May 6, 2019

2986 words 15 mins read

Paper Group ANR 354

FLOCK: Combating Astroturfing on Livestreaming Platforms. M3: Scaling Up Machine Learning via Memory Mapping. Self-Organising Maps in Computer Security. Analysis of gradient descent methods with non-diminishing, bounded errors. Incremental Learning for Fully Unsupervised Word Segmentation Using Penalized Likelihood and Model Selection. Fused DNN: A …

FLOCK: Combating Astroturfing on Livestreaming Platforms


Title	FLOCK: Combating Astroturfing on Livestreaming Platforms
Authors	Neil Shah
Abstract	Livestreaming platforms have become increasingly popular in recent years as a means of sharing and advertising creative content. Popular content streamers who attract large viewership to their live broadcasts can earn a living by means of ad revenue, donations and channel subscriptions. Unfortunately, this incentivized popularity has simultaneously resulted in incentive for fraudsters to provide services to astroturf, or artificially inflate viewership metrics by providing fake “live” views to customers. Our work provides a number of major contributions: (a) formulation: we are the first to introduce and characterize the viewbot fraud problem in livestreaming platforms, (b) methodology: we propose FLOCK, a principled and unsupervised method which efficiently and effectively identifies botted broadcasts and their constituent botted views, and (c) practicality: our approach achieves over 98% precision in identifying botted broadcasts and over 90% precision/recall against sizable synthetically generated viewbot attacks on a real-world livestreaming workload of over 16 million views and 92 thousand broadcasts. FLOCK successfully operates on larger datasets in practice and is regularly used at a large, undisclosed livestreaming corporation.
Tasks
Published	2016-10-04
URL	http://arxiv.org/abs/1610.01096v1
PDF	http://arxiv.org/pdf/1610.01096v1.pdf
PWC	https://paperswithcode.com/paper/flock-combating-astroturfing-on-livestreaming
Repo
Framework

M3: Scaling Up Machine Learning via Memory Mapping


Title	M3: Scaling Up Machine Learning via Memory Mapping
Authors	Dezhi Fang, Duen Horng Chau
Abstract	To process data that do not fit in RAM, conventional wisdom would suggest using distributed approaches. However, recent research has demonstrated virtual memory’s strong potential in scaling up graph mining algorithms on a single machine. We propose to use a similar approach for general machine learning. We contribute: (1) our latest finding that memory mapping is also a feasible technique for scaling up general machine learning algorithms like logistic regression and k-means, when data fits in or exceeds RAM (we tested datasets up to 190GB); (2) an approach, called M3, that enables existing machine learning algorithms to work with out-of-core datasets through memory mapping, achieving a speed that is significantly faster than a 4-instance Spark cluster, and comparable to an 8-instance cluster.
Tasks
Published	2016-04-11
URL	http://arxiv.org/abs/1604.03034v1
PDF	http://arxiv.org/pdf/1604.03034v1.pdf
PWC	https://paperswithcode.com/paper/m3-scaling-up-machine-learning-via-memory
Repo
Framework

Self-Organising Maps in Computer Security


Title	Self-Organising Maps in Computer Security
Authors	Jan Feyereisl, Uwe Aickelin
Abstract	Some argue that biologically inspired algorithms are the future of solving difficult problems in computer science. Others strongly believe that the future lies in the exploration of mathematical foundations of problems at hand. The field of computer security tends to accept the latter view as a more appropriate approach due to its more workable validation and verification possibilities. The lack of rigorous scientific practices prevalent in biologically inspired security research does not aid in presenting bio-inspired security approaches as a viable way of dealing with complex security problems. This chapter introduces a biologically inspired algorithm, called the Self Organising Map (SOM), that was developed by Teuvo Kohonen in 1981. Since the algorithm’s inception it has been scrutinised by the scientific community and analysed in more than 4000 research papers, many of which dealt with various computer security issues, from anomaly detection, analysis of executables all the way to wireless network monitoring. In this chapter a review of security related SOM research undertaken in the past is presented and analysed. The algorithm’s biological analogies are detailed and the author’s view on the future possibilities of this successful bio-inspired approach are given. The SOM algorithm’s close relation to a number of vital functions of the human brain and the emergence of multi-core computer architectures are the two main reasons behind our assumption that the future of the SOM algorithm and its variations is promising, notably in the field of computer security.
Tasks	Anomaly Detection
Published	2016-08-05
URL	http://arxiv.org/abs/1608.01668v1
PDF	http://arxiv.org/pdf/1608.01668v1.pdf
PWC	https://paperswithcode.com/paper/self-organising-maps-in-computer-security
Repo
Framework

