April 1, 2020

3402 words 16 mins read

Paper Group ANR 484

Learning Occupational Task-Shares Dynamics for the Future of Work. Towards information-rich, logical text generation with knowledge-enhanced neural models. Evaluating image matching methods for book cover identification. Graphs, Convolutions, and Neural Networks. Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games. A Hybrid Stochast …

Learning Occupational Task-Shares Dynamics for the Future of Work


Title	Learning Occupational Task-Shares Dynamics for the Future of Work
Authors	Subhro Das, Sebastian Steffen, Wyatt Clarke, Prabhat Reddy, Erik Brynjolfsson, Martin Fleming
Abstract	The recent wave of AI and automation has been argued to differ from previous General Purpose Technologies (GPTs), in that it may lead to rapid change in occupations’ underlying task requirements and persistent technological unemployment. In this paper, we apply a novel methodology of dynamic task shares to a large dataset of online job postings to explore how exactly occupational task demands have changed over the past decade of AI innovation, especially across high, mid and low wage occupations. Notably, big data and AI have risen significantly among high wage occupations since 2012 and 2016, respectively. We built an ARIMA model to predict future occupational task demands and showcase several relevant examples in Healthcare, Administration, and IT. Such task demands predictions across occupations will play a pivotal role in retraining the workforce of the future.
Tasks
Published	2020-01-28
URL	https://arxiv.org/abs/2002.05655v1
PDF	https://arxiv.org/pdf/2002.05655v1.pdf
PWC	https://paperswithcode.com/paper/learning-occupational-task-shares-dynamics
Repo
Framework

Towards information-rich, logical text generation with knowledge-enhanced neural models


Title	Towards information-rich, logical text generation with knowledge-enhanced neural models
Authors	Hao Wang, Bin Guo, Wei Wu, Zhiwen Yu
Abstract	Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life. However, existing end-to-end neural models suffer from the problem of tending to generate uninformative and generic text because they cannot ground input context with background knowledge. In order to solve this problem, many researchers begin to consider combining external knowledge in text generation systems, namely knowledge-enhanced text generation. The challenges of knowledge enhanced text generation including how to select the appropriate knowledge from large-scale knowledge bases, how to read and understand extracted knowledge, and how to integrate knowledge into generation process. This survey gives a comprehensive review of knowledge-enhanced text generation systems, summarizes research progress to solving these challenges and proposes some open issues and research directions.
Tasks	Text Generation
Published	2020-03-02
URL	https://arxiv.org/abs/2003.00814v1
PDF	https://arxiv.org/pdf/2003.00814v1.pdf
PWC	https://paperswithcode.com/paper/towards-information-rich-logical-text
Repo
Framework

Evaluating image matching methods for book cover identification


Title	Evaluating image matching methods for book cover identification
Authors	Rabie Hachemi, Ikram Achar, Biasi Wiga, Mahfoud Sidi Ali Mebarek
Abstract	Humans are capable of identifying a book only by looking at its cover, but how can computers do the same? In this paper, we explore different feature detectors and matching methods for book cover identification, and compare their performances in terms of both speed and accuracy. This will allow, for example, libraries to develop interactive services based on cover book picture. Only one single image of a cover book needs to be available through a database. Tests have been performed by taking into account different transformations of each book cover image. Encouraging results have been achieved.
Tasks
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05200v1
PDF	https://arxiv.org/pdf/2001.05200v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-image-matching-methods-for-book
Repo
Framework

Graphs, Convolutions, and Neural Networks


Title	Graphs, Convolutions, and Neural Networks
Authors	Fernando Gama, Elvin Isufi, Geert Leus, Alejandro Ribeiro
Abstract	Network data can be conveniently modeled as a graph signal, where data values are assigned to nodes of a graph that describes the underlying network topology. Successful learning from network data is built upon methods that effectively exploit this graph structure. In this work, we overview graph convolutional filters, which are linear, local and distributed operations that adequately leverage the graph structure. We then discuss graph neural networks (GNNs), built upon graph convolutional filters, that have been shown to be powerful nonlinear learning architectures. We show that GNNs are permutation equivariant and stable to changes in the underlying graph topology, allowing them to scale and transfer. We also introduce GNN extensions using edge-varying and autoregressive moving average graph filters and discuss their properties. Finally, we study the use of GNNs in learning decentralized controllers for robot swarm and in addressing the recommender system problem.
Tasks	Recommendation Systems
Published	2020-03-08
URL	https://arxiv.org/abs/2003.03777v1
PDF	https://arxiv.org/pdf/2003.03777v1.pdf
PWC	https://paperswithcode.com/paper/graphs-convolutions-and-neural-networks
Repo
Framework

Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games


Title	Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games
Authors	Edward Hughes, Thomas W. Anthony, Tom Eccles, Joel Z. Leibo, David Balduzzi, Yoram Bachrach
Abstract	Zero-sum games have long guided artificial intelligence research, since they possess both a rich strategy space of best-responses and a clear evaluation metric. What’s more, competition is a vital mechanism in many real-world multi-agent systems capable of generating intelligent innovations: Darwinian evolution, the market economy and the AlphaZero algorithm, to name a few. In two-player zero-sum games, the challenge is usually viewed as finding Nash equilibrium strategies, safeguarding against exploitation regardless of the opponent. While this captures the intricacies of chess or Go, it avoids the notion of cooperation with co-players, a hallmark of the major transitions leading from unicellular organisms to human civilization. Beyond two players, alliance formation often confers an advantage; however this requires trust, namely the promise of mutual cooperation in the face of incentives to defect. Successful play therefore requires adaptation to co-players rather than the pursuit of non-exploitability. Here we argue that a systematic study of many-player zero-sum games is a crucial element of artificial intelligence research. Using symmetric zero-sum matrix games, we demonstrate formally that alliance formation may be seen as a social dilemma, and empirically that na"ive multi-agent reinforcement learning therefore fails to form alliances. We introduce a toy model of economic competition, and show how reinforcement learning may be augmented with a peer-to-peer contract mechanism to discover and enforce alliances. Finally, we generalize our agent model to incorporate temporally-extended contracts, presenting opportunities for further work.
Tasks	Multi-agent Reinforcement Learning
Published	2020-02-27
URL	https://arxiv.org/abs/2003.00799v1
PDF	https://arxiv.org/pdf/2003.00799v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-resolve-alliance-dilemmas-in-many
Repo
Framework

A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning


Title	A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning
Authors	Nhan H. Pham, Lam M. Nguyen, Dzung T. Phan, Phuong Ha Nguyen, Marten van Dijk, Quoc Tran-Dinh
Abstract	We propose a novel hybrid stochastic policy gradient estimator by combining an unbiased policy gradient estimator, the REINFORCE estimator, with another biased one, an adapted SARAH estimator for policy optimization. The hybrid policy gradient estimator is shown to be biased, but has variance reduced property. Using this estimator, we develop a new Proximal Hybrid Stochastic Policy Gradient Algorithm (ProxHSPGA) to solve a composite policy optimization problem that allows us to handle constraints or regularizers on the policy parameters. We first propose a single-looped algorithm then introduce a more practical restarting variant. We prove that both algorithms can achieve the best-known trajectory complexity $\mathcal{O}\left(\varepsilon^{-3}\right)$ to attain a first-order stationary point for the composite problem which is better than existing REINFORCE/GPOMDP $\mathcal{O}\left(\varepsilon^{-4}\right)$ and SVRPG $\mathcal{O}\left(\varepsilon^{-10/3}\right)$ in the non-composite setting. We evaluate the performance of our algorithm on several well-known examples in reinforcement learning. Numerical results show that our algorithm outperforms two existing methods on these examples. Moreover, the composite settings indeed have some advantages compared to the non-composite ones on certain problems.
Tasks
Published	2020-03-01
URL	https://arxiv.org/abs/2003.00430v1
PDF	https://arxiv.org/pdf/2003.00430v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-stochastic-policy-gradient-algorithm
Repo
Framework

Machine Learning Based Channel Modeling for Vehicular Visible Light Communication


