Paper Group ANR 514
Graph Centrality Measures for Boosting Popularity-Based Entity Linking. An efficient quantum algorithm for generative machine learning. Enhanced Quantum Synchronization via Quantum Machine Learning. Quantum autoencoders via quantum adders with genetic algorithms. Quantum machine learning: a classical perspective. Mining Supervisor Evaluation and Pe …
Graph Centrality Measures for Boosting Popularity-Based Entity Linking
| Title | Graph Centrality Measures for Boosting Popularity-Based Entity Linking |
| Authors | Hussam Hamdan, Jean-Gabriel Ganascia |
| Abstract | Many Entity Linking systems use collective graph-based methods to disambiguate the entity mentions within a document. Most of them have focused on graph construction and initial weighting of the candidate entities, less attention has been devoted to compare the graph ranking algorithms. In this work, we focus on the graph-based ranking algorithms, therefore we propose to apply five centrality measures: Degree, HITS, PageRank, Betweenness and Closeness. A disambiguation graph of candidate entities is constructed for each document using the popularity method, then centrality measures are applied to choose the most relevant candidate to boost the results of entity popularity method. We investigate the effectiveness of each centrality measure on the performance across different domains and datasets. Our experiments show that a simple and fast centrality measure such as Degree centrality can outperform other more time-consuming measures. |
| Tasks | Entity Linking, graph construction, Graph Ranking |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1712.00044v1 |
| http://arxiv.org/pdf/1712.00044v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-centrality-measures-for-boosting |
| Repo | |
| Framework | |
An efficient quantum algorithm for generative machine learning
| Title | An efficient quantum algorithm for generative machine learning |
| Authors | Xun Gao, Zhengyu Zhang, Luming Duan |
| Abstract | A central task in the field of quantum computing is to find applications where quantum computer could provide exponential speedup over any classical computer. Machine learning represents an important field with broad applications where quantum computer may offer significant speedup. Several quantum algorithms for discriminative machine learning have been found based on efficient solving of linear algebraic problems, with potential exponential speedup in runtime under the assumption of effective input from a quantum random access memory. In machine learning, generative models represent another large class which is widely used for both supervised and unsupervised learning. Here, we propose an efficient quantum algorithm for machine learning based on a quantum generative model. We prove that our proposed model is exponentially more powerful to represent probability distributions compared with classical generative models and has exponential speedup in training and inference at least for some instances under a reasonable assumption in computational complexity theory. Our result opens a new direction for quantum machine learning and offers a remarkable example in which a quantum algorithm shows exponential improvement over any classical algorithm in an important application field. |
| Tasks | Quantum Machine Learning |
| Published | 2017-11-06 |
| URL | http://arxiv.org/abs/1711.02038v1 |
| http://arxiv.org/pdf/1711.02038v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-quantum-algorithm-for-generative |
| Repo | |
| Framework | |
Enhanced Quantum Synchronization via Quantum Machine Learning
| Title | Enhanced Quantum Synchronization via Quantum Machine Learning |
| Authors | F. A. Cárdenas-López, M. Sanz, J. C. Retamal, E. Solano |
| Abstract | We study the quantum synchronization between a pair of two-level systems inside two coupled cavities. By using a digital-analog decomposition of the master equation that rules the system dynamics, we show that this approach leads to quantum synchronization between both two-level systems. Moreover, we can identify in this digital-analog block decomposition the fundamental elements of a quantum machine learning protocol, in which the agent and the environment (learning units) interact through a mediating system, namely, the register. If we can additionally equip this algorithm with a classical feedback mechanism, which consists of projective measurements in the register, reinitialization of the register state and local conditional operations on the agent and environment subspace, a powerful and flexible quantum machine learning protocol emerges. Indeed, numerical simulations show that this protocol enhances the synchronization process, even when every subsystem experience different loss/decoherence mechanisms, and give us the flexibility to choose the synchronization state. Finally, we propose an implementation based on current technologies in superconducting circuits. |
