July 28, 2019

3197 words 16 mins read

Paper Group ANR 196

Deep Deterministic Policy Gradient for Urban Traffic Light Control. Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network. Automatic Rule Extraction from Long Short Term Memory Networks. Reconstruction of Hidden Representation for Robust Feature Extraction. Spectral and matrix factorization methods for consistent community …

Deep Deterministic Policy Gradient for Urban Traffic Light Control


Title	Deep Deterministic Policy Gradient for Urban Traffic Light Control
Authors	Noe Casas
Abstract	Traffic light timing optimization is still an active line of research despite the wealth of scientific literature on the topic, and the problem remains unsolved for any non-toy scenario. One of the key issues with traffic light optimization is the large scale of the input information that is available for the controlling agent, namely all the traffic data that is continually sampled by the traffic detectors that cover the urban network. This issue has in the past forced researchers to focus on agents that work on localized parts of the traffic network, typically on individual intersections, and to coordinate every individual agent in a multi-agent setup. In order to overcome the large scale of the available state information, we propose to rely on the ability of deep Learning approaches to handle large input spaces, in the form of Deep Deterministic Policy Gradient (DDPG) algorithm. We performed several experiments with a range of models, from the very simple one (one intersection) to the more complex one (a big city section).
Tasks
Published	2017-03-27
URL	http://arxiv.org/abs/1703.09035v2
PDF	http://arxiv.org/pdf/1703.09035v2.pdf
PWC	https://paperswithcode.com/paper/deep-deterministic-policy-gradient-for-urban
Repo
Framework

Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network


Title	Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network
Authors	Alexandros Tsaptsinos
Abstract	Music genre classification, especially using lyrics alone, remains a challenging topic in Music Information Retrieval. In this study we apply recurrent neural network models to classify a large dataset of intact song lyrics. As lyrics exhibit a hierarchical layer structure - in which words combine to form lines, lines form segments, and segments form a complete song - we adapt a hierarchical attention network (HAN) to exploit these layers and in addition learn the importance of the words, lines, and segments. We test the model over a 117-genre dataset and a reduced 20-genre dataset. Experimental results show that the HAN outperforms both non-neural models and simpler neural models, whilst also classifying over a higher number of genres than previous research. Through the learning process we can also visualise which words or lines in a song the model believes are important to classifying the genre. As a result the HAN provides insights, from a computational perspective, into lyrical structure and language features that differentiate musical genres.
Tasks	Information Retrieval, Music Information Retrieval
Published	2017-07-15
URL	http://arxiv.org/abs/1707.04678v1
PDF	http://arxiv.org/pdf/1707.04678v1.pdf
PWC	https://paperswithcode.com/paper/lyrics-based-music-genre-classification-using
Repo
Framework

Automatic Rule Extraction from Long Short Term Memory Networks


Title	Automatic Rule Extraction from Long Short Term Memory Networks
Authors	W. James Murdoch, Arthur Szlam
Abstract	Although deep learning models have proven effective at solving problems in natural language processing, the mechanism by which they come to their conclusions is often unclear. As a result, these models are generally treated as black boxes, yielding no insight of the underlying learned patterns. In this paper we consider Long Short Term Memory networks (LSTMs) and demonstrate a new approach for tracking the importance of a given input to the LSTM for a given output. By identifying consistently important patterns of words, we are able to distill state of the art LSTMs on sentiment analysis and question answering into a set of representative phrases. This representation is then quantitatively validated by using the extracted phrases to construct a simple, rule-based classifier which approximates the output of the LSTM.
Tasks	Question Answering, Sentiment Analysis
Published	2017-02-08
URL	http://arxiv.org/abs/1702.02540v2
PDF	http://arxiv.org/pdf/1702.02540v2.pdf
PWC	https://paperswithcode.com/paper/automatic-rule-extraction-from-long-short
Repo
Framework