Title	Machine Learning Based Channel Modeling for Vehicular Visible Light Communication
Authors	Bugra Turan, Sinem Coleri
Abstract	Optical Wireless Communication (OWC) propagation channel characterization plays a key role on the design and performance analysis of Vehicular Visible Light Communication (VVLC) systems. Current OWC channel models based on deterministic and stochastic methods, fail to address mobility induced ambient light, optical turbulence and road reflection effects on channel characterization. Therefore, alternative machine learning (ML) based schemes, considering ambient light, optical turbulence, road reflection effects in addition to intervehicular distance and geometry, are proposed to obtain accurate VVLC channel loss and channel frequency response (CFR). This work demonstrates synthesis of ML based VVLC channel model frameworks through multi layer perceptron feed-forward neural network (MLP), radial basis function neural network (RBF-NN) and Random Forest ensemble learning algorithms. Predictor and response variables, collected through practical road measurements, are employed to train and validate proposed models for various conditions. Additionally, the importance of different predictor variables on channel loss and CFR is assessed, normalized importance of features for measured VVLC channel is introduced. We show that RBF-NN, Random Forest and MLP based models yield more accurate channel loss estimations with 3.53 dB, 3.81 dB, 3.95 dB root mean square error (RMSE), respectively, when compared to fitting curve based VVLC channel model with 7 dB RMSE. Moreover, RBF-NN and MLP models are demonstrated to predict VVLC CFR with respect to distance, ambient light and receiver inclination angle predictor variables with 3.78 dB and 3.60 dB RMSE respectively.
Tasks
Published	2020-02-03
URL	https://arxiv.org/abs/2002.03774v1
PDF	https://arxiv.org/pdf/2002.03774v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-based-channel-modeling-for
Repo
Framework

Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims


Title	Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims
Authors	Kevin Meng, Damian Jimenez, Fatma Arslan, Jacob Daniel Devasier, Daniel Obembe, Chengkai Li
Abstract	We present a study on the efficacy of adversarial training on transformer neural network models, with respect to the task of detecting check-worthy claims. In this work, we introduce the first adversarially-regularized, transformer-based claim spotter model that achieves state-of-the-art results on multiple challenging benchmarks. We obtain a 4.31 point F1-score improvement and a 1.09 point mAP score improvement over current state-of-the-art models on the ClaimBuster Dataset and CLEF2019 Dataset, respectively. In the process, we propose a method to apply adversarial training to transformer models, which has the potential to be generalized to many similar text classification tasks. Along with our results, we are releasing our codebase and manually labeled datasets. We also showcase our models’ real world usage via a live public API.
Tasks	Text Classification
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07725v1
PDF	https://arxiv.org/pdf/2002.07725v1.pdf
PWC	https://paperswithcode.com/paper/gradient-based-adversarial-training-on
Repo
Framework

A Permutation-Equivariant Neural Network Architecture For Auction Design


Title	A Permutation-Equivariant Neural Network Architecture For Auction Design
Authors	Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg
Abstract	Designing an incentive compatible auction that maximizes expected revenue is a central problem in Auction Design. Theoretical approaches to the problem have hit some limits in the past decades and analytical solutions are known for only a few simple settings. Computational approaches to the problem through the use of LPs have their own set of limitations. Building on the success of deep learning, a new approach was recently proposed by D"utting et al., 2017 in which the auction is modeled by a feed-forward neural network and the design problem is framed as a learning problem. The neural architectures used in that work are general purpose and do not take advantage of any of the symmetries the problem could present, such as permutation equivariance. In this work, we consider auction design problems that have permutation-equivariant symmetry and construct a neural architecture that is capable of perfectly recovering the permutation-equivariant optimal mechanism, which we show is not possible with the previous architecture. We demonstrate that permutation-equivariant architectures are not only capable of recovering previous results, they also have better generalization properties.
Tasks
Published	2020-03-02
URL	https://arxiv.org/abs/2003.01497v1
PDF	https://arxiv.org/pdf/2003.01497v1.pdf
PWC	https://paperswithcode.com/paper/a-permutation-equivariant-neural-network
Repo
Framework

Guided Generative Adversarial Neural Network for Representation Learning and High Fidelity Audio Generation using Fewer Labelled Audio Data


