October 18, 2019

2924 words 14 mins read

Paper Group ANR 669

Sequential Behavioral Data Processing Using Deep Learning and the Markov Transition Field in Online Fraud Detection. Automated Data Slicing for Model Validation:A Big data - AI Integration Approach. Meta Transfer Learning for Facial Emotion Recognition. On Cross-validation for Sparse Reduced Rank Regression. On the Runtime Analysis of the Clearing …

Sequential Behavioral Data Processing Using Deep Learning and the Markov Transition Field in Online Fraud Detection


Title	Sequential Behavioral Data Processing Using Deep Learning and the Markov Transition Field in Online Fraud Detection
Authors	Ruinan Zhang, Fanglan Zheng, Wei Min
Abstract	Due to the popularity of the Internet and smart mobile devices, more and more financial transactions and activities have been digitalized. Compared to traditional financial fraud detection strategies using credit-related features, customers are generating a large amount of unstructured behavioral data every second. In this paper, we propose an Recurrent Neural Netword (RNN) based deep-learning structure integrated with Markov Transition Field (MTF) for predicting online fraud behaviors using customer’s interactions with websites or smart-phone apps as a series of states. In practice, we tested and proved that the proposed network structure for processing sequential behavioral data could significantly boost fraud predictive ability comparing with the multilayer perceptron network and distance based classifier with Dynamic Time Warping(DTW) as distance metric.
Tasks	Fraud Detection
Published	2018-08-16
URL	http://arxiv.org/abs/1808.05329v1
PDF	http://arxiv.org/pdf/1808.05329v1.pdf
PWC	https://paperswithcode.com/paper/sequential-behavioral-data-processing-using
Repo
Framework

Automated Data Slicing for Model Validation:A Big data - AI Integration Approach


Title	Automated Data Slicing for Model Validation:A Big data - AI Integration Approach
Authors	Yeounoh Chung, Tim Kraska, Neoklis Polyzotis, Ki Hyun Tae, Steven Euijong Whang
Abstract	As machine learning systems become democratized, it becomes increasingly important to help users easily debug their models. However, current data tools are still primitive when it comes to helping users trace model performance problems all the way to the data. We focus on the particular problem of slicing data to identify subsets of the validation data where the model performs poorly. This is an important problem in model validation because the overall model performance can fail to reflect that of the smaller subsets, and slicing allows users to analyze the model performance on a more granular-level. Unlike general techniques (e.g., clustering) that can find arbitrary slices, our goal is to find interpretable slices (which are easier to take action compared to arbitrary subsets) that are problematic and large. We propose Slice Finder, which is an interactive framework for identifying such slices using statistical techniques. Applications include diagnosing model fairness and fraud detection, where identifying slices that are interpretable to humans is crucial. This research is part of a larger trend of Big data and Artificial Intelligence (AI) integration and opens many opportunities for new research.
Tasks	Fraud Detection
Published	2018-07-16
URL	http://arxiv.org/abs/1807.06068v3
PDF	http://arxiv.org/pdf/1807.06068v3.pdf
PWC	https://paperswithcode.com/paper/automated-data-slicing-for-model-validationa
Repo
Framework

Meta Transfer Learning for Facial Emotion Recognition


Title	Meta Transfer Learning for Facial Emotion Recognition
Authors	Dung Nguyen, Kien Nguyen, Sridha Sridharan, Iman Abbasnejad, David Dean, Clinton Fookes
Abstract	The use of deep learning techniques for automatic facial expression recognition has recently attracted great interest but developed models are still unable to generalize well due to the lack of large emotion datasets for deep learning. To overcome this problem, in this paper, we propose utilizing a novel transfer learning approach relying on PathNet and investigate how knowledge can be accumulated within a given dataset and how the knowledge captured from one emotion dataset can be transferred into another in order to improve the overall performance. To evaluate the robustness of our system, we have conducted various sets of experiments on two emotion datasets: SAVEE and eNTERFACE. The experimental results demonstrate that our proposed system leads to improvement in performance of emotion recognition and performs significantly better than the recent state-of-the-art schemes adopting fine-\ tuning/pre-trained approaches.
Tasks	Emotion Recognition, Facial Expression Recognition, Transfer Learning
Published	2018-05-25
URL	http://arxiv.org/abs/1805.09946v1
PDF	http://arxiv.org/pdf/1805.09946v1.pdf
PWC	https://paperswithcode.com/paper/meta-transfer-learning-for-facial-emotion
Repo
Framework