Reconstruction of Hidden Representation for Robust Feature Extraction


Title	Reconstruction of Hidden Representation for Robust Feature Extraction
Authors	Zeng Yu, Tianrui Li, Ning Yu, Yi Pan, Hongmei Chen, Bing Liu
Abstract	This paper aims to develop a new and robust approach to feature representation. Motivated by the success of Auto-Encoders, we first theoretical summarize the general properties of all algorithms that are based on traditional Auto-Encoders: 1) The reconstruction error of the input can not be lower than a lower bound, which can be viewed as a guiding principle for reconstructing the input. Additionally, when the input is corrupted with noises, the reconstruction error of the corrupted input also can not be lower than a lower bound. 2) The reconstruction of a hidden representation achieving its ideal situation is the necessary condition for the reconstruction of the input to reach the ideal state. 3) Minimizing the Frobenius norm of the Jacobian matrix of the hidden representation has a deficiency and may result in a much worse local optimum value. We believe that minimizing the reconstruction error of the hidden representation is more robust than minimizing the Frobenius norm of the Jacobian matrix of the hidden representation. Based on the above analysis, we propose a new model termed Double Denoising Auto-Encoders (DDAEs), which uses corruption and reconstruction on both the input and the hidden representation. We demonstrate that the proposed model is highly flexible and extensible and has a potentially better capability to learn invariant and robust feature representations. We also show that our model is more robust than Denoising Auto-Encoders (DAEs) for dealing with noises or inessential features. Furthermore, we detail how to train DDAEs with two different pre-training methods by optimizing the objective function in a combined and separate manner, respectively. Comparative experiments illustrate that the proposed model is significantly better for representation learning than the state-of-the-art models.
Tasks	Denoising, Representation Learning
Published	2017-10-08
URL	http://arxiv.org/abs/1710.02844v2
PDF	http://arxiv.org/pdf/1710.02844v2.pdf
PWC	https://paperswithcode.com/paper/reconstruction-of-hidden-representation-for
Repo
Framework

Spectral and matrix factorization methods for consistent community detection in multi-layer networks


Title	Spectral and matrix factorization methods for consistent community detection in multi-layer networks
Authors	Subhadeep Paul, Yuguo Chen
Abstract	We consider the problem of estimating a consensus community structure by combining information from multiple layers of a multi-layer network using methods based on the spectral clustering or a low-rank matrix factorization. As a general theme, these “intermediate fusion” methods involve obtaining a low column rank matrix by optimizing an objective function and then using the columns of the matrix for clustering. However, the theoretical properties of these methods remain largely unexplored. In the absence of statistical guarantees on the objective functions, it is difficult to determine if the algorithms optimizing the objectives will return good community structures. We investigate the consistency properties of the global optimizer of some of these objective functions under the multi-layer stochastic blockmodel. For this purpose, we derive several new asymptotic results showing consistency of the intermediate fusion techniques along with the spectral clustering of mean adjacency matrix under a high dimensional setup, where the number of nodes, the number of layers and the number of communities of the multi-layer graph grow. Our numerical study shows that the intermediate fusion techniques outperform late fusion methods, namely spectral clustering on aggregate spectral kernel and module allegiance matrix in sparse networks, while they outperform the spectral clustering of mean adjacency matrix in multi-layer networks that contain layers with both homophilic and heterophilic communities.
Tasks	Community Detection
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07353v3
PDF	http://arxiv.org/pdf/1704.07353v3.pdf
PWC	https://paperswithcode.com/paper/spectral-and-matrix-factorization-methods-for
Repo
Framework

On the Computation of Paracoherent Answer Sets


Title	On the Computation of Paracoherent Answer Sets
Authors	Giovanni Amendola, Carmine Dodaro, Wolfgang Faber, Nicola Leone, Francesco Ricca
Abstract	Answer Set Programming (ASP) is a well-established formalism for nonmonotonic reasoning. An ASP program can have no answer set due to cyclic default negation. In this case, it is not possible to draw any conclusion, even if this is not intended. Recently, several paracoherent semantics have been proposed that address this issue, and several potential applications for these semantics have been identified. However, paracoherent semantics have essentially been inapplicable in practice, due to the lack of efficient algorithms and implementations. In this paper, this lack is addressed, and several different algorithms to compute semi-stable and semi-equilibrium models are proposed and implemented into an answer set solving framework. An empirical performance comparison among the new algorithms on benchmarks from ASP competitions is given as well.
Tasks
Published	2017-07-21
URL	http://arxiv.org/abs/1707.06813v1
PDF	http://arxiv.org/pdf/1707.06813v1.pdf
PWC	https://paperswithcode.com/paper/on-the-computation-of-paracoherent-answer
Repo
Framework