Analysis of gradient descent methods with non-diminishing, bounded errors


Title	Analysis of gradient descent methods with non-diminishing, bounded errors
Authors	Arunselvan Ramaswamy, Shalabh Bhatnagar
Abstract	The main aim of this paper is to provide an analysis of gradient descent (GD) algorithms with gradient errors that do not necessarily vanish, asymptotically. In particular, sufficient conditions are presented for both stability (almost sure boundedness of the iterates) and convergence of GD with bounded, (possibly) non-diminishing gradient errors. In addition to ensuring stability, such an algorithm is shown to converge to a small neighborhood of the minimum set, which depends on the gradient errors. It is worth noting that the main result of this paper can be used to show that GD with asymptotically vanishing errors indeed converges to the minimum set. The results presented herein are not only more general when compared to previous results, but our analysis of GD with errors is new to the literature to the best of our knowledge. Our work extends the contributions of Mangasarian & Solodov, Bertsekas & Tsitsiklis and Tadic & Doucet. Using our framework, a simple yet effective implementation of GD using simultaneous perturbation stochastic approximations (SP SA), with constant sensitivity parameters, is presented. Another important improvement over many previous results is that there are no `additional’ restrictions imposed on the step-sizes. In machine learning applications where step-sizes are related to learning rates, our assumptions, unlike those of other papers, do not affect these learning rates. Finally, we present experimental results to validate our theory. \|
Tasks
Published	2016-04-01
URL	http://arxiv.org/abs/1604.00151v3
PDF	http://arxiv.org/pdf/1604.00151v3.pdf
PWC	https://paperswithcode.com/paper/analysis-of-gradient-descent-methods-with-non
Repo
Framework

Incremental Learning for Fully Unsupervised Word Segmentation Using Penalized Likelihood and Model Selection


Title	Incremental Learning for Fully Unsupervised Word Segmentation Using Penalized Likelihood and Model Selection
Authors	Ruey-Cheng Chen
Abstract	We present a novel incremental learning approach for unsupervised word segmentation that combines features from probabilistic modeling and model selection. This includes super-additive penalties for addressing the cognitive burden imposed by long word formation, and new model selection criteria based on higher-order generative assumptions. Our approach is fully unsupervised; it relies on a small number of parameters that permits flexible modeling and a mechanism that automatically learns parameters from the data. Through experimentation, we show that this intricate design has led to top-tier performance in both phonemic and orthographic word segmentation.
Tasks	Model Selection
Published	2016-07-20
URL	http://arxiv.org/abs/1607.05822v2
PDF	http://arxiv.org/pdf/1607.05822v2.pdf
PWC	https://paperswithcode.com/paper/incremental-learning-for-fully-unsupervised
Repo
Framework

Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection


Title	Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection
Authors	Xianzhi Du, Mostafa El-Khamy, Jungwon Lee, Larry S. Davis
Abstract	We propose a deep neural network fusion architecture for fast and robust pedestrian detection. The proposed network fusion architecture allows for parallel processing of multiple networks for speed. A single shot deep convolutional network is trained as a object detector to generate all possible pedestrian candidates of different sizes and occlusions. This network outputs a large variety of pedestrian candidates to cover the majority of ground-truth pedestrians while also introducing a large number of false positives. Next, multiple deep neural networks are used in parallel for further refinement of these pedestrian candidates. We introduce a soft-rejection based network fusion method to fuse the soft metrics from all networks together to generate the final confidence scores. Our method performs better than existing state-of-the-arts, especially when detecting small-size and occluded pedestrians. Furthermore, we propose a method for integrating pixel-wise semantic segmentation network into the network fusion architecture as a reinforcement to the pedestrian detector. The approach outperforms state-of-the-art methods on most protocols on Caltech Pedestrian dataset, with significant boosts on several protocols. It is also faster than all other methods.
Tasks	Pedestrian Detection, Semantic Segmentation
Published	2016-10-11
URL	http://arxiv.org/abs/1610.03466v2
PDF	http://arxiv.org/pdf/1610.03466v2.pdf
PWC	https://paperswithcode.com/paper/fused-dnn-a-deep-neural-network-fusion
Repo
Framework

Learning Discriminative Features with Class Encoder


Title	Learning Discriminative Features with Class Encoder
Authors	Hailin Shi, Xiangyu Zhu, Zhen Lei, Shengcai Liao, Stan Z. Li
Abstract	Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the application of auto-encoders is usually limited to small, well aligned images. In this paper, we incorporate the supervised information to propose a novel formulation, namely class-encoder, whose training objective is to reconstruct a sample from another one of which the labels are identical. Class-encoder aims to minimize the intra-class variations in the feature space, and to learn a good discriminative manifolds on a class scale. We impose the class-encoder as a constraint into the softmax for better supervised training, and extend the reconstruction on feature-level to tackle the parameter size issue and translation issue. The experiments show that the class-encoder helps to improve the performance on benchmarks of classification and face recognition. This could also be a promising direction for fast training of face recognition models.
Tasks	Face Recognition
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02424v1
PDF	http://arxiv.org/pdf/1605.02424v1.pdf
PWC	https://paperswithcode.com/paper/learning-discriminative-features-with-class
Repo
Framework

Text Summarization using Deep Learning and Ridge Regression


Title	Text Summarization using Deep Learning and Ridge Regression
Authors	Karthik Bangalore Mani
Abstract	We develop models and extract relevant features for automatic text summarization and investigate the performance of different models on the DUC 2001 dataset. Two different models were developed, one being a ridge regressor and the other one was a multi-layer perceptron. The hyperparameters were varied and their performance were noted. We segregated the summarization task into 2 main steps, the first being sentence ranking and the second step being sentence selection. In the first step, given a document, we sort the sentences based on their Importance, and in the second step, in order to obtain non-redundant sentences, we weed out the sentences that are have high similarity with the previously selected sentences.
Tasks	Text Summarization
Published	2016-12-26
URL	http://arxiv.org/abs/1612.08333v4
PDF	http://arxiv.org/pdf/1612.08333v4.pdf
PWC	https://paperswithcode.com/paper/text-summarization-using-deep-learning-and
Repo
Framework

