October 17, 2019

3115 words 15 mins read

Paper Group ANR 743

Simplified SPARQL REST API - CRUD on JSON Object Graphs via URI Paths. End-to-End Learning for Answering Structured Queries Directly over Text. OCTID: Optical Coherence Tomography Image Database. Neural Arithmetic Expression Calculator. Audio Source Separation Using Variational Autoencoders and Weak Class Supervision. Whale swarm algorithm with the …

Simplified SPARQL REST API - CRUD on JSON Object Graphs via URI Paths


Title	Simplified SPARQL REST API - CRUD on JSON Object Graphs via URI Paths
Authors	Markus Schröder, Jörn Hees, Ansgar Bernardi, Daniel Ewert, Peter Klotz, Steffen Stadtmüller
Abstract	Within the Semantic Web community, SPARQL is one of the predominant languages to query and update RDF knowledge. However, the complexity of SPARQL, the underlying graph structure and various encodings are common sources of confusion for Semantic Web novices. In this paper we present a general purpose approach to convert any given SPARQL endpoint into a simple to use REST API. To lower the initial hurdle, we represent the underlying graph as an interlinked view of nested JSON objects that can be traversed by the API path.
Tasks
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01825v1
PDF	http://arxiv.org/pdf/1805.01825v1.pdf
PWC	https://paperswithcode.com/paper/simplified-sparql-rest-api-crud-on-json
Repo
Framework

End-to-End Learning for Answering Structured Queries Directly over Text


Title	End-to-End Learning for Answering Structured Queries Directly over Text
Authors	Paul Groth, Antony Scerri, Ron Daniel, Jr., Bradley P. Allen
Abstract	Structured queries expressed in languages (such as SQL, SPARQL, or XQuery) offer a convenient and explicit way for users to express their information needs for a number of tasks. In this work, we present an approach to answer these directly over text data without storing results in a database. We specifically look at the case of knowledge bases where queries are over entities and the relations between them. Our approach combines distributed query answering (e.g. Triple Pattern Fragments) with models built for extractive question answering. Importantly, by applying distributed querying answering we are able to simplify the model learning problem. We train models for a large portion (572) of the relations within Wikidata and achieve an average 0.70 F1 measure across all models. We also present a systematic method to construct the necessary training data for this task from knowledge graphs and describe a prototype implementation.
Tasks	Knowledge Graphs, Question Answering
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06303v2
PDF	http://arxiv.org/pdf/1811.06303v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-learning-for-answering-structured
Repo
Framework

OCTID: Optical Coherence Tomography Image Database


Title	OCTID: Optical Coherence Tomography Image Database
Authors	Peyman Gholami, Priyanka Roy, Mohana Kuppuswamy Parthasarathy, Vasudevan Lakshminarayanan
Abstract	Optical coherence tomography (OCT) is a non-invasive imaging modality which is widely used in clinical ophthalmology. OCT images are capable of visualizing deep retinal layers which is crucial for early diagnosis of retinal diseases. In this paper, we describe a comprehensive open-access database containing more than 500 highresolution images categorized into different pathological conditions. The image classes include Normal (NO), Macular Hole (MH), Age-related Macular Degeneration (AMD), Central Serous Retinopathy (CSR), and Diabetic Retinopathy (DR). The images were obtained from a raster scan protocol with a 2mm scan length and 512x1024 pixel resolution. We have also included 25 normal OCT images with their corresponding ground truth delineations which can be used for an accurate evaluation of OCT image segmentation. In addition, we have provided a user-friendly GUI which can be used by clinicians for manual (and semi-automated) segmentation.
Tasks	Semantic Segmentation
Published	2018-12-17
URL	https://arxiv.org/abs/1812.07056v2
PDF	https://arxiv.org/pdf/1812.07056v2.pdf
PWC	https://paperswithcode.com/paper/octid-optical-coherence-tomography-image
Repo
Framework

