January 25, 2020

3168 words 15 mins read

Paper Group ANR 1655

Learning Embeddings from Cancer Mutation Sets for Classification Tasks. Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding. A Hybrid Precipitation Prediction Method based on Multicellular Gene Expression Programming. Fraud Detection in Networks: State-of-the-art. Deep lea …

Learning Embeddings from Cancer Mutation Sets for Classification Tasks


Title	Learning Embeddings from Cancer Mutation Sets for Classification Tasks
Authors	Geoffroy Dubourg-Felonneau, Yasmeen Kussad, Dominic Kirkham, John W Cassidy, Nirmesh Patel, Harry W Clifford
Abstract	Analysis of somatic mutation profiles from cancer patients is essential in the development of cancer research. However, the low frequency of most mutations and the varying rates of mutations across patients makes the data extremely challenging to statistically analyze as well as difficult to use in classification problems, for clustering, visualization or for learning useful information. Thus, the creation of low dimensional representations of somatic mutation profiles that hold useful information about the DNA of cancer cells will facilitate the use of such data in applications that will progress precision medicine. In this paper, we talk about the open problem of learning from somatic mutations, and present Flatsomatic: a solution that utilizes variational autoencoders (VAEs) to create latent representations of somatic profiles. The work done in this paper shows great potential for this method, with the VAE embeddings performing better than PCA for a clustering task, and performing equally well to the raw high dimensional data for a classification task. We believe the methods presented herein can be of great value in future research and in bringing data-driven models into precision oncology.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.09008v1
PDF	https://arxiv.org/pdf/1911.09008v1.pdf
PWC	https://paperswithcode.com/paper/learning-embeddings-from-cancer-mutation-sets
Repo
Framework

Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding


Title	Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding
Authors	Pan Zhou, Ruchao Fan, Wei Chen, Jia Jia
Abstract	Transformer showed promising results in many sequence to sequence transformation tasks recently. It utilizes a number of feed-forward self-attention layers in the encoder and decoder to replace recurrent neural networks (RNN) in attention-based encoder decoder (AED). Self-attention layer learns temporal dependence by incorporating sinusoidal positional embedding of tokens in sequences for parallel computing. Quicker iteration speed in training than sequential operation of RNN can be obtained. The deeper layer of transformer also makes it perform better than RNN-based AED. However, this parallelization makes it hard to apply schedule sampling training. Self-attention with sinusoidal positional embedding may also cause performance degradations for longer sequence that has similar acoustic or semantic information at different positions. To address these problems, we propose to use parallel schedule sampling (PSS) and relative positional embedding (RPE) to help transformer generalize to unseen data. Our proposed methods achieve 7% relative improvement for short utterances and 30% absolute gains for long utterances on a 10,000-hour ASR task.
Tasks	Speech Recognition
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00203v1
PDF	https://arxiv.org/pdf/1911.00203v1.pdf
PWC	https://paperswithcode.com/paper/improving-generalization-of-transformer-for
Repo
Framework

A Hybrid Precipitation Prediction Method based on Multicellular Gene Expression Programming


Title	A Hybrid Precipitation Prediction Method based on Multicellular Gene Expression Programming
Authors	Hongya Li, Yuzhong Peng, Chuyan Deng, Yonghua Pan, Daoqing Gong, Hao Zhang
Abstract	Prompt and accurate precipitation forecast is very important for development management of regional water resource, flood disaster prevention and people’s daily activity and production plan; however, non-linear and nonstationary characteristics of precipitation data and noise seriously affect forecast accuracy. This paper combines multicellular gene expression programming with more powerful function mining ability and wavelet analysis with more powerful denoising and extracting data fine feature capability for precipitation forecast modeling, proposing to estimate meteorological precipitation with WTGEPRP algorithm. Comparative result for simulation experiment with actual precipitation data in Zhengzhou, Nanning and Melbourne in Australia indicated that: fitting and forecasting performance of WTGEPRP algorithm is better than the algorithm Multicellular Gene Expression Programming-based Hybrid Model for Precipitation Prediction Coupled with EMD, Supporting Vector Regression, BP Neural Network, Multicellular Gene Expression Programming and Gene Expression Programming, and has good application prospect.
Tasks	Denoising
Published	2019-04-01
URL	https://arxiv.org/abs/1906.08852v1
PDF	https://arxiv.org/pdf/1906.08852v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-precipitation-prediction-method
Repo
Framework

