October 16, 2019

3177 words 15 mins read

Paper Group ANR 1091

Towards Decentralization of Social Media. Constant Step Size Stochastic Gradient Descent for Probabilistic Modeling. Near-Linear Time Local Polynomial Nonparametric Estimation. Fast Decoding in Sequence Models using Discrete Latent Variables. Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access. Travel Speed Prediction with a Hierarchic …


Title	Towards Decentralization of Social Media
Authors	Sarang Mahajan, Amey Kasar
Abstract	Facebook uses Artificial Intelligence for targeting users with advertisements based on the events in which they engage like sharing, liking, making comments, posts by a friend, a group creation, etcetera. Each user interacts with these events in different ways, thus receiving different recommendations curated by Facebook’s intelligent systems. Facebook segregates its users into chambers, fragmenting them into communities. The technology has completely changed the marketing domain. It is however caught in a race for our finite attention with a motive to make more and more money. Facebook is not a neutral product. It is programmed to get users addicted to it with a goal of gaining added information about the users and optimizing the recommendations provided to the users according to his or her preferences. This paper delineates how Facebook’s recommendation system works and presents three methods to safeguard human vulnerabilities exploited by Facebook and other corporations.
Tasks
Published	2018-11-28
URL	http://arxiv.org/abs/1811.11522v1
PDF	http://arxiv.org/pdf/1811.11522v1.pdf
PWC	https://paperswithcode.com/paper/towards-decentralization-of-social-media
Repo
Framework

Constant Step Size Stochastic Gradient Descent for Probabilistic Modeling


Title	Constant Step Size Stochastic Gradient Descent for Probabilistic Modeling
Authors	Dmitry Babichev, Francis Bach
Abstract	Stochastic gradient methods enable learning probabilistic models from large amounts of data. While large step-sizes (learning rates) have shown to be best for least-squares (e.g., Gaussian noise) once combined with parameter averaging, these are not leading to convergent algorithms in general. In this paper, we consider generalized linear models, that is, conditional models based on exponential families. We propose averaging moment parameters instead of natural parameters for constant-step-size stochastic gradient descent. For finite-dimensional models, we show that this can sometimes (and surprisingly) lead to better predictions than the best linear model. For infinite-dimensional models, we show that it always converges to optimal predictions, while averaging natural parameters never does. We illustrate our findings with simulations on synthetic data and classical benchmarks with many observations.
Tasks
Published	2018-04-16
URL	http://arxiv.org/abs/1804.05567v2
PDF	http://arxiv.org/pdf/1804.05567v2.pdf
PWC	https://paperswithcode.com/paper/constant-step-size-stochastic-gradient
Repo
Framework

Near-Linear Time Local Polynomial Nonparametric Estimation


Title	Near-Linear Time Local Polynomial Nonparametric Estimation
Authors	Yining Wang, Yi Wu, Simon S. Du
Abstract	Local polynomial regression (Fan & Gijbels, 1996) is an important class of methods for nonparametric density estimation and regression problems. However, straightforward implementation of local polynomial regression has quadratic time complexity which hinders its applicability in large-scale data analysis. In this paper, we significantly accelerate the computation of local polynomial estimates by novel applications of multi-dimensional binary indexed trees (Fenwick, 1994). Both time and space complexities of our proposed algorithm are nearly linear in the number of inputs. Simulation results confirm the efficiency and effectiveness of our approach.
Tasks	Density Estimation
Published	2018-02-26
URL	http://arxiv.org/abs/1802.09578v1
PDF	http://arxiv.org/pdf/1802.09578v1.pdf
PWC	https://paperswithcode.com/paper/near-linear-time-local-polynomial
Repo
Framework