Neural Arithmetic Expression Calculator


Title	Neural Arithmetic Expression Calculator
Authors	Kaiyu Chen, Yihan Dong, Xipeng Qiu, Zitian Chen
Abstract	This paper presents a pure neural solver for arithmetic expression calculation (AEC) problem. Previous work utilizes the powerful capabilities of deep neural networks and attempts to build an end-to-end model to solve this problem. However, most of these methods can only deal with the additive operations. It is still a challenging problem to solve the complex expression calculation problem, which includes the adding, subtracting, multiplying, dividing and bracketing operations. In this work, we regard the arithmetic expression calculation as a hierarchical reinforcement learning problem. An arithmetic operation is decomposed into a series of sub-tasks, and each sub-task is dealt with by a skill module. The skill module could be a basic module performing elementary operations, or interactive module performing complex operations by invoking other skill models. With curriculum learning, our model can deal with a complex arithmetic expression calculation with the deep hierarchical structure of skill models. Experiments show that our model significantly outperforms the previous models for arithmetic expression calculation.
Tasks	Hierarchical Reinforcement Learning
Published	2018-09-23
URL	http://arxiv.org/abs/1809.08590v1
PDF	http://arxiv.org/pdf/1809.08590v1.pdf
PWC	https://paperswithcode.com/paper/neural-arithmetic-expression-calculator
Repo
Framework

Audio Source Separation Using Variational Autoencoders and Weak Class Supervision


Title	Audio Source Separation Using Variational Autoencoders and Weak Class Supervision
Authors	Ertuğ Karamatlı, Ali Taylan Cemgil, Serap Kırbız
Abstract	In this paper, we propose a source separation method that is trained by observing the mixtures and the class labels of the sources present in the mixture without any access to isolated sources. Since our method does not require source class labels for every time-frequency bin but only a single label for each source constituting the mixture signal, we call this scenario as weak class supervision. We associate a variational autoencoder (VAE) with each source class within a non-negative (compositional) model. Each VAE provides a prior model to identify the signal from its associated class in a sound mixture. After training the model on mixtures, we obtain a generative model for each source class and demonstrate our method on one-second mixtures of utterances of digits from 0 to 9. We show that the separation performance obtained by source class supervision is as good as the performance obtained by source signal supervision.
Tasks	Denoising
Published	2018-10-31
URL	https://arxiv.org/abs/1810.13104v3
PDF	https://arxiv.org/pdf/1810.13104v3.pdf
PWC	https://paperswithcode.com/paper/weak-label-supervision-for-monaural-source
Repo
Framework

Whale swarm algorithm with the mechanism of identifying and escaping from extreme points for multimodal function optimization


Title	Whale swarm algorithm with the mechanism of identifying and escaping from extreme points for multimodal function optimization
Authors	Bing Zeng, Xinyu Li, Liang Gao, Yuyan Zhang, Haozhen Dong
Abstract	Most real-world optimization problems often come with multiple global optima or local optima. Therefore, increasing niching metaheuristic algorithms, which devote to finding multiple optima in a single run, are developed to solve these multimodal optimization problems. However, there are two difficulties urgently to be solved for most existing niching metaheuristic algorithms: how to set the optimal values of niching parameters for different optimization problems, and how to jump out of the local optima efficiently. These two difficulties limited their practicality largely. Based on Whale Swarm Algorithm (WSA) we proposed previously, this paper presents a new multimodal optimizer named WSA with Iterative Counter (WSA-IC) to address these two difficulties. In the one hand, WSA-IC improves the iteration rule of the original WSA for multimodal optimization, which removes the need of specifying different values of attenuation coefficient for different problems to form multiple subpopulations, without introducing any niching parameter. In the other hand, WSA-IC enables the identification of extreme point during iterations relying on two new parameters (i.e., stability threshold Ts and fitness threshold Tf), to jump out of the located extreme point. Moreover, the convergence of WSA-IC is proved. Finally, the proposed WSA-IC is compared with several niching metaheuristic algorithms on CEC2015 niching benchmark test functions and five additional classical multimodal functions with high dimensions. The experimental results demonstrate that WSA-IC statistically outperforms other niching metaheuristic algorithms on most test functions.
Tasks
Published	2018-04-09
URL	https://arxiv.org/abs/1804.02851v3
PDF	https://arxiv.org/pdf/1804.02851v3.pdf
PWC	https://paperswithcode.com/paper/whale-swarm-algorithm-with-the-mechanism-of
Repo
Framework

Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems


Title	Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems
Authors	Timothy A. Mann, Sven Gowal, András György, Ray Jiang, Huiyi Hu, Balaji Lakshminarayanan, Prav Srinivasan
Abstract	Predicting delayed outcomes is an important problem in recommender systems (e.g., if customers will finish reading an ebook). We formalize the problem as an adversarial, delayed online learning problem and consider how a proxy for the delayed outcome (e.g., if customers read a third of the book in 24 hours) can help minimize regret, even though the proxy is not available when making a prediction. Motivated by our regret analysis, we propose two neural network architectures: Factored Forecaster (FF) which is ideal if the proxy is informative of the outcome in hindsight, and Residual Factored Forecaster (RFF) that is robust to a non-informative proxy. Experiments on two real-world datasets for predicting human behavior show that RFF outperforms both FF and a direct forecaster that does not make use of the proxy. Our results suggest that exploiting proxies by factorization is a promising way to mitigate the impact of long delays in human-behavior prediction tasks.
Tasks	Recommendation Systems
Published	2018-07-24
URL	https://arxiv.org/abs/1807.09387v2
PDF	https://arxiv.org/pdf/1807.09387v2.pdf
PWC	https://paperswithcode.com/paper/learning-from-delayed-outcomes-with
Repo
Framework

Disentangled Variational Representation for Heterogeneous Face Recognition


Title	Disentangled Variational Representation for Heterogeneous Face Recognition
Authors	Xiang Wu, Huaibo Huang, Vishal M. Patel, Ran He, Zhenan Sun
Abstract	Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms. Existing approaches attempt to tackle this problem by either synthesizing visible faces from NIR faces, extracting domain-invariant features from these modalities, or projecting heterogeneous data onto a common latent space for cross-modal matching. In this paper, we take a different approach in which we make use of the Disentangled Variational Representation (DVR) for cross-modal matching. First, we model a face representation with an intrinsic identity information and its within-person variations. By exploring the disentangled latent variable space, a variational lower bound is employed to optimize the approximate posterior for NIR and VIS representations. Second, aiming at obtaining more compact and discriminative disentangled latent space, we impose a minimization of the identity information for the same subject and a relaxed correlation alignment constraint between the NIR and VIS modality variations. An alternative optimization scheme is proposed for the disentangled variational representation part and the heterogeneous face recognition network part. The mutual promotion between these two parts effectively reduces the NIR and VIS domain discrepancy and alleviates over-fitting. Extensive experiments on three challenging NIR-VIS heterogeneous face recognition databases demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods.
Tasks	Face Recognition, Heterogeneous Face Recognition
Published	2018-09-06
URL	http://arxiv.org/abs/1809.01936v3
PDF	http://arxiv.org/pdf/1809.01936v3.pdf
PWC	https://paperswithcode.com/paper/disentangled-variational-representation-for
Repo
Framework