PersonRank: Detecting Important People in Images


Title	PersonRank: Detecting Important People in Images
Authors	Wei-Hong Li, Benchao Li, Wei-Shi Zheng
Abstract	Always, some individuals in images are more important/attractive than others in some events such as presentation, basketball game or speech. However, it is challenging to find important people among all individuals in images directly based on their spatial or appearance information due to the existence of diverse variations of pose, action, appearance of persons and various changes of occasions. We overcome this difficulty by constructing a multiple Hyper-Interaction Graph to treat each individual in an image as a node and inferring the most active node referring to interactions estimated by various types of clews. We model pairwise interactions between persons as the edge message communicated between nodes, resulting in a bidirectional pairwise-interaction graph. To enrich the personperson interaction estimation, we further introduce a unidirectional hyper-interaction graph that models the consensus of interaction between a focal person and any person in a local region around. Finally, we modify the PageRank algorithm to infer the activeness of persons on the multiple Hybrid-Interaction Graph (HIG), the union of the pairwise-interaction and hyperinteraction graphs, and we call our algorithm the PersonRank. In order to provide publicable datasets for evaluation, we have contributed a new dataset called Multi-scene Important People Image Dataset and gathered a NCAA Basketball Image Dataset from sports game sequences. We have demonstrated that the proposed PersonRank outperforms related methods clearly and substantially.
Tasks
Published	2017-11-06
URL	http://arxiv.org/abs/1711.01984v1
PDF	http://arxiv.org/pdf/1711.01984v1.pdf
PWC	https://paperswithcode.com/paper/personrank-detecting-important-people-in
Repo
Framework

Using NLU in Context for Question Answering: Improving on Facebook’s bAbI Tasks


Title	Using NLU in Context for Question Answering: Improving on Facebook’s bAbI Tasks
Authors	John S. Ball
Abstract	For the next step in human to machine interaction, Artificial Intelligence (AI) should interact predominantly using natural language because, if it worked, it would be the fastest way to communicate. Facebook’s toy tasks (bAbI) provide a useful benchmark to compare implementations for conversational AI. While the published experiments so far have been based on exploiting the distributional hypothesis with machine learning, our model exploits natural language understanding (NLU) with the decomposition of language based on Role and Reference Grammar (RRG) and the brain-based Patom theory. Our combinatorial system for conversational AI based on linguistics has many advantages: passing bAbI task tests without parsing or statistics while increasing scalability. Our model validates both the training and test data to find ‘garbage’ input and output (GIGO). It is not rules-based, nor does it use parts of speech, but instead relies on meaning. While Deep Learning is difficult to debug and fix, every step in our model can be understood and changed like any non-statistical computer program. Deep Learning’s lack of explicable reasoning has raised opposition to AI, partly due to fear of the unknown. To support the goals of AI, we propose extended tasks to use human-level statements with tense, aspect and voice, and embedded clauses with junctures: and answers to be natural language generation (NLG) instead of keywords. While machine learning permits invalid training data to produce incorrect test responses, our system cannot because the context tracking would need to be intentionally broken. We believe no existing learning systems can currently solve these extended natural language tests. There appears to be a knowledge gap between NLP researchers and linguists, but ongoing competitive results such as these promise to narrow that gap.
Tasks	Question Answering, Text Generation
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04558v2
PDF	http://arxiv.org/pdf/1709.04558v2.pdf
PWC	https://paperswithcode.com/paper/using-nlu-in-context-for-question-answering
Repo
Framework