Fast Decoding in Sequence Models using Discrete Latent Variables


Title	Fast Decoding in Sequence Models using Discrete Latent Variables
Authors	Łukasz Kaiser, Aurko Roy, Ashish Vaswani, Niki Parmar, Samy Bengio, Jakob Uszkoreit, Noam Shazeer
Abstract	Autoregressive sequence models based on deep neural networks, such as RNNs, Wavenet and the Transformer attain state-of-the-art results on many tasks. However, they are difficult to parallelize and are thus slow at processing long sequences. RNNs lack parallelism both during training and decoding, while architectures like WaveNet and Transformer are much more parallelizable during training, yet still operate sequentially during decoding. Inspired by [arxiv:1711.00937], we present a method to extend sequence models using discrete latent variables that makes decoding much more parallelizable. We first auto-encode the target sequence into a shorter sequence of discrete latent variables, which at inference time is generated autoregressively, and finally decode the output sequence from this shorter latent sequence in parallel. To this end, we introduce a novel method for constructing a sequence of discrete latent variables and compare it with previously introduced methods. Finally, we evaluate our model end-to-end on the task of neural machine translation, where it is an order of magnitude faster at decoding than comparable autoregressive models. While lower in BLEU than purely autoregressive models, our model achieves higher scores than previously proposed non-autoregressive translation models.
Tasks	Machine Translation
Published	2018-03-09
URL	http://arxiv.org/abs/1803.03382v6
PDF	http://arxiv.org/pdf/1803.03382v6.pdf
PWC	https://paperswithcode.com/paper/fast-decoding-in-sequence-models-using
Repo
Framework

Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access


Title	Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access
Authors	Meghana Bande, Venugopal V. Veeravalli
Abstract	A multi-user multi-armed bandit (MAB) framework is used to develop algorithms for uncoordinated spectrum access. The number of users is assumed to be unknown to each user. A stochastic setting is first considered, where the rewards on a channel are the same for each user. In contrast to prior work, it is assumed that the number of users can possibly exceed the number of channels, and that rewards can be non-zero even under collisions. The proposed algorithm consists of an estimation phase and an allocation phase. It is shown that if every user adopts the algorithm, the system wide regret is constant with time with high probability. The regret guarantees hold for any number of users and channels, in particular, even when the number of users is less than the number of channels. Next, an adversarial multi-user MAB framework is considered, where the rewards on the channels are user-dependent. It is assumed that the number of users is less than the number of channels, and that the users receive zero reward on collision. The proposed algorithm combines the Exp3.P algorithm developed in prior work for single user adversarial bandits with a collision resolution mechanism to achieve sub-linear regret. It is shown that if every user employs the proposed algorithm, the system wide regret is of the order $O(T^\frac{3}{4})$ over a horizon of time $T$. The algorithms in both stochastic and adversarial scenarios are extended to the dynamic case where the number of users in the system evolves over time and are shown to lead to sub-linear regret.
Tasks	Multi-Armed Bandits
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00867v5
PDF	http://arxiv.org/pdf/1807.00867v5.pdf
PWC	https://paperswithcode.com/paper/multi-user-multi-armed-bandits-for
Repo
Framework

Travel Speed Prediction with a Hierarchical Convolutional Neural Network and Long Short-Term Memory Model Framework


Title	Travel Speed Prediction with a Hierarchical Convolutional Neural Network and Long Short-Term Memory Model Framework
Authors	Wei Wang, Xucheng Li
Abstract	Advanced travel information and warning, if provided accurately, can help road users avoid traffic congestion through dynamic route planning and behavior change. It also enables traffic control centres mitigate the impact of congestion by activating Intelligent Transport System (ITS) proactively. Deep learning has become increasingly popular in recent years, following a surge of innovative GPU technology, high-resolution, big datasets and thriving machine learning algorithms. However, there are few examples exploiting this emerging technology to develop applications for traffic prediction. This is largely due to the difficulty in capturing random, seasonal, non-linear, and spatio-temporal correlated nature of traffic data. In this paper, we propose a data-driven modelling approach with a novel hierarchical D-CLSTM-t deep learning model for short-term traffic speed prediction, a framework combined with convolutional neural network (CNN) and long short-term memory (LSTM) models. A deep CNN model is employed to learn the spatio-temporal traffic patterns of the input graphs, which are then fed into a deep LSTM model for sequence learning. To capture traffic seasonal variations, time of the day and day of the week indicators are fused with trained features. The model is trained end-to-end to predict travel speed in 15 to 90 minutes in the future. We compare the model performance against other baseline models including CNN, LGBM, LSTM, and traditional speed-flow curves. Experiment results show that the D-CLSTM-t outperforms other models considerably. Model tests show that speed upstream also responds sensibly to a sudden accident occurring downstream. Our D-CLSTM-t model framework is also highly scalable for future extension such as for network-wide traffic prediction, which can also be improved by including additional features such as weather, long term seasonality and accident information.
Tasks	Traffic Prediction
Published	2018-09-06
URL	http://arxiv.org/abs/1809.01887v2
PDF	http://arxiv.org/pdf/1809.01887v2.pdf
PWC	https://paperswithcode.com/paper/travel-speed-prediction-with-a-hierarchical
Repo
Framework