Title	Guided Generative Adversarial Neural Network for Representation Learning and High Fidelity Audio Generation using Fewer Labelled Audio Data
Authors	Kazi Nazmul Haque, Rajib Rana, Björn Schuller
Abstract	Recent improvements in Generative Adversarial Neural Networks (GANs) have shown their ability to generate higher quality samples as well as to learn good representations for transfer learning. Most of the representation learning methods based on GANs learn representations ignoring their post-use scenario, which can lead to increased generalisation ability. However, the model can become redundant if it is intended for a specific task. For example, assume we have a vast unlabelled audio dataset, and we want to learn a representation from this dataset so that it can be used to improve the emotion recognition performance of a small labelled audio dataset. During the representation learning training, if the model does not know the post emotion recognition task, it can completely ignore emotion-related characteristics in the learnt representation. This is a fundamental challenge for any unsupervised representation learning model. In this paper, we aim to address this challenge by proposing a novel GAN framework: Guided Generative Neural Network (GGAN), which guides a GAN to focus on learning desired representations and generating superior quality samples for audio data leveraging fewer labelled samples. Experimental results show that using a very small amount of labelled data as guidance, a GGAN learns significantly better representations.
Tasks	Audio Generation, Emotion Recognition, Representation Learning, Transfer Learning, Unsupervised Representation Learning
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02836v1
PDF	https://arxiv.org/pdf/2003.02836v1.pdf
PWC	https://paperswithcode.com/paper/guided-generative-adversarial-neural-network
Repo
Framework


Title	Smart Summarizer for Blind People
Authors	Mona teja K, Mohan Sai. S, H S S S Raviteja D, Sai Kushagra P V
Abstract	In today’s world, time is a very important resource. In our busy lives, most of us hardly have time to read the complete news so what we have to do is just go through the headlines and satisfy ourselves with that. As a result, we might miss a part of the news or misinterpret the complete thing. The situation is even worse for the people who are visually impaired or have lost their ability to see. The inability of these people to read text has a huge impact on their lives. There are a number of methods for blind people to read the text. Braille script, in particular, is one of the examples, but it is a highly inefficient method as it is really time taking and requires a lot of practice. So, we present a method for visually impaired people based on the sense of sound which is obviously better and more accurate than the sense of touch. This paper deals with an efficient method to summarize news into important keywords so as to save the efforts to go through the complete text every single time. This paper deals with many API’s and modules like the tesseract, GTTS, and many algorithms that have been discussed and implemented in detail such as Luhn’s Algorithm, Latent Semantic Analysis Algorithm, Text Ranking Algorithm. And the other functionality that this paper deals with is converting the summarized text to speech so that the system can aid even the blind people.
Tasks
Published	2020-01-01
URL	https://arxiv.org/abs/2001.00575v1
PDF	https://arxiv.org/pdf/2001.00575v1.pdf
PWC	https://paperswithcode.com/paper/smart-summarizer-for-blind-people
Repo
Framework

Trends of digitalization and adoption of big data & analytics among UK SMEs: Analysis and lessons drawn from a case study of 53 SMEs


Title	Trends of digitalization and adoption of big data & analytics among UK SMEs: Analysis and lessons drawn from a case study of 53 SMEs
Authors	Muhidin Mohamed, Philip Weber
Abstract	Small and Medium Enterprises (SMEs) now generate digital data at an unprecedented rate from online transactions, social media marketing and associated customer interactions, online product or service reviews and feedback, clinical diagnosis, Internet of Things (IoT) sensors, and production processes. All these forms of data can be transformed into monetary value if put into a proper data value chain. This requires both skills and IT investments for the long-term benefit of businesses. However, such spending is beyond the capacity of most SMEs due to their limited resources and restricted access to finances. This paper presents lessons learned from a case study of 53 UK SMEs, mostly from the West Midlands region of England, supported as part of a 3-year ERDF project, Big Data Corridor, in the areas of big data management, analytics and related IT issues. Based on our study’s sample companies, several perspectives including the digital technology trends, challenges facing the UK SMEs, and the state of their adoption in data analytics and big data, are presented in the paper.
Tasks
Published	2020-02-14
URL	https://arxiv.org/abs/2002.11623v2
PDF	https://arxiv.org/pdf/2002.11623v2.pdf
PWC	https://paperswithcode.com/paper/trends-of-digitalization-and-adoption-of-big
Repo
Framework

MLModelScope: A Distributed Platform for Model Evaluation and Benchmarking at Scale