| Tasks | Quantum Machine Learning |
| Published | 2017-09-25 |
| URL | http://arxiv.org/abs/1709.08519v2 |
| http://arxiv.org/pdf/1709.08519v2.pdf | |
| PWC | https://paperswithcode.com/paper/enhanced-quantum-synchronization-via-quantum |
| Repo | |
| Framework | |
Quantum autoencoders via quantum adders with genetic algorithms
| Title | Quantum autoencoders via quantum adders with genetic algorithms |
| Authors | L. Lamata, U. Alvarez-Rodriguez, J. D. Martín-Guerrero, M. Sanz, E. Solano |
| Abstract | The quantum autoencoder is a recent paradigm in the field of quantum machine learning, which may enable an enhanced use of resources in quantum technologies. To this end, quantum neural networks with less nodes in the inner than in the outer layers were considered. Here, we propose a useful connection between approximate quantum adders and quantum autoencoders. Specifically, this link allows us to employ optimized approximate quantum adders, obtained with genetic algorithms, for the implementation of quantum autoencoders for a variety of initial states. Furthermore, we can also directly optimize the quantum autoencoders via genetic algorithms. Our approach opens a different path for the design of quantum autoencoders in controllable quantum platforms. |
| Tasks | Quantum Machine Learning |
| Published | 2017-09-21 |
| URL | http://arxiv.org/abs/1709.07409v2 |
| http://arxiv.org/pdf/1709.07409v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-autoencoders-via-quantum-adders-with |
| Repo | |
| Framework | |
Quantum machine learning: a classical perspective
| Title | Quantum machine learning: a classical perspective |
| Authors | Carlo Ciliberto, Mark Herbster, Alessandro Davide Ialongo, Massimiliano Pontil, Andrea Rocchetto, Simone Severini, Leonard Wossnig |
| Abstract | Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning techniques to impressive results in regression, classification, data-generation and reinforcement learning tasks. Despite these successes, the proximity to the physical limits of chip fabrication alongside the increasing size of datasets are motivating a growing number of researchers to explore the possibility of harnessing the power of quantum computation to speed-up classical machine learning algorithms. Here we review the literature in quantum machine learning and discuss perspectives for a mixed readership of classical machine learning and quantum computation experts. Particular emphasis will be placed on clarifying the limitations of quantum algorithms, how they compare with their best classical counterparts and why quantum resources are expected to provide advantages for learning problems. Learning in the presence of noise and certain computationally hard problems in machine learning are identified as promising directions for the field. Practical questions, like how to upload classical data into quantum form, will also be addressed. |
| Tasks | Quantum Machine Learning |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08561v3 |
| http://arxiv.org/pdf/1707.08561v3.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-machine-learning-a-classical |
| Repo | |
| Framework | |
Mining Supervisor Evaluation and Peer Feedback in Performance Appraisals
| Title | Mining Supervisor Evaluation and Peer Feedback in Performance Appraisals |
| Authors | Girish Keshav Palshikar, Sachin Pawar, Saheb Chourasia, Nitin Ramrakhiyani |
| Abstract | Performance appraisal (PA) is an important HR process to periodically measure and evaluate every employee’s performance vis-a-vis the goals established by the organization. A PA process involves purposeful multi-step multi-modal communication between employees, their supervisors and their peers, such as self-appraisal, supervisor assessment and peer feedback. Analysis of the structured data and text produced in PA is crucial for measuring the quality of appraisals and tracking actual improvements. In this paper, we apply text mining techniques to produce insights from PA text. First, we perform sentence classification to identify strengths, weaknesses and suggestions of improvements found in the supervisor assessments and then use clustering to discover broad categories among them. Next we use multi-class multi-label classification techniques to match supervisor assessments to predefined broad perspectives on performance. Finally, we propose a short-text summarization technique to produce a summary of peer feedback comments for a given employee and compare it with manual summaries. All techniques are illustrated using a real-life dataset of supervisor assessment and peer feedback text produced during the PA of 4528 employees in a large multi-national IT company. |