Call Detail Records Driven Anomaly Detection and Traffic Prediction in Mobile Cellular Networks


Title	Call Detail Records Driven Anomaly Detection and Traffic Prediction in Mobile Cellular Networks
Authors	Kashif Sultan, Hazrat Ali, Zhongshan Zhang
Abstract	Mobile networks possess information about the users as well as the network. Such information is useful for making the network end-to-end visible and intelligent. Big data analytics can efficiently analyze user and network information, unearth meaningful insights with the help of machine learning tools. Utilizing big data analytics and machine learning, this work contributes in three ways. First, we utilize the call detail records (CDR) data to detect anomalies in the network. For authentication and verification of anomalies, we use k-means clustering, an unsupervised machine learning algorithm. Through effective detection of anomalies, we can proceed to suitable design for resource distribution as well as fault detection and avoidance. Second, we prepare anomaly-free data by removing anomalous activities and train a neural network model. By passing anomaly and anomaly-free data through this model, we observe the effect of anomalous activities in training of the model and also observe mean square error of anomaly and anomaly free data. Lastly, we use an autoregressive integrated moving average (ARIMA) model to predict future traffic for a user. Through simple visualization, we show that anomaly free data better generalizes the learning models and performs better on prediction task.
Tasks	Anomaly Detection, Fault Detection, Traffic Prediction
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11545v1
PDF	http://arxiv.org/pdf/1807.11545v1.pdf
PWC	https://paperswithcode.com/paper/call-detail-records-driven-anomaly-detection
Repo
Framework

Incorporating GAN for Negative Sampling in Knowledge Representation Learning


Title	Incorporating GAN for Negative Sampling in Knowledge Representation Learning
Authors	Peifeng Wang, Shuangyin Li, Rong pan
Abstract	Knowledge representation learning aims at modeling knowledge graph by encoding entities and relations into a low dimensional space. Most of the traditional works for knowledge embedding need negative sampling to minimize a margin-based ranking loss. However, those works construct negative samples through a random mode, by which the samples are often too trivial to fit the model efficiently. In this paper, we propose a novel knowledge representation learning framework based on Generative Adversarial Networks (GAN). In this GAN-based framework, we take advantage of a generator to obtain high-quality negative samples. Meanwhile, the discriminator in GAN learns the embeddings of the entities and relations in knowledge graph. Thus, we can incorporate the proposed GAN-based framework into various traditional models to improve the ability of knowledge representation learning. Experimental results show that our proposed GAN-based framework outperforms baselines on triplets classification and link prediction tasks.
Tasks	Link Prediction, Representation Learning
Published	2018-09-23
URL	http://arxiv.org/abs/1809.11017v1
PDF	http://arxiv.org/pdf/1809.11017v1.pdf
PWC	https://paperswithcode.com/paper/incorporating-gan-for-negative-sampling-in
Repo
Framework

Fusing Video and Inertial Sensor Data for Walking Person Identification


Title	Fusing Video and Inertial Sensor Data for Walking Person Identification
Authors	Yuehong Huang, Yu-Chee Tseng
Abstract	An autonomous computer system (such as a robot) typically needs to identify, locate, and track persons appearing in its sight. However, most solutions have their limitations regarding efficiency, practicability, or environmental constraints. In this paper, we propose an effective and practical system which combines video and inertial sensors for person identification (PID). Persons who do different activities are easy to identify. To show the robustness and potential of our system, we propose a walking person identification (WPID) method to identify persons walking at the same time. By comparing features derived from both video and inertial sensor data, we can associate sensors in smartphones with human objects in videos. Results show that the correctly identified rate of our WPID method can up to 76% in 2 seconds.
Tasks	Person Identification
Published	2018-02-20
URL	http://arxiv.org/abs/1802.07021v1
PDF	http://arxiv.org/pdf/1802.07021v1.pdf
PWC	https://paperswithcode.com/paper/fusing-video-and-inertial-sensor-data-for
Repo
Framework