Deep density networks and uncertainty in recommender systems


Title	Deep density networks and uncertainty in recommender systems
Authors	Yoel Zeldes, Stavros Theodorakis, Efrat Solodnik, Aviv Rotman, Gil Chamiel, Dan Friedman
Abstract	Building robust online content recommendation systems requires learning complex interactions between user preferences and content features. The field has evolved rapidly in recent years from traditional multi-arm bandit and collaborative filtering techniques, with new methods employing Deep Learning models to capture non-linearities. Despite progress, the dynamic nature of online recommendations still poses great challenges, such as finding the delicate balance between exploration and exploitation. In this paper we show how uncertainty estimations can be incorporated by employing them in an optimistic exploitation/exploration strategy for more efficient exploration of new recommendations. We provide a novel hybrid deep neural network model, Deep Density Networks (DDN), which integrates content-based deep learning models with a collaborative scheme that is able to robustly model and estimate uncertainty. Finally, we present online and offline results after incorporating DNN into a real world content recommendation system that serves billions of recommendations per day, and show the benefit of using DDN in practice.
Tasks	Efficient Exploration, Recommendation Systems
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02487v3
PDF	http://arxiv.org/pdf/1711.02487v3.pdf
PWC	https://paperswithcode.com/paper/deep-density-networks-and-uncertainty-in
Repo
Framework

Theoretical Foundations of Forward Feature Selection Methods based on Mutual Information


Title	Theoretical Foundations of Forward Feature Selection Methods based on Mutual Information
Authors	Francisco Macedo, M. Rosário Oliveira, António Pacheco, Rui Valadas
Abstract	Feature selection problems arise in a variety of applications, such as microarray analysis, clinical prediction, text categorization, image classification and face recognition, multi-label learning, and classification of internet traffic. Among the various classes of methods, forward feature selection methods based on mutual information have become very popular and are widely used in practice. However, comparative evaluations of these methods have been limited by being based on specific datasets and classifiers. In this paper, we develop a theoretical framework that allows evaluating the methods based on their theoretical properties. Our framework is grounded on the properties of the target objective function that the methods try to approximate, and on a novel categorization of features, according to their contribution to the explanation of the class; we derive upper and lower bounds for the target objective function and relate these bounds with the feature types. Then, we characterize the types of approximations taken by the methods, and analyze how these approximations cope with the good properties of the target objective function. Additionally, we develop a distributional setting designed to illustrate the various deficiencies of the methods, and provide several examples of wrong feature selections. Based on our work, we identify clearly the methods that should be avoided, and the methods that currently have the best performance.
Tasks	Face Recognition, Feature Selection, Image Classification, Multi-Label Learning, Text Categorization
Published	2017-01-26
URL	http://arxiv.org/abs/1701.07761v2
PDF	http://arxiv.org/pdf/1701.07761v2.pdf
PWC	https://paperswithcode.com/paper/theoretical-foundations-of-forward-feature
Repo
Framework

Target-adaptive CNN-based pansharpening


Title	Target-adaptive CNN-based pansharpening
Authors	Giuseppe Scarpa, Sergio Vitale, Davide Cozzolino
Abstract	We recently proposed a convolutional neural network (CNN) for remote sensing image pansharpening obtaining a significant performance gain over the state of the art. In this paper, we explore a number of architectural and training variations to this baseline, achieving further performance gains with a lightweight network which trains very fast. Leveraging on this latter property, we propose a target-adaptive usage modality which ensures a very good performance also in the presence of a mismatch w.r.t. the training set, and even across different sensors. The proposed method, published online as an off-the-shelf software tool, allows users to perform fast and high-quality CNN-based pansharpening of their own target images on general-purpose hardware.
Tasks
Published	2017-09-18
URL	http://arxiv.org/abs/1709.06054v3
PDF	http://arxiv.org/pdf/1709.06054v3.pdf
PWC	https://paperswithcode.com/paper/target-adaptive-cnn-based-pansharpening
Repo
Framework