| Tasks | Multi-Label Classification, Sentence Classification, Text Summarization |
| Published | 2017-12-04 |
| URL | http://arxiv.org/abs/1712.00991v1 |
| http://arxiv.org/pdf/1712.00991v1.pdf | |
| PWC | https://paperswithcode.com/paper/mining-supervisor-evaluation-and-peer |
| Repo | |
| Framework | |
Forward-Backward Selection with Early Dropping
| Title | Forward-Backward Selection with Early Dropping |
| Authors | Giorgos Borboudakis, Ioannis Tsamardinos |
| Abstract | Forward-backward selection is one of the most basic and commonly-used feature selection algorithms available. It is also general and conceptually applicable to many different types of data. In this paper, we propose a heuristic that significantly improves its running time, while preserving predictive accuracy. The idea is to temporarily discard the variables that are conditionally independent with the outcome given the selected variable set. Depending on how those variables are reconsidered and reintroduced, this heuristic gives rise to a family of algorithms with increasingly stronger theoretical guarantees. In distributions that can be faithfully represented by Bayesian networks or maximal ancestral graphs, members of this algorithmic family are able to correctly identify the Markov blanket in the sample limit. In experiments we show that the proposed heuristic increases computational efficiency by about two orders of magnitude in high-dimensional problems, while selecting fewer variables and retaining predictive performance. Furthermore, we show that the proposed algorithm and feature selection with LASSO perform similarly when restricted to select the same number of variables, making the proposed algorithm an attractive alternative for problems where no (efficient) algorithm for LASSO exists. |
| Tasks | Feature Selection |
| Published | 2017-05-30 |
| URL | http://arxiv.org/abs/1705.10770v1 |
| http://arxiv.org/pdf/1705.10770v1.pdf | |
| PWC | https://paperswithcode.com/paper/forward-backward-selection-with-early |
| Repo | |
| Framework | |
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
| Title | The Effectiveness of Data Augmentation in Image Classification using Deep Learning |
| Authors | Luis Perez, Jason Wang |
| Abstract | In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping, rotating, and flipping input images. We artificially constrain our access to data to a small subset of the ImageNet dataset, and compare each data augmentation technique in turn. One of the more successful data augmentations strategies is the traditional transformations mentioned above. We also experiment with GANs to generate images of different styles. Finally, we propose a method to allow a neural net to learn augmentations that best improve the classifier, which we call neural augmentation. We discuss the successes and shortcomings of this method on various datasets. |
| Tasks | Data Augmentation, Image Classification |
| Published | 2017-12-13 |
| URL | http://arxiv.org/abs/1712.04621v1 |
| http://arxiv.org/pdf/1712.04621v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-effectiveness-of-data-augmentation-in |
| Repo | |
| Framework | |
FFT-Based Deep Learning Deployment in Embedded Systems
| Title | FFT-Based Deep Learning Deployment in Embedded Systems |
| Authors | Sheng Lin, Ning Liu, Mahdi Nazemi, Hongjia Li, Caiwen Ding, Yanzhi Wang, Massoud Pedram |
| Abstract | Deep learning has delivered its powerfulness in many application domains, especially in image and speech recognition. As the backbone of deep learning, deep neural networks (DNNs) consist of multiple layers of various types with hundreds to thousands of neurons. Embedded platforms are now becoming essential for deep learning deployment due to their portability, versatility, and energy efficiency. The large model size of DNNs, while providing excellent accuracy, also burdens the embedded platforms with intensive computation and storage. Researchers have investigated on reducing DNN model size with negligible accuracy loss. This work proposes a Fast Fourier Transform (FFT)-based DNN training and inference model suitable for embedded platforms with reduced asymptotic complexity of both computation and storage, making our approach distinguished from existing approaches. We develop the training and inference algorithms based on FFT as the computing kernel and deploy the FFT-based inference model on embedded platforms achieving extraordinary processing speed. |
| Tasks | Speech Recognition |
| Published | 2017-12-13 |
| URL | http://arxiv.org/abs/1712.04910v1 |
| http://arxiv.org/pdf/1712.04910v1.pdf | |
| PWC | https://paperswithcode.com/paper/fft-based-deep-learning-deployment-in |
| Repo | |