A Deep Learning Algorithm for One-step Contour Aware Nuclei Segmentation of Histopathological Images


Title	A Deep Learning Algorithm for One-step Contour Aware Nuclei Segmentation of Histopathological Images
Authors	Yuxin Cui, Guiying Zhang, Zhonghao Liu, Zheng Xiong, Jianjun Hu
Abstract	This paper addresses the task of nuclei segmentation in high-resolution histopathological images. We propose an auto- matic end-to-end deep neural network algorithm for segmenta- tion of individual nuclei. A nucleus-boundary model is introduced to predict nuclei and their boundaries simultaneously using a fully convolutional neural network. Given a color normalized image, the model directly outputs an estimated nuclei map and a boundary map. A simple, fast and parameter-free post-processing procedure is performed on the estimated nuclei map to produce the final segmented nuclei. An overlapped patch extraction and assembling method is also designed for seamless prediction of nuclei in large whole-slide images. We also show the effectiveness of data augmentation methods for nuclei segmentation task. Our experiments showed our method outperforms prior state-of-the- art methods. Moreover, it is efficient that one 1000X1000 image can be segmented in less than 5 seconds. This makes it possible to precisely segment the whole-slide image in acceptable time
Tasks	Data Augmentation
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02786v1
PDF	http://arxiv.org/pdf/1803.02786v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-algorithm-for-one-step
Repo
Framework

Deep Learning Based Vehicle Make-Model Classification


Title	Deep Learning Based Vehicle Make-Model Classification
Authors	Burak Satar, Ahmet Emir Dirik
Abstract	This paper studies the problems of vehicle make & model classification. Some of the main challenges are reaching high classification accuracy and reducing the annotation time of the images. To address these problems, we have created a fine-grained database using online vehicle marketplaces of Turkey. A pipeline is proposed to combine an SSD (Single Shot Multibox Detector) model with a CNN (Convolutional Neural Network) model to train on the database. In the pipeline, we first detect the vehicles by following an algorithm which reduces the time for annotation. Then, we feed them into the CNN model. It is reached approximately 4% better classification accuracy result than using a conventional CNN model. Next, we propose to use the detected vehicles as ground truth bounding box (GTBB) of the images and feed them into an SSD model in another pipeline. At this stage, it is reached reasonable classification accuracy result without using perfectly shaped GTBB. Lastly, an application is implemented in a use case by using our proposed pipelines. It detects the unauthorized vehicles by comparing their license plate numbers and make & models. It is assumed that license plates are readable.
Tasks
Published	2018-08-23
URL	http://arxiv.org/abs/1809.00953v2
PDF	http://arxiv.org/pdf/1809.00953v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-vehicle-make-model
Repo
Framework

Towards an Understanding of Entity-Oriented Search Intents


Title	Towards an Understanding of Entity-Oriented Search Intents
Authors	Darío Garigliotti, Krisztian Balog
Abstract	Entity-oriented search deals with a wide variety of information needs, from displaying direct answers to interacting with services. In this work, we aim to understand what are prominent entity-oriented search intents and how they can be fulfilled. We develop a scheme of entity intent categories, and use them to annotate a sample of queries. Specifically, we annotate unique query refiners on the level of entity types. We observe that, on average, over half of those refiners seek to interact with a service, while over a quarter of the refiners search for information that may be looked up in a knowledge base.
Tasks
Published	2018-02-22
URL	http://arxiv.org/abs/1802.08010v1
PDF	http://arxiv.org/pdf/1802.08010v1.pdf
PWC	https://paperswithcode.com/paper/towards-an-understanding-of-entity-oriented
Repo
Framework