Make Hawkes Processes Explainable by Decomposing Self-Triggering Kernels


Title	Make Hawkes Processes Explainable by Decomposing Self-Triggering Kernels
Authors	Rafael Lima, Jaesik Choi
Abstract	Hawkes Processes capture self-excitation and mutual-excitation between events when the arrival of an event makes future events more likely to happen. Identification of such temporal covariance can reveal the underlying structure to better predict future events. In this paper, we present a new framework to decompose discrete events with a composition of multiple self-triggering kernels. The composition scheme allows us to decompose empirical covariance densities into the sum or the product of base kernels which are easily interpretable. Here, we present the first multiplicative kernel composition methods for Hawkes Processes. We demonstrate that the new automatic kernel decomposition procedure outperforms the existing methods on the prediction of discrete events in real-world data.
Tasks
Published	2017-03-27
URL	http://arxiv.org/abs/1703.09068v5
PDF	http://arxiv.org/pdf/1703.09068v5.pdf
PWC	https://paperswithcode.com/paper/make-hawkes-processes-explainable-by
Repo
Framework

Syntax Aware LSTM Model for Chinese Semantic Role Labeling


Title	Syntax Aware LSTM Model for Chinese Semantic Role Labeling
Authors	Feng Qian, Lei Sha, Baobao Chang, Lu-chen Liu, Ming Zhang
Abstract	As for semantic role labeling (SRL) task, when it comes to utilizing parsing information, both traditional methods and recent recurrent neural network (RNN) based methods use the feature engineering way. In this paper, we propose Syntax Aware Long Short Time Memory(SA-LSTM). The structure of SA-LSTM modifies according to dependency parsing information in order to model parsing information directly in an architecture engineering way instead of feature engineering way. We experimentally demonstrate that SA-LSTM gains more improvement from the model architecture. Furthermore, SA-LSTM outperforms the state-of-the-art on CPB 1.0 significantly according to Student t-test ($p<0.05$).
Tasks	Dependency Parsing, Feature Engineering, Semantic Role Labeling
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00405v2
PDF	http://arxiv.org/pdf/1704.00405v2.pdf
PWC	https://paperswithcode.com/paper/syntax-aware-lstm-model-for-chinese-semantic
Repo
Framework

Machine learning approach for early detection of autism by combining questionnaire and home video screening


Title	Machine learning approach for early detection of autism by combining questionnaire and home video screening
Authors	Halim Abbas, Ford Garberson, Eric Glover, Dennis P Wall
Abstract	Existing screening tools for early detection of autism are expensive, cumbersome, time-intensive, and sometimes fall short in predictive value. In this work, we apply Machine Learning (ML) to gold standard clinical data obtained across thousands of children at risk for autism spectrum disorders to create a low-cost, quick, and easy to apply autism screening tool that performs as well or better than most widely used standardized instruments. This new tool combines two screening methods into a single assessment, one based on short, structured parent-report questionnaires and the other on tagging key behaviors from short, semi-structured home videos of children. To overcome the scarcity, sparsity, and imbalance of training data, we apply creative feature selection, feature engineering, and novel feature encoding techniques. We allow for inconclusive determination where appropriate in order to boost screening accuracy when conclusive. We demonstrate a significant accuracy improvement over standard screening tools in a clinical study sample of 162 children.
Tasks	Feature Engineering, Feature Selection
Published	2017-03-15
URL	http://arxiv.org/abs/1703.06076v1
PDF	http://arxiv.org/pdf/1703.06076v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-approach-for-early-detection
Repo
Framework

Effective face landmark localization via single deep network


Title	Effective face landmark localization via single deep network
Authors	Zongping Deng, Ke Li, Qijun Zhao, Yi Zhang, Hu Chen
Abstract	In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data. Rather than using a max-pooling layer followed one convolutional layer in typical convolutional neural networks (CNN), SDN adopts a stack of 3 layer groups instead. Each group layer contains two convolutional layers and a max-pooling layer, which can extract the features hierarchically. Moreover, an effective data augmentation strategy and corresponding training skills are also proposed to over-come the lack of training images on COFW and 300-W da-tasets. The experiment results show that our method outper-forms state-of-the-art methods in both detection accuracy and speed.
Tasks	Data Augmentation, Face Alignment
Published	2017-02-09
URL	http://arxiv.org/abs/1702.02719v1
PDF	http://arxiv.org/pdf/1702.02719v1.pdf
PWC	https://paperswithcode.com/paper/effective-face-landmark-localization-via
Repo
Framework