| Framework | |
Social Media Text Processing and Semantic Analysis for Smart Cities
| Title | Social Media Text Processing and Semantic Analysis for Smart Cities |
| Authors | João Filipe Figueiredo Pereira |
| Abstract | With the rise of Social Media, people obtain and share information almost instantly on a 24/7 basis. Many research areas have tried to gain valuable insights from these large volumes of freely available user generated content. With the goal of extracting knowledge from social media streams that might be useful in the context of intelligent transportation systems and smart cities, we designed and developed a framework that provides functionalities for parallel collection of geo-located tweets from multiple pre-defined bounding boxes (cities or regions), including filtering of non-complying tweets, text pre-processing for Portuguese and English language, topic modeling, and transportation-specific text classifiers, as well as, aggregation and data visualization. We performed an exploratory data analysis of geo-located tweets in 5 different cities: Rio de Janeiro, S~ao Paulo, New York City, London and Melbourne, comprising a total of more than 43 million tweets in a period of 3 months. Furthermore, we performed a large scale topic modelling comparison between Rio de Janeiro and S~ao Paulo. Interestingly, most of the topics are shared between both cities which despite being in the same country are considered very different regarding population, economy and lifestyle. We take advantage of recent developments in word embeddings and train such representations from the collections of geo-located tweets. We then use a combination of bag-of-embeddings and traditional bag-of-words to train travel-related classifiers in both Portuguese and English to filter travel-related content from non-related. We created specific gold-standard data to perform empirical evaluation of the resulting classifiers. Results are in line with research work in other application areas by showing the robustness of using word embeddings to learn word similarities that bag-of-words is not able to capture. |
| Tasks | Word Embeddings |
| Published | 2017-09-11 |
| URL | http://arxiv.org/abs/1709.03406v1 |
| http://arxiv.org/pdf/1709.03406v1.pdf | |
| PWC | https://paperswithcode.com/paper/social-media-text-processing-and-semantic |
| Repo | |
| Framework | |
Learned Features are better for Ethnicity Classification
| Title | Learned Features are better for Ethnicity Classification |
| Authors | Inzamam Anwar, Naeem Ul Islam |
| Abstract | Ethnicity is a key demographic attribute of human beings and it plays a vital role in automatic facial recognition and have extensive real world applications such as Human Computer Interaction (HCI); demographic based classification; biometric based recognition; security and defense to name a few. In this paper we present a novel approach for extracting ethnicity from the facial images. The proposed method makes use of a pre trained Convolutional Neural Network (CNN) to extract the features and then Support Vector Machine (SVM) with linear kernel is used as a classifier. This technique uses translational invariant hierarchical features learned by the network, in contrast to previous works, which use hand crafted features such as Local Binary Pattern (LBP); Gabor etc. Thorough experiments are presented on ten different facial databases which strongly suggest that our approach is robust to different expressions and illuminations conditions. Here we consider ethnicity classification as a three class problem including Asian, African-American and Caucasian. Average classification accuracy over all databases is 98.28%, 99.66% and 99.05% for Asian, African-American and Caucasian respectively. |
| Tasks | |
| Published | 2017-09-21 |
| URL | http://arxiv.org/abs/1709.07429v2 |
| http://arxiv.org/pdf/1709.07429v2.pdf | |
| PWC | https://paperswithcode.com/paper/learned-features-are-better-for-ethnicity |
| Repo | |
| Framework | |
On Formalizing Fairness in Prediction with Machine Learning
| Title | On Formalizing Fairness in Prediction with Machine Learning |
| Authors | Pratik Gajane, Mykola Pechenizkiy |
| Abstract | Machine learning algorithms for prediction are increasingly being used in critical decisions affecting human lives. Various fairness formalizations, with no firm consensus yet, are employed to prevent such algorithms from systematically discriminating against people based on certain attributes protected by law. The aim of this article is to survey how fairness is formalized in the machine learning literature for the task of prediction and present these formalizations with their corresponding notions of distributive justice from the social sciences literature. We provide theoretical as well as empirical critiques of these notions from the social sciences literature and explain how these critiques limit the suitability of the corresponding fairness formalizations to certain domains. We also suggest two notions of distributive justice which address some of these critiques and discuss avenues for prospective fairness formalizations. |