Integrative Biological Simulation, Neuropsychology, and AI Safety


Title	Integrative Biological Simulation, Neuropsychology, and AI Safety
Authors	Gopal P. Sarma, Adam Safron, Nick J. Hay
Abstract	We describe a biologically-inspired research agenda with parallel tracks aimed at AI and AI safety. The bottom-up component consists of building a sequence of biophysically realistic simulations of simple organisms such as the nematode $Caenorhabditis$ $elegans$, the fruit fly $Drosophila$ $melanogaster$, and the zebrafish $Danio$ $rerio$ to serve as platforms for research into AI algorithms and system architectures. The top-down component consists of an approach to value alignment that grounds AI goal structures in neuropsychology, broadly considered. Our belief is that parallel pursuit of these tracks will inform the development of value-aligned AI systems that have been inspired by embodied organisms with sensorimotor integration. An important set of side benefits is that the research trajectories we describe here are grounded in long-standing intellectual traditions within existing research communities and funding structures. In addition, these research programs overlap with significant contemporary themes in the biological and psychological sciences such as data/model integration and reproducibility.
Tasks
Published	2018-11-07
URL	http://arxiv.org/abs/1811.03493v2
PDF	http://arxiv.org/pdf/1811.03493v2.pdf
PWC	https://paperswithcode.com/paper/integrative-biological-simulation
Repo
Framework

Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard


Title	Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard
Authors	Wouter Bulten, Péter Bándi, Jeffrey Hoven, Rob van de Loo, Johannes Lotz, Nick Weiss, Jeroen van der Laak, Bram van Ginneken, Christina Hulsbergen-van de Kaa, Geert Litjens
Abstract	Prostate cancer (PCa) is graded by pathologists by examining the architectural pattern of cancerous epithelial tissue on hematoxylin and eosin (H&E) stained slides. Given the importance of gland morphology, automatically differentiating between glandular epithelial tissue and other tissues is an important prerequisite for the development of automated methods for detecting PCa. We propose a new method, using deep learning, for automatically segmenting epithelial tissue in digitized prostatectomy slides. We employed immunohistochemistry (IHC) to render the ground truth less subjective and more precise compared to manual outlining on H&E slides, especially in areas with high-grade and poorly differentiated PCa. Our dataset consisted of 102 tissue blocks, including both low and high grade PCa. From each block a single new section was cut, stained with H&E, scanned, restained using P63 and CK8/18 to highlight the epithelial structure, and scanned again. The H&E slides were co-registered to the IHC slides. On a subset of the IHC slides we applied color deconvolution, corrected stain errors manually, and trained a U-Net to perform segmentation of epithelial structures. Whole-slide segmentation masks generated by the IHC U-Net were used to train a second U-Net on H&E. Our system makes precise cell-level segmentations and segments both intact glands as well as individual (tumor) epithelial cells. We achieved an F1-score of 0.895 on a hold-out test set and 0.827 on an external reference set from a different center. We envision this segmentation as being the first part of a fully automated prostate cancer detection and grading pipeline.
Tasks
Published	2018-08-17
URL	http://arxiv.org/abs/1808.05883v2
PDF	http://arxiv.org/pdf/1808.05883v2.pdf
PWC	https://paperswithcode.com/paper/epithelium-segmentation-using-deep-learning
Repo
Framework


Title	Semi-blind source separation with multichannel variational autoencoder
Authors	Hirokazu Kameoka, Li Li, Shota Inoue, Shoji Makino
Abstract	This paper proposes a multichannel source separation technique called the multichannel variational autoencoder (MVAE) method, which uses a conditional VAE (CVAE) to model and estimate the power spectrograms of the sources in a mixture. By training the CVAE using the spectrograms of training examples with source-class labels, we can use the trained decoder distribution as a universal generative model capable of generating spectrograms conditioned on a specified class label. By treating the latent space variables and the class label as the unknown parameters of this generative model, we can develop a convergence-guaranteed semi-blind source separation algorithm that consists of iteratively estimating the power spectrograms of the underlying sources as well as the separation matrices. In experimental evaluations, our MVAE produced better separation performance than a baseline method.
Tasks
Published	2018-08-02
URL	http://arxiv.org/abs/1808.00892v3
PDF	http://arxiv.org/pdf/1808.00892v3.pdf
PWC	https://paperswithcode.com/paper/semi-blind-source-separation-with
Repo
Framework