On Cross-validation for Sparse Reduced Rank Regression


Title	On Cross-validation for Sparse Reduced Rank Regression
Authors	Yiyuan She, Hoang Tran
Abstract	In high-dimensional data analysis, regularization methods pursuing sparsity and/or low rank have received a lot of attention recently. To provide a proper amount of shrinkage, it is typical to use a grid search and a model comparison criterion to find the optimal regularization parameters. However, we show that fixing the parameters across all folds may result in an inconsistency issue, and it is more appropriate to cross-validate projection-selection patterns to obtain the best coefficient estimate. Our in-sample error studies in jointly sparse and rank-deficient models lead to a new class of information criteria with four scale-free forms to bypass the estimation of the noise level. By use of an identity, we propose a novel scale-free calibration to help cross-validation achieve the minimax optimal error rate non-asymptotically. Experiments support the efficacy of the proposed methods.
Tasks	Calibration
Published	2018-12-30
URL	http://arxiv.org/abs/1812.11555v1
PDF	http://arxiv.org/pdf/1812.11555v1.pdf
PWC	https://paperswithcode.com/paper/on-cross-validation-for-sparse-reduced-rank
Repo
Framework

On the Runtime Analysis of the Clearing Diversity-Preserving Mechanism


Title	On the Runtime Analysis of the Clearing Diversity-Preserving Mechanism
Authors	Edgar Covantes Osuna, Dirk Sudholt
Abstract	Clearing is a niching method inspired by the principle of assigning the available resources among a niche to a single individual. The clearing procedure supplies these resources only to the best individual of each niche: the winner. So far, its analysis has been focused on experimental approaches that have shown that clearing is a powerful diversity-preserving mechanism. Using rigorous runtime analysis to explain how and why it is a powerful method, we prove that a mutation-based evolutionary algorithm with a large enough population size, and a phenotypic distance function always succeeds in optimising all functions of unitation for small niches in polynomial time, while a genotypic distance function requires exponential time. Finally, we prove that with phenotypic and genotypic distances clearing is able to find both optima for Twomax and several general classes of bimodal functions in polynomial expected time. We use empirical analysis to highlight some of the characteristics that makes it a useful mechanism and to support the theoretical results.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09715v1
PDF	http://arxiv.org/pdf/1803.09715v1.pdf
PWC	https://paperswithcode.com/paper/on-the-runtime-analysis-of-the-clearing
Repo
Framework

Comparative Analysis of Unsupervised Algorithms for Breast MRI Lesion Segmentation


Title	Comparative Analysis of Unsupervised Algorithms for Breast MRI Lesion Segmentation
Authors	Sulaiman Vesal, Nishant Ravikumar, Stephan Ellman, Andreas Maier
Abstract	Accurate segmentation of breast lesions is a crucial step in evaluating the characteristics of tumors. However, this is a challenging task, since breast lesions have sophisticated shape, topological structure, and variation in the intensity distribution. In this paper, we evaluated the performance of three unsupervised algorithms for the task of breast Magnetic Resonance (MRI) lesion segmentation, namely, Gaussian Mixture Model clustering, K-means clustering and a marker-controlled Watershed transformation based method. All methods were applied on breast MRI slices following selection of regions of interest (ROIs) by an expert radiologist and evaluated on 106 subjects’ images, which include 59 malignant and 47 benign lesions. Segmentation accuracy was evaluated by comparing our results with ground truth masks, using the Dice similarity coefficient (DSC), Jaccard index (JI), Hausdorff distance and precision-recall metrics. The results indicate that the marker-controlled Watershed transformation outperformed all other algorithms investigated.
Tasks	Lesion Segmentation
Published	2018-02-23
URL	http://arxiv.org/abs/1802.08655v1
PDF	http://arxiv.org/pdf/1802.08655v1.pdf
PWC	https://paperswithcode.com/paper/comparative-analysis-of-unsupervised
Repo
Framework