Fraud Detection in Networks: State-of-the-art


Title	Fraud Detection in Networks: State-of-the-art
Authors	Paul Irofti, Andrei Patrascu, Andra Baltoiu
Abstract	Financial fraud detection represents the challenge of finding anomalies in networks of financial transactions. In general, anomaly detection is the problem of distinguishing between normal data samples with well defined patterns or signatures and those that do not conform to the expected profiles. The fraudulent behavior in money laundering may manifest itself through unusual patterns in financial transaction networks. Most commonly, these networks are represented as attributed graphs, with numerical features complementing relational information. We present a survey on anomaly detection techniques used for fraud detection that exploit both the graph structure underlying the data and the contextual information contained in the attributes.
Tasks	Anomaly Detection, Fraud Detection
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11299v2
PDF	https://arxiv.org/pdf/1910.11299v2.pdf
PWC	https://paperswithcode.com/paper/fraud-detection-in-networks-state-of-the-art
Repo
Framework

Deep learning guided Android malware and anomaly detection


Title	Deep learning guided Android malware and anomaly detection
Authors	Nikola Milosevic, Junfan Huang
Abstract	In the past decade, the cyber-crime related to mobile devices has increased. Mobile devices, especially the ones running on Android operating system are particularly interesting to malware creators, as the users often keep the biggest amount of personal information on their mobile devices, such as their contacts, social media profiles, emails, and bank accounts. Both dynamic and static malware analysis is necessary to prevent and detect malware, as both techniques have their benefits and shortcomings. In this paper, we propose a deep learning technique that relies on LSTM and encoder-decoder neural network architectures for dynamic malware analysis based on CPU, memory and battery usage. The proposed system is able to detect and notify users about anomalies in system that is likely consequence of malware behaviour. The method was implemented as a part of OWASP Seraphimdroids anti-malware mechanism and notifies users about anomalies on their devices. The method proved to perform with an F1-score of 79.2%.
Tasks	Anomaly Detection
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10660v1
PDF	https://arxiv.org/pdf/1910.10660v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-guided-android-malware-and
Repo
Framework

Unreliable Multi-Armed Bandits: A Novel Approach to Recommendation Systems


Title	Unreliable Multi-Armed Bandits: A Novel Approach to Recommendation Systems
Authors	Aditya Narayan Ravi, Pranav Poduval, Dr. Sharayu Moharir
Abstract	We use a novel modification of Multi-Armed Bandits to create a new model for recommendation systems. We model the recommendation system as a bandit seeking to maximize reward by pulling on arms with unknown rewards. The catch however is that this bandit can only access these arms through an unreliable intermediate that has some level of autonomy while choosing its arms. For example, in a streaming website the user has a lot of autonomy while choosing content they want to watch. The streaming sites can use targeted advertising as a means to bias opinions of these users. Here the streaming site is the bandit aiming to maximize reward and the user is the unreliable intermediate. We model the intermediate as accessing states via a Markov chain. The bandit is allowed to perturb this Markov chain. We prove fundamental theorems for this setting after which we show a close-to-optimal Explore-Commit algorithm.
Tasks	Multi-Armed Bandits, Recommendation Systems
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06239v1
PDF	https://arxiv.org/pdf/1911.06239v1.pdf
PWC	https://paperswithcode.com/paper/unreliable-multi-armed-bandits-a-novel
Repo
Framework