| Tasks | |
| Published | 2017-10-09 |
| URL | http://arxiv.org/abs/1710.03184v3 |
| http://arxiv.org/pdf/1710.03184v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-formalizing-fairness-in-prediction-with |
| Repo | |
| Framework | |
Adversarial Image Perturbation for Privacy Protection – A Game Theory Perspective
| Title | Adversarial Image Perturbation for Privacy Protection – A Game Theory Perspective |
| Authors | Seong Joon Oh, Mario Fritz, Bernt Schiele |
| Abstract | Users like sharing personal photos with others through social media. At the same time, they might want to make automatic identification in such photos difficult or even impossible. Classic obfuscation methods such as blurring are not only unpleasant but also not as effective as one would expect. Recent studies on adversarial image perturbations (AIP) suggest that it is possible to confuse recognition systems effectively without unpleasant artifacts. However, in the presence of counter measures against AIPs, it is unclear how effective AIP would be in particular when the choice of counter measure is unknown. Game theory provides tools for studying the interaction between agents with uncertainties in the strategies. We introduce a general game theoretical framework for the user-recogniser dynamics, and present a case study that involves current state of the art AIP and person recognition techniques. We derive the optimal strategy for the user that assures an upper bound on the recognition rate independent of the recogniser’s counter measure. Code is available at https://goo.gl/hgvbNK. |
| Tasks | Person Recognition |
| Published | 2017-03-28 |
| URL | http://arxiv.org/abs/1703.09471v2 |
| http://arxiv.org/pdf/1703.09471v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-image-perturbation-for-privacy |
| Repo | |
| Framework | |
Predicting the Law Area and Decisions of French Supreme Court Cases
| Title | Predicting the Law Area and Decisions of French Supreme Court Cases |
| Authors | Octavia-Maria Sulea, Marcos Zampieri, Mihaela Vela, Josef van Genabith |
| Abstract | In this paper, we investigate the application of text classification methods to predict the law area and the decision of cases judged by the French Supreme Court. We also investigate the influence of the time period in which a ruling was made over the textual form of the case description and the extent to which it is necessary to mask the judge’s motivation for a ruling to emulate a real-world test scenario. We report results of 96% f1 score in predicting a case ruling, 90% f1 score in predicting the law area of a case, and 75.9% f1 score in estimating the time span when a ruling has been issued using a linear Support Vector Machine (SVM) classifier trained on lexical features. |
| Tasks | Text Classification |
| Published | 2017-08-04 |
| URL | http://arxiv.org/abs/1708.01681v1 |
| http://arxiv.org/pdf/1708.01681v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-the-law-area-and-decisions-of |
| Repo | |
| Framework | |
Deep Learning for Real Time Crime Forecasting
| Title | Deep Learning for Real Time Crime Forecasting |
| Authors | Bao Wang, Duo Zhang, Duanhao Zhang, P. Jeffery Brantingham, Andrea L. Bertozzi |
| Abstract | Accurate real time crime prediction is a fundamental issue for public safety, but remains a challenging problem for the scientific community. Crime occurrences depend on many complex factors. Compared to many predictable events, crime is sparse. At different spatio-temporal scales, crime distributions display dramatically different patterns. These distributions are of very low regularity in both space and time. In this work, we adapt the state-of-the-art deep learning spatio-temporal predictor, ST-ResNet [Zhang et al, AAAI, 2017], to collectively predict crime distribution over the Los Angeles area. Our models are two staged. First, we preprocess the raw crime data. This includes regularization in both space and time to enhance predictable signals. Second, we adapt hierarchical structures of residual convolutional units to train multi-factor crime prediction models. Experiments over a half year period in Los Angeles reveal highly accurate predictive power of our models. |
| Tasks | Crime Prediction |
| Published | 2017-07-09 |
| URL | http://arxiv.org/abs/1707.03340v1 |
| http://arxiv.org/pdf/1707.03340v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-real-time-crime-forecasting-1 |
| Repo | |
| Framework | |