Deep Learning


Title	Deep Learning
Authors	Nicholas G. Polson, Vadim O. Sokolov
Abstract	Deep learning (DL) is a high dimensional data reduction technique for constructing high-dimensional predictors in input-output models. DL is a form of machine learning that uses hierarchical layers of latent features. In this article, we review the state-of-the-art of deep learning from a modeling and algorithmic perspective. We provide a list of successful areas of applications in Artificial Intelligence (AI), Image Processing, Robotics and Automation. Deep learning is predictive in its nature rather then inferential and can be viewed as a black-box methodology for high-dimensional function estimation.
Tasks
Published	2018-07-20
URL	http://arxiv.org/abs/1807.07987v2
PDF	http://arxiv.org/pdf/1807.07987v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning
Repo
Framework

On Lyapunov exponents and adversarial perturbation


Title	On Lyapunov exponents and adversarial perturbation
Authors	Vinay Uday Prabhu, Nishant Desai, John Whaley
Abstract	In this paper, we would like to disseminate a serendipitous discovery involving Lyapunov exponents of a 1-D time series and their use in serving as a filtering defense tool against a specific kind of deep adversarial perturbation. To this end, we use the state-of-the-art CleverHans library to generate adversarial perturbations against a standard Convolutional Neural Network (CNN) architecture trained on the MNIST as well as the Fashion-MNIST datasets. We empirically demonstrate how the Lyapunov exponents computed on the flattened 1-D vector representations of the images served as highly discriminative features that could be to pre-classify images as adversarial or legitimate before feeding the image into the CNN for classification. We also explore the issue of possible false-alarms when the input images are noisy in a non-adversarial sense.
Tasks	Time Series
Published	2018-02-20
URL	http://arxiv.org/abs/1802.06927v1
PDF	http://arxiv.org/pdf/1802.06927v1.pdf
PWC	https://paperswithcode.com/paper/on-lyapunov-exponents-and-adversarial
Repo
Framework

Improving Optimization for Models With Continuous Symmetry Breaking


Title	Improving Optimization for Models With Continuous Symmetry Breaking
Authors	Robert Bamler, Stephan Mandt
Abstract	Many loss functions in representation learning are invariant under a continuous symmetry transformation. For example, the loss function of word embeddings (Mikolov et al., 2013) remains unchanged if we simultaneously rotate all word and context embedding vectors. We show that representation learning models for time series possess an approximate continuous symmetry that leads to slow convergence of gradient descent. We propose a new optimization algorithm that speeds up convergence using ideas from gauge theory in physics. Our algorithm leads to orders of magnitude faster convergence and to more interpretable representations, as we show for dynamic extensions of matrix factorization and word embedding models. We further present an example application of our proposed algorithm that translates modern words into their historic equivalents.
Tasks	Representation Learning, Time Series, Word Embeddings
Published	2018-03-08
URL	http://arxiv.org/abs/1803.03234v3
PDF	http://arxiv.org/pdf/1803.03234v3.pdf
PWC	https://paperswithcode.com/paper/improving-optimization-for-models-with
Repo
Framework

AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples


Title	AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples
Authors	Dongyeop Kang, Tushar Khot, Ashish Sabharwal, Eduard Hovy
Abstract	We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large lexical resources in entailment models via only a handful of rule templates. Second, to make the entailment model - a discriminator - more robust, we propose the first GAN-style approach for training it using a natural language example generator that iteratively adjusts based on the discriminator’s performance. We demonstrate effectiveness using two entailment datasets, where the proposed methods increase accuracy by 4.7% on SciTail and by 2.8% on a 1% training sub-sample of SNLI. Notably, even a single hand-written rule, negate, improves the accuracy on the negation examples in SNLI by 6.1%.
Tasks	Natural Language Inference
Published	2018-05-12
URL	http://arxiv.org/abs/1805.04680v1
PDF	http://arxiv.org/pdf/1805.04680v1.pdf
PWC	https://paperswithcode.com/paper/adventure-adversarial-training-for-textual
Repo
Framework

Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks


Title	Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
Authors	Saeid Asgari Taghanaki, Arkadeep Das, Ghassan Hamarneh
Abstract	Recently, there have been several successful deep learning approaches for automatically classifying chest X-ray images into different disease categories. However, there is not yet a comprehensive vulnerability analysis of these models against the so-called adversarial perturbations/attacks, which makes deep models more trustful in clinical practices. In this paper, we extensively analyzed the performance of two state-of-the-art classification deep networks on chest X-ray images. These two networks were attacked by three different categories (ten methods in total) of adversarial methods (both white- and black-box), namely gradient-based, score-based, and decision-based attacks. Furthermore, we modified the pooling operations in the two classification networks to measure their sensitivities against different attacks, on the specific task of chest X-ray classification.
Tasks	Image Classification
Published	2018-07-09
URL	http://arxiv.org/abs/1807.02905v2
PDF	http://arxiv.org/pdf/1807.02905v2.pdf
PWC	https://paperswithcode.com/paper/vulnerability-analysis-of-chest-x-ray-image
Repo
Framework

Reactive Reinforcement Learning in Asynchronous Environments


Title	Reactive Reinforcement Learning in Asynchronous Environments
Authors	Jaden B. Travnik, Kory W. Mathewson, Richard S. Sutton, Patrick M. Pilarski
Abstract	The relationship between a reinforcement learning (RL) agent and an asynchronous environment is often ignored. Frequently used models of the interaction between an agent and its environment, such as Markov Decision Processes (MDP) or Semi-Markov Decision Processes (SMDP), do not capture the fact that, in an asynchronous environment, the state of the environment may change during computation performed by the agent. In an asynchronous environment, minimizing reaction time—the time it takes for an agent to react to an observation—also minimizes the time in which the state of the environment may change following observation. In many environments, the reaction time of an agent directly impacts task performance by permitting the environment to transition into either an undesirable terminal state or a state where performing the chosen action is inappropriate. We propose a class of reactive reinforcement learning algorithms that address this problem of asynchronous environments by immediately acting after observing new state information. We compare a reactive SARSA learning algorithm with the conventional SARSA learning algorithm on two asynchronous robotic tasks (emergency stopping and impact prevention), and show that the reactive RL algorithm reduces the reaction time of the agent by approximately the duration of the algorithm’s learning update. This new class of reactive algorithms may facilitate safer control and faster decision making without any change to standard learning guarantees.
Tasks	Decision Making
Published	2018-02-16
URL	http://arxiv.org/abs/1802.06139v1
PDF	http://arxiv.org/pdf/1802.06139v1.pdf
PWC	https://paperswithcode.com/paper/reactive-reinforcement-learning-in
Repo
Framework

EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning


Title	EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning
Authors	Kunal Menda, Katherine Driggs-Campbell, Mykel J. Kochenderfer
Abstract	While imitation learning is often used in robotics, the approach frequently suffers from data mismatch and compounding errors. DAgger is an iterative algorithm that addresses these issues by aggregating training data from both the expert and novice policies, but does not consider the impact of safety. We present a probabilistic extension to DAgger, which attempts to quantify the confidence of the novice policy as a proxy for safety. Our method, EnsembleDAgger, approximates a Gaussian Process using an ensemble of neural networks. Using the variance as a measure of confidence, we compute a decision rule that captures how much we doubt the novice, thus determining when it is safe to allow the novice to act. With this approach, we aim to maximize the novice’s share of actions, while constraining the probability of failure. We demonstrate improved safety and learning performance compared to other DAgger variants and classic imitation learning on an inverted pendulum and in the MuJoCo HalfCheetah environment.
Tasks	Imitation Learning
Published	2018-07-22
URL	https://arxiv.org/abs/1807.08364v3
PDF	https://arxiv.org/pdf/1807.08364v3.pdf
PWC	https://paperswithcode.com/paper/ensembledagger-a-bayesian-approach-to-safe
Repo
Framework

The Logoscope: a Semi-Automatic Tool for Detecting and Documenting French New Words


Title	The Logoscope: a Semi-Automatic Tool for Detecting and Documenting French New Words
Authors	Ingrid Falk, Delphine Bernhard, Christophe Gérard
Abstract	In this article we present the design and implementation of the Logoscope, the first tool especially developed to detect new words of the French language, to document them and allow a public access through a web interface. This semi-automatic tool collects new words daily by browsing the online versions of French well known newspapers such as Le Monde, Le Figaro, L’Equipe, Lib'eration, La Croix, Les 'Echos. In contrast to other existing tools essentially dedicated to dictionary development, the Logoscope attempts to give a more complete account of the context in which the new words occur. In addition to the commonly given morpho-syntactic information it also provides information about the textual and discursive contexts of the word creation; in particular, it automatically determines the (journalistic) topics of the text containing the new word. In this article we first give a general overview of the developed tool. We then describe the approach taken, we discuss the linguistic background which guided our design decisions and present the computational methods we used to implement it.
Tasks
Published	2018-10-25
URL	http://arxiv.org/abs/1810.10797v1
PDF	http://arxiv.org/pdf/1810.10797v1.pdf
PWC	https://paperswithcode.com/paper/the-logoscope-a-semi-automatic-tool-for
Repo
Framework

Deep Semantic Hashing with Generative Adversarial Networks


Title	Deep Semantic Hashing with Generative Adversarial Networks
Authors	Zhaofan Qiu, Yingwei Pan, Ting Yao, Tao Mei
Abstract	Hashing has been a widely-adopted technique for nearest neighbor search in large-scale image retrieval tasks. Recent research has shown that leveraging supervised information can lead to high quality hashing. However, the cost of annotating data is often an obstacle when applying supervised hashing to a new domain. Moreover, the results can suffer from the robustness problem as the data at training and test stage could come from similar but different distributions. This paper studies the exploration of generating synthetic data through semi-supervised generative adversarial networks (GANs), which leverages largely unlabeled and limited labeled training data to produce highly compelling data with intrinsic invariance and global coherence, for better understanding statistical structures of natural data. We demonstrate that the above two limitations can be well mitigated by applying the synthetic data for hashing. Specifically, a novel deep semantic hashing with GANs (DSH-GANs) is presented, which mainly consists of four components: a deep convolution neural networks (CNN) for learning image representations, an adversary stream to distinguish synthetic images from real ones, a hash stream for encoding image representations to hash codes and a classification stream. The whole architecture is trained end-to-end by jointly optimizing three losses, i.e., adversarial loss to correct label of synthetic or real for each sample, triplet ranking loss to preserve the relative similarity ordering in the input real-synthetic triplets and classification loss to classify each sample accurately. Extensive experiments conducted on both CIFAR-10 and NUS-WIDE image benchmarks validate the capability of exploiting synthetic images for hashing. Our framework also achieves superior results when compared to state-of-the-art deep hash models.
Tasks	Image Retrieval
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08275v1
PDF	http://arxiv.org/pdf/1804.08275v1.pdf
PWC	https://paperswithcode.com/paper/deep-semantic-hashing-with-generative
Repo
Framework