Photoshopping Colonoscopy Video Frames


Title	Photoshopping Colonoscopy Video Frames
Authors	Yuyuan Liu, Yu Tian, Gabriel Maicas, Leonardo Z. C. T. Pu, Rajvinder Singh, Johan W. Verjans, Gustavo Carneiro
Abstract	The automatic detection of frames containing polyps from a colonoscopy video sequence is an important first step for a fully automated colonoscopy analysis tool. Typically, such detection system is built using a large annotated data set of frames with and without polyps, which is expensive to be obtained. In this paper, we introduce a new system that detects frames containing polyps as anomalies from a distribution of frames from exams that do not contain any polyps. The system is trained using a one-class training set consisting of colonoscopy frames without polyps – such training set is considerably less expensive to obtain, compared to the 2-class data set mentioned above. During inference, the system is only able to reconstruct frames without polyps, and when it tries to reconstruct a frame with polyp, it automatically removes (i.e., photoshop) it from the frame – the difference between the input and reconstructed frames is used to detect frames with polyps. We name our proposed model as anomaly detection generative adversarial network (ADGAN), comprising a dual GAN with two generators and two discriminators. We show that our proposed approach achieves the state-of-the-art result on this data set, compared with recently proposed anomaly detection systems.
Tasks	Anomaly Detection
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10345v1
PDF	https://arxiv.org/pdf/1910.10345v1.pdf
PWC	https://paperswithcode.com/paper/photoshopping-colonoscopy-video-frames
Repo
Framework

Disease classification of macular Optical Coherence Tomography scans using deep learning software: validation on independent, multi-centre data


Title	Disease classification of macular Optical Coherence Tomography scans using deep learning software: validation on independent, multi-centre data
Authors	Kanwal K. Bhatia, Mark S. Graham, Louise Terry, Ashley Wood, Paris Tranos, Sameer Trikha, Nicolas Jaccard
Abstract	Purpose: To evaluate Pegasus-OCT, a clinical decision support software for the identification of features of retinal disease from macula OCT scans, across heterogenous populations involving varying patient demographics, device manufacturers, acquisition sites and operators. Methods: 5,588 normal and anomalous macular OCT volumes (162,721 B-scans), acquired at independent centres in five countries, were processed using the software. Results were evaluated against ground truth provided by the dataset owners. Results: Pegasus-OCT performed with AUROCs of at least 98% for all datasets in the detection of general macular anomalies. For scans of sufficient quality, the AUROCs for general AMD and DME detection were found to be at least 99% and 98%, respectively. Conclusions: The ability of a clinical decision support system to cater for different populations is key to its adoption. Pegasus-OCT was shown to be able to detect AMD, DME and general anomalies in OCT volumes acquired across multiple independent sites with high performance. Its use thus offers substantial promise, with the potential to alleviate the burden of growing demand in eye care services caused by retinal disease.
Tasks
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05164v1
PDF	https://arxiv.org/pdf/1907.05164v1.pdf
PWC	https://paperswithcode.com/paper/disease-classification-of-macular-optical
Repo
Framework

Adversarial Anomaly Detection for Marked Spatio-Temporal Streaming Data


Title	Adversarial Anomaly Detection for Marked Spatio-Temporal Streaming Data
Authors	Shixiang Zhu, Henry Shaowu Yuchi, Yao Xie
Abstract	Spatio-temporal event data are becoming increasingly available in a wide variety of applications, such as electronic transaction records, social network data, and crime data. How to efficiently detect anomalies in these dynamic systems using these streaming event data? We propose a novel anomaly detection framework for such event data combining the Long short-term memory (LSTM) and marked spatio-temporal point processes. The detection procedure can be computed in an online and distributed fashion via feeding the streaming data through an LSTM and a neural network-based discriminator. We study the false-alarm-rate and detection delay using theory and simulation and show that it can achieve weak signal detection by aggregating local statistics over time and networks. Finally, we demonstrate the good performance using real-world datasets.
Tasks	Anomaly Detection, Point Processes
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09161v1
PDF	https://arxiv.org/pdf/1910.09161v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-anomaly-detection-for-marked
Repo
Framework