CubeNet: Equivariance to 3D Rotation and Translation


Title	CubeNet: Equivariance to 3D Rotation and Translation
Authors	Daniel Worrall, Gabriel Brostow
Abstract	3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful representation of the voxelized object, while explaining the pose-difference between the two inputs. An equivariant representation vector has two components: the invariant identity part, and a discernable encoding of the transformation. Models that can’t explain pose-differences risk “diluting” the representation, in pursuit of optimizing a classification or regression loss function. We introduce a Group Convolutional Neural Network with linear equivariance to translations and right angle rotations in three dimensions. We call this network CubeNet, reflecting its cube-like symmetry. By construction, this network helps preserve a 3D shape’s global and local signature, as it is transformed through successive layers. We apply this network to a variety of 3D inference problems, achieving state-of-the-art on the ModelNet10 classification challenge, and comparable performance on the ISBI 2012 Connectome Segmentation Benchmark. To the best of our knowledge, this is the first 3D rotation equivariant CNN for voxel representations.
Tasks
Published	2018-04-12
URL	http://arxiv.org/abs/1804.04458v1
PDF	http://arxiv.org/pdf/1804.04458v1.pdf
PWC	https://paperswithcode.com/paper/cubenet-equivariance-to-3d-rotation-and
Repo
Framework

Wikistat 2.0: Educational Resources for Artificial Intelligence


Title	Wikistat 2.0: Educational Resources for Artificial Intelligence
Authors	Philippe Besse, Brendan Guillouet, Béatrice Laurent
Abstract	Big data, data science, deep learning, artificial intelligence are the key words of intense hype related with a job market in full evolution, that impose to adapt the contents of our university professional trainings. Which artificial intelligence is mostly concerned by the job offers? Which methodologies and technologies should be favored in the training programs? Which objectives, tools and educational resources do we needed to put in place to meet these pressing needs? We answer these questions in describing the contents and operational resources in the Data Science orientation of the specialty Applied Mathematics at INSA Toulouse. We focus on basic mathematics training (Optimization, Probability, Statistics), associated with the practical implementation of the most performing statistical learning algorithms, with the most appropriate technologies and on real examples. Considering the huge volatility of the technologies, it is imperative to train students in seft-training, this will be their technological watch tool when they will be in professional activity. This explains the structuring of the educational site github.com/wikistat into a set of tutorials. Finally, to motivate the thorough practice of these tutorials, a serious game is organized each year in the form of a prediction contest between students of Master degrees in Applied Mathematics for IA.
Tasks
Published	2018-09-28
URL	http://arxiv.org/abs/1810.02688v2
PDF	http://arxiv.org/pdf/1810.02688v2.pdf
PWC	https://paperswithcode.com/paper/wikistat-20-educational-resources-for
Repo
Framework

Hierarchical Reinforcement Learning with Deep Nested Agents


Title	Hierarchical Reinforcement Learning with Deep Nested Agents
Authors	Marc Brittain, Peng Wei
Abstract	Deep hierarchical reinforcement learning has gained a lot of attention in recent years due to its ability to produce state-of-the-art results in challenging environments where non-hierarchical frameworks fail to learn useful policies. However, as problem domains become more complex, deep hierarchical reinforcement learning can become inefficient, leading to longer convergence times and poor performance. We introduce the Deep Nested Agent framework, which is a variant of deep hierarchical reinforcement learning where information from the main agent is propagated to the low level $nested$ agent by incorporating this information into the nested agent’s state. We demonstrate the effectiveness and performance of the Deep Nested Agent framework by applying it to three scenarios in Minecraft with comparisons to a deep non-hierarchical single agent framework, as well as, a deep hierarchical framework.
Tasks	Hierarchical Reinforcement Learning
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07008v1
PDF	http://arxiv.org/pdf/1805.07008v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-reinforcement-learning-with-deep
Repo
Framework

PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making


Title	PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making
Authors	Fangkai Yang, Daoming Lyu, Bo Liu, Steven Gustafson
Abstract	Reinforcement learning and symbolic planning have both been used to build intelligent autonomous agents. Reinforcement learning relies on learning from interactions with real world, which often requires an unfeasibly large amount of experience. Symbolic planning relies on manually crafted symbolic knowledge, which may not be robust to domain uncertainties and changes. In this paper we present a unified framework {\em PEORL} that integrates symbolic planning with hierarchical reinforcement learning (HRL) to cope with decision-making in a dynamic environment with uncertainties. Symbolic plans are used to guide the agent’s task execution and learning, and the learned experience is fed back to symbolic knowledge to improve planning. This method leads to rapid policy search and robust symbolic plans in complex domains. The framework is tested on benchmark domains of HRL.
Tasks	Decision Making, Hierarchical Reinforcement Learning
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07779v3
PDF	http://arxiv.org/pdf/1804.07779v3.pdf
PWC	https://paperswithcode.com/paper/peorl-integrating-symbolic-planning-and
Repo
Framework

