https://arxiv.org/pdf/1912.12016v1.pdf
PWC	https://paperswithcode.com/paper/crowdfunding-dynamics-tracking-a
Repo
Framework


Title	Social Influence and Radicalization: A Social Data Analytics Study
Authors	Vahid Moraveji Hashemi
Abstract	The confluence of technological and societal advances is changing the nature of global terrorism. For example, engagement with Web, social media, and smart devices has the potential to affect the mental behavior of the individuals and influence extremist and criminal behaviors such as Radicalization. In this context, social data analytics (i.e., the discovery, interpretation, and communication of meaningful patterns in social data) and influence maximization (i.e., the problem of finding a small subset of nodes in a social network which can maximize the propagation of influence) has the potential to become a vital asset to explore the factors involved in influencing people to participate in extremist activities. To address this challenge, we study and analyze the recent work done in influence maximization and social data analytics from effectiveness, efficiency and scalability viewpoints. We introduce a social data analytics pipeline, namely iRadical, to enable analysts engage with social data to explore the potential for online radicalization. In iRadical, we present algorithms to analyse the social data as well as the user activity patterns to learn how influence flows in social networks. We implement iRadical as an extensible architecture that is publicly available on GitHub and present the evaluation results.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1910.01212v1
PDF	https://arxiv.org/pdf/1910.01212v1.pdf
PWC	https://paperswithcode.com/paper/social-influence-and-radicalization-a-social
Repo
Framework

Differentially Private Markov Chain Monte Carlo


Title	Differentially Private Markov Chain Monte Carlo
Authors	Mikko A. Heikkilä, Joonas Jälkö, Onur Dikmen, Antti Honkela
Abstract	Recent developments in differentially private (DP) machine learning and DP Bayesian learning have enabled learning under strong privacy guarantees for the training data subjects. In this paper, we further extend the applicability of DP Bayesian learning by presenting the first general DP Markov chain Monte Carlo (MCMC) algorithm whose privacy-guarantees are not subject to unrealistic assumptions on Markov chain convergence and that is applicable to posterior inference in arbitrary models. Our algorithm is based on a decomposition of the Barker acceptance test that allows evaluating the R'enyi DP privacy cost of the accept-reject choice. We further show how to improve the DP guarantee through data subsampling and approximate acceptance tests.
Tasks
Published	2019-01-29
URL	https://arxiv.org/abs/1901.10275v2
PDF	https://arxiv.org/pdf/1901.10275v2.pdf
PWC	https://paperswithcode.com/paper/differentially-private-markov-chain-monte
Repo
Framework

Quasi-Newton Trust Region Policy Optimization


Title	Quasi-Newton Trust Region Policy Optimization
Authors	Devesh Jha, Arvind Raghunathan, Diego Romeres
Abstract	We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement learning tasks with continuous controls. The algorithm has achieved state-of-the-art performance when used in reinforcement learning across a wide range of tasks. However, the algorithm suffers from a number of drawbacks including: lack of stepsize selection criterion, and slow convergence. We investigate the use of a trust region method using dogleg step and a Quasi-Newton approximation for the Hessian for policy optimization. We demonstrate through numerical experiments over a wide range of challenging continuous control tasks that our particular choice is efficient in terms of number of samples and improves performance
Tasks	Continuous Control
Published	2019-12-26
URL	https://arxiv.org/abs/1912.11912v1
PDF	https://arxiv.org/pdf/1912.11912v1.pdf
PWC	https://paperswithcode.com/paper/quasi-newton-trust-region-policy-optimization
Repo
Framework

Quantum-assisted associative adversarial network: Applying quantum annealing in deep learning


Title	Quantum-assisted associative adversarial network: Applying quantum annealing in deep learning
Authors	Max Wilson, Thomas Vandal, Tad Hogg, Eleanor Rieffel
Abstract	We present an algorithm for learning a latent variable generative model via generative adversarial learning where the canonical uniform noise input is replaced by samples from a graphical model. This graphical model is learned by a Boltzmann machine which learns low-dimensional feature representation of data extracted by the discriminator. A quantum annealer, the D-Wave 2000Q, is used to sample from this model. This algorithm joins a growing family of algorithms that use a quantum annealing subroutine in deep learning, and provides a framework to test the advantages of quantum-assisted learning in GANs. Fully connected, symmetric bipartite and Chimera graph topologies are compared on a reduced stochastically binarized MNIST dataset, for both classical and quantum annealing sampling methods. The quantum-assisted associative adversarial network successfully learns a generative model of the MNIST dataset for all topologies, and is also applied to the LSUN dataset bedrooms class for the Chimera topology. Evaluated using the Fr'{e}chet inception distance and inception score, the quantum and classical versions of the algorithm are found to have equivalent performance for learning an implicit generative model of the MNIST dataset.
Tasks
Published	2019-04-23
URL	http://arxiv.org/abs/1904.10573v1
PDF	http://arxiv.org/pdf/1904.10573v1.pdf
PWC	https://paperswithcode.com/paper/quantum-assisted-associative-adversarial
Repo
Framework