Mining Minimal Map-Segments for Visual Place Classifiers


Title	Mining Minimal Map-Segments for Visual Place Classifiers
Authors	Tanaka Kanji
Abstract	In visual place recognition (VPR), map segmentation (MS) is a preprocessing technique used to partition a given view-sequence map into place classes (i.e., map segments) so that each class has good place-specific training images for a visual place classifier (VPC). Existing approaches to MS implicitly/explicitly suppose that map segments have a certain size, or individual map segments are balanced in size. However, recent VPR systems showed that very small important map segments (minimal map segments) often suffice for VPC, and the remaining large unimportant portion of the map should be discarded to minimize map maintenance cost. Here, a new MS algorithm that can mine minimal map segments from a large view-sequence map is presented. To solve the inherently NP hard problem, MS is formulated as a video-segmentation problem and the efficient point-trajectory based paradigm of video segmentation is used. The proposed map representation was implemented with three types of VPC: deep convolutional neural network, bag-of-words, and object class detector, and each was integrated into a Monte Carlo localization algorithm (MCL) within a topometric VPR framework. Experiments using the publicly available NCLT dataset thoroughly investigate the efficacy of MS in terms of VPR performance.
Tasks	Video Semantic Segmentation, Visual Place Recognition
Published	2019-09-15
URL	https://arxiv.org/abs/1909.09594v1
PDF	https://arxiv.org/pdf/1909.09594v1.pdf
PWC	https://paperswithcode.com/paper/mining-minimal-map-segments-for-visual-place
Repo
Framework

Generating Black-Box Adversarial Examples for Text Classifiers Using a Deep Reinforced Model


Title	Generating Black-Box Adversarial Examples for Text Classifiers Using a Deep Reinforced Model
Authors	Prashanth Vijayaraghavan, Deb Roy
Abstract	Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by applying adversarial training techniques. In natural language domain, small perturbations in the form of misspellings or paraphrases can drastically change the semantics of the text. We propose a reinforcement learning based approach towards generating adversarial examples in black-box settings. We demonstrate that our method is able to fool well-trained models for (a) IMDB sentiment classification task and (b) AG’s news corpus news categorization task with significantly high success rates. We find that the adversarial examples generated are semantics-preserving perturbations to the original text.
Tasks	Sentiment Analysis
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07873v1
PDF	https://arxiv.org/pdf/1909.07873v1.pdf
PWC	https://paperswithcode.com/paper/generating-black-box-adversarial-examples-for
Repo
Framework

Confidence Intervals for Policy Evaluation in Adaptive Experiments


Title	Confidence Intervals for Policy Evaluation in Adaptive Experiments
Authors	Vitor Hadad, David A. Hirshberg, Ruohan Zhan, Stefan Wager, Susan Athey
Abstract	Adaptive experiments can result in considerable cost savings in multi-armed trials by enabling analysts to quickly focus on the most promising alternatives. Most existing work on adaptive experiments (which include multi-armed bandits) has focused maximizing the speed at which the analyst can identify the optimal arm and/or minimizing the number of draws from sub-optimal arms. In many scientific settings, however, it is not only of interest to identify the optimal arm, but also to perform a statistical analysis of the data collected from the experiment. Naive approaches to statistical inference with adaptive inference fail because many commonly used statistics (such as sample means or inverse propensity weighting) do not have an asymptotically Gaussian limiting distribution centered on the estimate, and so confidence intervals constructed from these statistics do not have correct coverage. But, as shown in this paper, carefully designed data-adaptive weighting schemes can be used to overcome this issue and restore a relevant central limit theorem, enabling hypothesis testing. We validate the accuracy of the resulting confidence intervals in numerical experiments.
Tasks	Multi-Armed Bandits
Published	2019-11-07
URL	https://arxiv.org/abs/1911.02768v1
PDF	https://arxiv.org/pdf/1911.02768v1.pdf
PWC	https://paperswithcode.com/paper/confidence-intervals-for-policy-evaluation-in
Repo
Framework