Patchwise object tracking via structural local sparse appearance model


Title	Patchwise object tracking via structural local sparse appearance model
Authors	Hossein Kashiyani, Shahriar B. Shokouhi
Abstract	In this paper, we propose a robust visual tracking method which exploits the relationships of targets in adjacent frames using patchwise joint sparse representation. Two sets of overlapping patches with different sizes are extracted from target candidates to construct two dictionaries with consideration of joint sparse representation. By applying this representation into structural sparse appearance model, we can take two-fold advantages. First, the correlation of target patches over time is considered. Second, using this local appearance model with different patch sizes takes into account local features of target thoroughly. Furthermore, the position of candidate patches and their occlusion levels are utilized simultaneously to obtain the final likelihood of target candidates. Evaluations on recent challenging benchmark show that our tracking method outperforms the state-of-the-art trackers.
Tasks	Object Tracking, Visual Tracking
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06141v1
PDF	http://arxiv.org/pdf/1803.06141v1.pdf
PWC	https://paperswithcode.com/paper/patchwise-object-tracking-via-structural
Repo
Framework

Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification


Title	Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
Authors	Yang Du, Chunfeng Yuan, Bing Li, Lili Zhao, Yangxi Li, Weiming Hu
Abstract	Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local feature to obtain its weight score, which ignores interactions among local features. To address this, we propose an effective interaction-aware self-attention model inspired by PCA to learn attention maps. Furthermore, since different layers in a deep network capture feature maps of different scales, we use these feature maps to construct a spatial pyramid and then utilize multi-scale information to obtain more accurate attention scores, which are used to weight the local features in all spatial positions of feature maps to calculate attention maps. Moreover, our spatial pyramid attention is unrestricted to the number of its input feature maps so it is easily extended to a spatio-temporal version. Finally, our model is embedded in general CNNs to form end-to-end attention networks for action classification. Experimental results show that our method achieves the state-of-the-art results on the UCF101, HMDB51 and untrimmed Charades.
Tasks	Action Classification
Published	2018-08-03
URL	http://arxiv.org/abs/1808.01106v1
PDF	http://arxiv.org/pdf/1808.01106v1.pdf
PWC	https://paperswithcode.com/paper/interaction-aware-spatio-temporal-pyramid
Repo
Framework

Estimation of Non-Normalized Mixture Models and Clustering Using Deep Representation


Title	Estimation of Non-Normalized Mixture Models and Clustering Using Deep Representation
Authors	Takeru Matsuda, Aapo Hyvarinen
Abstract	We develop a general method for estimating a finite mixture of non-normalized models. Here, a non-normalized model is defined to be a parametric distribution with an intractable normalization constant. Existing methods for estimating non-normalized models without computing the normalization constant are not applicable to mixture models because they contain more than one intractable normalization constant. The proposed method is derived by extending noise contrastive estimation (NCE), which estimates non-normalized models by discriminating between the observed data and some artificially generated noise. We also propose an extension of NCE with multiple noise distributions. Then, based on the observation that conventional classification learning with neural networks is implicitly assuming an exponential family as a generative model, we introduce a method for clustering unlabeled data by estimating a finite mixture of distributions in an exponential family. Estimation of this mixture model is attained by the proposed extensions of NCE where the training data of neural networks are used as noise. Thus, the proposed method provides a probabilistically principled clustering method that is able to utilize a deep representation. Application to image clustering using a deep neural network gives promising results.
Tasks	Image Clustering
Published	2018-05-19
URL	http://arxiv.org/abs/1805.07516v1
PDF	http://arxiv.org/pdf/1805.07516v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-non-normalized-mixture-models
Repo
Framework