Efficacy of Modern Neuro-Evolutionary Strategies for Continuous Control Optimization


Title	Efficacy of Modern Neuro-Evolutionary Strategies for Continuous Control Optimization
Authors	Paolo Pagliuca, Nicola Milano, Stefano Nolfi
Abstract	We analyze the efficacy of modern neuro-evolutionary strategies for continuous control optimization. Overall the results collected on a wide variety of qualitatively different benchmark problems indicate that these methods are generally effective and scale well with respect to the number of parameters and the complexity of the problem. We demonstrate the importance of using suitable fitness functions or reward criteria since functions that are optimal for reinforcement learning algorithms tend to be sub-optimal for evolutionary strategies and vice versa. Finally, we provide an analysis of the role of hyper-parameters that demonstrates the importance of normalization techniques, especially in complex problems.
Tasks	Continuous Control
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05239v1
PDF	https://arxiv.org/pdf/1912.05239v1.pdf
PWC	https://paperswithcode.com/paper/efficacy-of-modern-neuro-evolutionary
Repo
Framework

Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey


Title	Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
Authors	Longlong Jing, Yingli Tian
Abstract	Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos. First, the motivation, general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the main components and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used image and video datasets and the existing self-supervised visual feature learning methods. Finally, quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual feature learning.
Tasks	Self-Supervised Image Classification
Published	2019-02-16
URL	http://arxiv.org/abs/1902.06162v1
PDF	http://arxiv.org/pdf/1902.06162v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-visual-feature-learning-with
Repo
Framework

Deep Morphological Simplification Network (MS-Net) for Guided Registration of Brain Magnetic Resonance Images


Title	Deep Morphological Simplification Network (MS-Net) for Guided Registration of Brain Magnetic Resonance Images
Authors	Dongming Wei, Zhengwang Wu, Gang Li, Xiaohuan Cao, Dinggang Shen, Qian Wang
Abstract	Objective: Deformable brain MR image registration is challenging due to large inter-subject anatomical variation. For example, the highly complex cortical folding pattern makes it hard to accurately align corresponding cortical structures of individual images. In this paper, we propose a novel deep learning way to simplify the difficult registration problem of brain MR images. Methods: We train a morphological simplification network (MS-Net), which can generate a “simple” image with less anatomical details based on the “complex” input. With MS-Net, the complexity of the fixed image or the moving image under registration can be reduced gradually, thus building an individual (simplification) trajectory represented by MS-Net outputs. Since the generated images at the ends of the two trajectories (of the fixed and moving images) are so simple and very similar in appearance, they are easy to register. Thus, the two trajectories can act as a bridge to link the fixed and the moving images, and guide their registration. Results: Our experiments show that the proposed method can achieve highly accurate registration performance on different datasets (i.e., NIREP, LPBA, IBSR, CUMC, and MGH). Moreover, the method can be also easily transferred across diverse image datasets and obtain superior accuracy on surface alignment. Conclusion and Significance: We propose MS-Net as a powerful and flexible tool to simplify brain MR images and their registration. To our knowledge, this is the first work to simplify brain MR image registration by deep learning, instead of estimating deformation field directly.
Tasks	Image Registration
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02342v1
PDF	http://arxiv.org/pdf/1902.02342v1.pdf
PWC	https://paperswithcode.com/paper/deep-morphological-simplification-network-ms
Repo
Framework

Compatible features for Monotonic Policy Improvement


Title	Compatible features for Monotonic Policy Improvement
Authors	Marcin B. Tomczak, Sergio Valcarcel Macua, Enrique Munoz de Cote, Peter Vrancx
Abstract	Recent policy optimization approaches have achieved substantial empirical success by constructing surrogate optimization objectives. The Approximate Policy Iteration objective (Schulman et al., 2015a; Kakade and Langford, 2002) has become a standard optimization target for reinforcement learning problems. Using this objective in practice requires an estimator of the advantage function. Policy optimization methods such as those proposed in Schulman et al. (2015b) estimate the advantages using a parametric critic. In this work we establish conditions under which the parametric approximation of the critic does not introduce bias to the updates of surrogate objective. These results hold for a general class of parametric policies, including deep neural networks. We obtain a result analogous to the compatible features derived for the original Policy Gradient Theorem (Sutton et al., 1999). As a result, we also identify a previously unknown bias that current state-of-the-art policy optimization algorithms (Schulman et al., 2015a, 2017) have introduced by not employing these compatible features.
Tasks
Published	2019-10-09
URL	https://arxiv.org/abs/1910.03880v2
PDF	https://arxiv.org/pdf/1910.03880v2.pdf
PWC	https://paperswithcode.com/paper/compatible-features-for-monotonic-policy
Repo
Framework