Neural Epitome Search for Architecture-Agnostic Network Compression


Title	Neural Epitome Search for Architecture-Agnostic Network Compression
Authors	Daquan Zhou, Xiaojie Jin, Qibin Hou, Kaixin Wang, Jianchao Yang, Jiashi Feng
Abstract	The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNNs). However, the weights sampling strategy of WSNet ishandcrafted and fixed which may severely limit the expression ability of the resultedCNNs and weaken its compression ability. In this work, we present a novel auto-sampling method that is applicable to both 1D and 2D CNNs with significantperformance improvement over WSNet. Specifically, our proposed auto-samplingmethod learns the sampling rules end-to-end instead of being independent of thenetwork architecture design. With such differentiable weight sampling rule learning,the sampling stride and channel selection from the compact set are optimized toachieve better trade-off between model compression rate and performance. Wedemonstrate that at the same compression ratio, our method outperforms WSNetby6.5% on 1D convolution. Moreover, on ImageNet, our method outperformsMobileNetV2 full model by1.47%in classification accuracy with25%FLOPsreduction. With the same backbone architecture as baseline models, our methodeven outperforms some neural architecture search (NAS) based methods such asAMC [2] and MNasNet [3].
Tasks	Model Compression, Neural Architecture Search
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05642v3
PDF	https://arxiv.org/pdf/1907.05642v3.pdf
PWC	https://paperswithcode.com/paper/deep-model-compression-via-filter-auto
Repo
Framework

Modeling Feature Representations for Affective Speech using Generative Adversarial Networks


Title	Modeling Feature Representations for Affective Speech using Generative Adversarial Networks
Authors	Saurabh Sahu, Rahul Gupta, Carol Espy-Wilson
Abstract	Emotion recognition is a classic field of research with a typical setup extracting features and feeding them through a classifier for prediction. On the other hand, generative models jointly capture the distributional relationship between emotions and the feature profiles. Relatively recently, Generative Adversarial Networks (GANs) have surfaced as a new class of generative models and have shown considerable success in modeling distributions in the fields of computer vision and natural language understanding. In this work, we experiment with variants of GAN architectures to generate feature vectors corresponding to an emotion in two ways: (i) A generator is trained with samples from a mixture prior. Each mixture component corresponds to an emotional class and can be sampled to generate features from the corresponding emotion. (ii) A one-hot vector corresponding to an emotion can be explicitly used to generate the features. We perform analysis on such models and also propose different metrics used to measure the performance of the GAN models in their ability to generate realistic synthetic samples. Apart from evaluation on a given dataset of interest, we perform a cross-corpus study where we study the utility of the synthetic samples as additional training data in low resource conditions.
Tasks	Emotion Recognition
Published	2019-10-31
URL	https://arxiv.org/abs/1911.00030v1
PDF	https://arxiv.org/pdf/1911.00030v1.pdf
PWC	https://paperswithcode.com/paper/modeling-feature-representations-for
Repo
Framework

Iterative Construction of Gaussian Process Surrogate Models for Bayesian Inference


Title	Iterative Construction of Gaussian Process Surrogate Models for Bayesian Inference
Authors	Leen Alawieh, Jonathan Goodman, John B. Bell
Abstract	A new algorithm is developed to tackle the issue of sampling non-Gaussian model parameter posterior probability distributions that arise from solutions to Bayesian inverse problems. The algorithm aims to mitigate some of the hurdles faced by traditional Markov Chain Monte Carlo (MCMC) samplers, through constructing proposal probability densities that are both, easy to sample and that provide a better approximation to the target density than a simple Gaussian proposal distribution would. To achieve that, a Gaussian proposal distribution is augmented with a Gaussian Process (GP) surface that helps capture non-linearities in the log-likelihood function. In order to train the GP surface, an iterative approach is adopted for the optimal selection of points in parameter space. Optimality is sought by maximizing the information gain of the GP surface using a minimum number of forward model simulation runs. The accuracy of the GP-augmented surface approximation is assessed in two ways. The first consists of comparing predictions obtained from the approximate surface with those obtained through running the actual simulation model at hold-out points in parameter space. The second consists of a measure based on the relative variance of sample weights obtained from sampling the approximate posterior probability distribution of the model parameters. The efficacy of this new algorithm is tested on inferring reaction rate parameters in a 3-node and 6-node network toy problems, which imitate idealized reaction networks in combustion applications.
Tasks	Bayesian Inference
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07227v1
PDF	https://arxiv.org/pdf/1911.07227v1.pdf
PWC	https://paperswithcode.com/paper/iterative-construction-of-gaussian-process
Repo
Framework