Title	MLModelScope: A Distributed Platform for Model Evaluation and Benchmarking at Scale
Authors	Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-mei Hwu
Abstract	Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that researchers are hard-pressed to analyze and study them. The complicated procedures for evaluating innovations, along with the lack of standard and efficient ways of specifying and provisioning ML/DL evaluation, is a major “pain point” for the community. This paper proposes MLModelScope, an open-source, framework/hardware agnostic, extensible and customizable design that enables repeatable, fair, and scalable model evaluation and benchmarking. We implement the distributed design with support for all major frameworks and hardware, and equip it with web, command-line, and library interfaces. To demonstrate MLModelScope’s capabilities we perform parallel evaluation and show how subtle changes to model evaluation pipeline affects the accuracy and HW/SW stack choices affect performance.
Tasks
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08295v1
PDF	https://arxiv.org/pdf/2002.08295v1.pdf
PWC	https://paperswithcode.com/paper/mlmodelscope-a-distributed-platform-for-model
Repo
Framework

HDF: Hybrid Deep Features for Scene Image Representation


Title	HDF: Hybrid Deep Features for Scene Image Representation
Authors	Chiranjibi Sitaula, Yong Xiang, Anish Basnet, Sunil Aryal, Xuequan Lu
Abstract	Nowadays it is prevalent to take features extracted from pre-trained deep learning models as image representations which have achieved promising classification performance. Existing methods usually consider either object-based features or scene-based features only. However, both types of features are important for complex images like scene images, as they can complement each other. In this paper, we propose a novel type of features – hybrid deep features, for scene images. Specifically, we exploit both object-based and scene-based features at two levels: part image level (i.e., parts of an image) and whole image level (i.e., a whole image), which produces a total number of four types of deep features. Regarding the part image level, we also propose two new slicing techniques to extract part based features. Finally, we aggregate these four types of deep features via the concatenation operator. We demonstrate the effectiveness of our hybrid deep features on three commonly used scene datasets (MIT-67, Scene-15, and Event-8), in terms of the scene image classification task. Extensive comparisons show that our introduced features can produce state-of-the-art classification accuracies which are more consistent and stable than the results of existing features across all datasets.
Tasks	Image Classification
Published	2020-03-22
URL	https://arxiv.org/abs/2003.09773v1
PDF	https://arxiv.org/pdf/2003.09773v1.pdf
PWC	https://paperswithcode.com/paper/hdf-hybrid-deep-features-for-scene-image
Repo
Framework

Machine-learning classifiers for logographic name matching in public health applications: approaches for incorporating phonetic, visual, and keystroke similarity in large-scale probabilistic record linkage


Title	Machine-learning classifiers for logographic name matching in public health applications: approaches for incorporating phonetic, visual, and keystroke similarity in large-scale probabilistic record linkage
Authors	Philip A. Collender, Zhiyue Tom Hu, Charles Li, Qu Cheng, Xintong Li, Yue You, Song Liang, Changhong Yang, Justin V. Remais
Abstract	Approximate string-matching methods to account for complex variation in highly discriminatory text fields, such as personal names, can enhance probabilistic record linkage. However, discriminating between matching and non-matching strings is challenging for logographic scripts, where similarities in pronunciation, appearance, or keystroke sequence are not directly encoded in the string data. We leverage a large Chinese administrative dataset with known match status to develop logistic regression and Xgboost classifiers integrating measures of visual, phonetic, and keystroke similarity to enhance identification of potentially-matching name pairs. We evaluate three methods of leveraging name similarity scores in large-scale probabilistic record linkage, which can adapt to varying match prevalence and information in supporting fields: (1) setting a threshold score based on predicted quality of name-matching across all record pairs; (2) setting a threshold score based on predicted discriminatory power of the linkage model; and (3) using empirical score distributions among matches and nonmatches to perform Bayesian adjustment of matching probabilities estimated from exact-agreement linkage. In experiments on holdout data, as well as data simulated with varying name error rates and supporting fields, a logistic regression classifier incorporated via the Bayesian method demonstrated marked improvements over exact-agreement linkage with respect to discriminatory power, match probability estimation, and accuracy, reducing the total number of misclassified record pairs by 21% in test data and up to an average of 93% in simulated datasets. Our results demonstrate the value of incorporating visual, phonetic, and keystroke similarity for logographic name matching, as well as the promise of our Bayesian approach to leverage name-matching within large-scale record linkage.
Tasks
Published	2020-01-07
URL	https://arxiv.org/abs/2001.01895v1
PDF	https://arxiv.org/pdf/2001.01895v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-classifiers-for-logographic
Repo
Framework