Deep Learning for Pneumothorax Detection and Localization in Chest Radiographs


Title	Deep Learning for Pneumothorax Detection and Localization in Chest Radiographs
Authors	André Gooßen, Hrishikesh Deshpande, Tim Harder, Evan Schwab, Ivo Baltruschat, Thusitha Mabotuwana, Nathan Cross, Axel Saalbach
Abstract	Pneumothorax is a critical condition that requires timely communication and immediate action. In order to prevent significant morbidity or patient death, early detection is crucial. For the task of pneumothorax detection, we study the characteristics of three different deep learning techniques: (i) convolutional neural networks, (ii) multiple-instance learning, and (iii) fully convolutional networks. We perform a five-fold cross-validation on a dataset consisting of 1003 chest X-ray images. ROC analysis yields AUCs of 0.96, 0.93, and 0.92 for the three methods, respectively. We review the classification and localization performance of these approaches as well as an ensemble of the three aforementioned techniques.
Tasks	Multiple Instance Learning
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07324v1
PDF	https://arxiv.org/pdf/1907.07324v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-pneumothorax-detection-and
Repo
Framework

Multiview Representation Learning for a Union of Subspaces


Title	Multiview Representation Learning for a Union of Subspaces
Authors	Nils Holzenberger, Raman Arora
Abstract	Canonical correlation analysis (CCA) is a popular technique for learning representations that are maximally correlated across multiple views in data. In this paper, we extend the CCA based framework for learning a multiview mixture model. We show that the proposed model and a set of simple heuristics yield improvements over standard CCA, as measured in terms of performance on downstream tasks. Our experimental results show that our correlation-based objective meaningfully generalizes the CCA objective to a mixture of CCA models.
Tasks	Representation Learning
Published	2019-12-30
URL	https://arxiv.org/abs/1912.12766v1
PDF	https://arxiv.org/pdf/1912.12766v1.pdf
PWC	https://paperswithcode.com/paper/multiview-representation-learning-for-a-union
Repo
Framework

One-Shot Federated Learning


Title	One-Shot Federated Learning
Authors	Neel Guha, Ameet Talwalkar, Virginia Smith
Abstract	We present one-shot federated learning, where a central server learns a global model over a network of federated devices in a single round of communication. Our approach - drawing on ensemble learning and knowledge aggregation - achieves an average relative gain of 51.5% in AUC over local baselines and comes within 90.1% of the (unattainable) global ideal. We discuss these methods and identify several promising directions of future work.
Tasks
Published	2019-02-28
URL	http://arxiv.org/abs/1902.11175v2
PDF	http://arxiv.org/pdf/1902.11175v2.pdf
PWC	https://paperswithcode.com/paper/one-shot-federated-learning
Repo
Framework

Developing and Using Special-Purpose Lexicons for Cohort Selection from Clinical Notes


Title	Developing and Using Special-Purpose Lexicons for Cohort Selection from Clinical Notes
Authors	Samarth Rawal, Ashok Prakash, Soumya Adhya, Sidharth Kulkarni, Saadat Anwar, Chitta Baral, Murthy Devarakonda
Abstract	Background and Significance: Selecting cohorts for a clinical trial typically requires costly and time-consuming manual chart reviews resulting in poor participation. To help automate the process, National NLP Clinical Challenges (N2C2) conducted a shared challenge by defining 13 criteria for clinical trial cohort selection and by providing training and test datasets. This research was motivated by the N2C2 challenge. Methods: We broke down the task into 13 independent subtasks corresponding to each criterion and implemented subtasks using rules or a supervised machine learning model. Each task critically depended on knowledge resources in the form of task-specific lexicons, for which we developed a novel model-driven approach. The approach allowed us to first expand the lexicon from a seed set and then remove noise from the list, thus improving the accuracy. Results: Our system achieved an overall F measure of 0.9003 at the challenge, and was statistically tied for the first place out of 45 participants. The model-driven lexicon development and further debugging the rules/code on the training set improved overall F measure to 0.9140, overtaking the best numerical result at the challenge. Discussion: Cohort selection, like phenotype extraction and classification, is amenable to rule-based or simple machine learning methods, however, the lexicons involved, such as medication names or medical terms referring to a medical problem, critically determine the overall accuracy. Automated lexicon development has the potential for scalability and accuracy.
Tasks
Published	2019-02-26
URL	http://arxiv.org/abs/1902.09674v1
PDF	http://arxiv.org/pdf/1902.09674v1.pdf
PWC	https://paperswithcode.com/paper/developing-and-using-special-purpose-lexicons
Repo
Framework