The block-Poisson estimator for optimally tuned exact subsampling MCMC


Title	The block-Poisson estimator for optimally tuned exact subsampling MCMC
Authors	Matias Quiroz, Minh-Ngoc Tran, Mattias Villani, Robert Kohn, Khue-Dung Dang
Abstract	Speeding up Markov Chain Monte Carlo (MCMC) for datasets with many observations by data subsampling has recently received considerable attention in the literature. The currently available methods are either approximate, highly inefficient or limited to small dimensional models. We propose a pseudo-marginal MCMC method that estimates the likelihood by data subsampling using a block-Poisson estimator. The estimator is a product of Poisson estimators, each based on an independent subset of the observations. The construction allows us to update a subset of the blocks in each MCMC iteration, thereby inducing a controllable correlation between the estimates at the current and proposed draw in the Metropolis-Hastings ratio. This makes it possible to use highly variable likelihood estimators without adversely affecting the sampling efficiency. Poisson estimators are unbiased but not necessarily positive. We therefore follow Lyne et al. (2015) and run the MCMC on the absolute value of the estimator and use an importance sampling correction for occasionally negative likelihood estimates to estimate expectations of any function of the parameters. We provide analytically derived guidelines to select the optimal tuning parameters for the algorithm by minimizing the variance of the importance sampling corrected estimator per unit of computing time. The guidelines are derived under idealized conditions, but are demonstrated to be quite accurate in empirical experiments. The guidelines apply to any pseudo-marginal algorithm if the likelihood is estimated by the block-Poisson estimator, including the class of doubly intractable problems in Lyne et al. (2015). We illustrate the method in a logistic regression example and find dramatic improvements compared to regular MCMC without subsampling and a popular exact subsampling approach recently proposed in the literature.
Tasks
Published	2016-03-27
URL	http://arxiv.org/abs/1603.08232v5
PDF	http://arxiv.org/pdf/1603.08232v5.pdf
PWC	https://paperswithcode.com/paper/the-block-poisson-estimator-for-optimally
Repo
Framework

Zero-Shot Learning posed as a Missing Data Problem


Title	Zero-Shot Learning posed as a Missing Data Problem
Authors	Bo Zhao, Botong Wu, Tianfu Wu, Yizhou Wang
Abstract	This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem. Specifically, most existing ZSL methods focus on learning mapping functions from the image feature space to the label embedding space. Whereas, the proposed method explores a simple yet effective transductive framework in the reverse way -– our method estimates data distribution of unseen classes in the image feature space by transferring knowledge from the label embedding space. In experiments, our method outperforms the state-of-the-art on two popular datasets.
Tasks	Zero-Shot Learning
Published	2016-12-02
URL	http://arxiv.org/abs/1612.00560v2
PDF	http://arxiv.org/pdf/1612.00560v2.pdf
PWC	https://paperswithcode.com/paper/zero-shot-learning-posed-as-a-missing-data
Repo
Framework

Conformal Predictors for Compound Activity Prediction


Title	Conformal Predictors for Compound Activity Prediction
Authors	Paolo Toccacheli, Ilia Nouretdinov, Alexander Gammerman
Abstract	The paper presents an application of Conformal Predictors to a chemoinformatics problem of identifying activities of chemical compounds. The paper addresses some specific challenges of this domain: a large number of compounds (training examples), high-dimensionality of feature space, sparseness and a strong class imbalance. A variant of conformal predictors called Inductive Mondrian Conformal Predictor is applied to deal with these challenges. Results are presented for several non-conformity measures (NCM) extracted from underlying algorithms and different kernels. A number of performance measures are used in order to demonstrate the flexibility of Inductive Mondrian Conformal Predictors in dealing with such a complex set of data. Keywords: Conformal Prediction, Confidence Estimation, Chemoinformatics, Non-Conformity Measure.
Tasks	Activity Prediction
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04506v1
PDF	http://arxiv.org/pdf/1603.04506v1.pdf
PWC	https://paperswithcode.com/paper/conformal-predictors-for-compound-activity
Repo
Framework

Data fluidity in DARIAH – pushing the agenda forward


Title	Data fluidity in DARIAH – pushing the agenda forward
Authors	Laurent Romary, Mike Mertens, Anne Baillot
Abstract	This paper provides both an update concerning the setting up of the European DARIAH infrastructure and a series of strong action lines related to the development of a data centred strategy for the humanities in the coming years. In particular we tackle various aspect of data management: data hosting, the setting up of a DARIAH seal of approval, the establishment of a charter between cultural heritage institutions and scholars and finally a specific view on certification mechanisms for data.
Tasks
Published	2016-03-10
URL	http://arxiv.org/abs/1603.03170v2
PDF	http://arxiv.org/pdf/1603.03170v2.pdf
PWC	https://paperswithcode.com/paper/data-fluidity-in-dariah-pushing-the-agenda
Repo
Framework

Towards Accurate Word Segmentation for Chinese Patents


Title	Towards Accurate Word Segmentation for Chinese Patents
Authors	Si Li, Nianwen Xue
Abstract	A patent is a property right for an invention granted by the government to the inventor. An invention is a solution to a specific technological problem. So patents often have a high concentration of scientific and technical terms that are rare in everyday language. The Chinese word segmentation model trained on currently available everyday language data sets performs poorly because it cannot effectively recognize these scientific and technical terms. In this paper we describe a pragmatic approach to Chinese word segmentation on patents where we train a character-based semi-supervised sequence labeling model by extracting features from a manually segmented corpus of 142 patents, enhanced with information extracted from the Chinese TreeBank. Experiments show that the accuracy of our model reached 95.08% (F1 score) on a held-out test set and 96.59% on development set, compared with an F1 score of 91.48% on development set if the model is trained on the Chinese TreeBank. We also experimented with some existing domain adaptation techniques, the results show that the amount of target domain data and the selected features impact the performance of the domain adaptation techniques.
Tasks	Chinese Word Segmentation, Domain Adaptation
Published	2016-11-30
URL	http://arxiv.org/abs/1611.10038v1
PDF	http://arxiv.org/pdf/1611.10038v1.pdf
PWC	https://paperswithcode.com/paper/towards-accurate-word-segmentation-for
Repo
Framework

Weakly Supervised Cascaded Convolutional Networks


Title	Weakly Supervised Cascaded Convolutional Networks
Authors	Ali Diba, Vivek Sharma, Ali Pazandeh, Hamed Pirsiavash, Luc Van Gool
Abstract	Object detection is a challenging task in visual understanding domain, and even more so if the supervision is to be weak. Recently, few efforts to handle the task without expensive human annotations is established by promising deep neural network. A new architecture of cascaded networks is proposed to learn a convolutional neural network (CNN) under such conditions. We introduce two such architectures, with either two cascade stages or three which are trained in an end-to-end pipeline. The first stage of both architectures extracts best candidate of class specific region proposals by training a fully convolutional network. In the case of the three stage architecture, the middle stage provides object segmentation, using the output of the activation maps of first stage. The final stage of both architectures is a part of a convolutional neural network that performs multiple instance learning on proposals extracted in the previous stage(s). Our experiments on the PASCAL VOC 2007, 2010, 2012 and large scale object datasets, ILSVRC 2013, 2014 datasets show improvements in the areas of weakly-supervised object detection, classification and localization.
Tasks	Multiple Instance Learning, Object Detection, Semantic Segmentation, Weakly Supervised Object Detection
Published	2016-11-24
URL	http://arxiv.org/abs/1611.08258v1
PDF	http://arxiv.org/pdf/1611.08258v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-cascaded-convolutional
Repo
Framework


Title	How smart does your profile image look? Estimating intelligence from social network profile images
Authors	Xingjie Wei, David Stillwell
Abstract	Profile images on social networks are users’ opportunity to present themselves and to affect how others judge them. We examine what Facebook images say about users’ perceived and measured intelligence. 1,122 Facebook users completed a matrices intelligence test and shared their current Facebook profile image. Strangers also rated the images for perceived intelligence. We use automatically extracted image features to predict both measured and perceived intelligence. Intelligence estimation from images is a difficult task even for humans, but experimental results show that human accuracy can be equalled using computing methods. We report the image features that predict both measured and perceived intelligence, and highlight misleading features such as “smiling” and “wearing glasses” that are correlated with perceived but not measured intelligence. Our results give insights into inaccurate stereotyping from profile images and also have implications for privacy, especially since in most social networks profile images are public by default.
Tasks
Published	2016-06-29
URL	http://arxiv.org/abs/1606.09264v3
PDF	http://arxiv.org/pdf/1606.09264v3.pdf
PWC	https://paperswithcode.com/paper/how-smart-does-your-profile-image-look
Repo
Framework