January 26, 2020

3436 words 17 mins read

Paper Group ANR 1484

Enriching Ontology-based Data Access with Provenance (Extended Version). To Monitor Or Not: Observing Robot’s Behavior based on a Game-Theoretic Model of Trust. Short-term forecasting of solar irradiance without local telemetry: a generalized model using satellite data. Memory-Augmented Temporal Dynamic Learning for Action Recognition. Relation Str …

Enriching Ontology-based Data Access with Provenance (Extended Version)


Title	Enriching Ontology-based Data Access with Provenance (Extended Version)
Authors	Diego Calvanese, Davide Lanti, Ana Ozaki, Rafael Penaloza, Guohui Xiao
Abstract	Ontology-based data access (OBDA) is a popular paradigm for querying heterogeneous data sources by connecting them through mappings to an ontology. In OBDA, it is often difficult to reconstruct why a tuple occurs in the answer of a query. We address this challenge by enriching OBDA with provenance semirings, taking inspiration from database theory. In particular, we investigate the problems of (i) deciding whether a provenance annotated OBDA instance entails a provenance annotated conjunctive query, and (ii) computing a polynomial representing the provenance of a query entailed by a provenance annotated OBDA instance. Differently from pure databases, in our case these polynomials may be infinite. To regain finiteness, we consider idempotent semirings, and study the complexity in the case of DL-Lite ontologies. We implement Task (ii) in a state-of-the-art OBDA system and show the practical feasibility of the approach through an extensive evaluation against two popular benchmarks.
Tasks
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00179v1
PDF	https://arxiv.org/pdf/1906.00179v1.pdf
PWC	https://paperswithcode.com/paper/190600179
Repo
Framework

To Monitor Or Not: Observing Robot’s Behavior based on a Game-Theoretic Model of Trust


Title	To Monitor Or Not: Observing Robot’s Behavior based on a Game-Theoretic Model of Trust
Authors	Sailik Sengupta, Zahra Zahedi, Subbarao Kambhampati
Abstract	In scenarios where a robot generates and executes a plan, there may be instances where this generated plan is less costly for the robot to execute but incomprehensible to the human. When the human acts as a supervisor and is held accountable for the robot’s plan, the human may be at a higher risk if the incomprehensible behavior is deemed to be infeasible or unsafe. In such cases, the robot, who may be unaware of the human’s exact expectations, may choose to execute (1) the most constrained plan (i.e. one preferred by all possible supervisors) incurring the added cost of executing highly sub-optimal behavior when the human is monitoring it and (2) deviate to a more optimal plan when the human looks away. While robots do not have human-like ulterior motives (such as being lazy), such behavior may occur because the robot has to cater to the needs of different human supervisors. In such settings, the robot, being a rational agent, should take any chance it gets to deviate to a lower cost plan. On the other hand, continuous monitoring of the robot’s behavior is often difficult for humans because it costs them valuable resources (e.g., time, cognitive overload, etc.). Thus, to optimize the cost for monitoring while ensuring the robots follow the safe behavior, we model this problem in the game-theoretic framework of trust. In settings where the human does not initially trust the robot, pure-strategy Nash Equilibrium provides a useful policy for the human.
Tasks
Published	2019-03-01
URL	https://arxiv.org/abs/1903.00111v3
PDF	https://arxiv.org/pdf/1903.00111v3.pdf
PWC	https://paperswithcode.com/paper/to-monitor-or-to-trust-observing-robots
Repo
Framework

Short-term forecasting of solar irradiance without local telemetry: a generalized model using satellite data


Title	Short-term forecasting of solar irradiance without local telemetry: a generalized model using satellite data
Authors	Jesus Lago, Karel De Brabandere, Fjo De Ridder, Bart De Schutter
Abstract	Due to the increasing integration of solar power into the electrical grid, forecasting short-term solar irradiance has become key for many applications, e.g.~operational planning, power purchases, reserve activation, etc. In this context, as solar generators are geographically dispersed and ground measurements are not always easy to obtain, it is very important to have general models that can predict solar irradiance without the need of local data. In this paper, a model that can perform short-term forecasting of solar irradiance in any general location without the need of ground measurements is proposed. To do so, the model considers satellite-based measurements and weather-based forecasts, and employs a deep neural network structure that is able to generalize across locations; particularly, the network is trained only using a small subset of sites where ground data is available, and the model is able to generalize to a much larger number of locations where ground data does not exist. As a case study, 25 locations in The Netherlands are considered and the proposed model is compared against four local models that are individually trained for each location using ground measurements. Despite the general nature of the model, it is shown show that the proposed model is equal or better than the local models: when comparing the average performance across all the locations and prediction horizons, the proposed model obtains a 31.31% rRMSE (relative root mean square error) while the best local model achieves a 32.01% rRMSE.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04932v1
PDF	https://arxiv.org/pdf/1911.04932v1.pdf
PWC	https://paperswithcode.com/paper/short-term-forecasting-of-solar-irradiance
Repo
Framework

Memory-Augmented Temporal Dynamic Learning for Action Recognition


Title	Memory-Augmented Temporal Dynamic Learning for Action Recognition
Authors	Yuan Yuan, Dong Wang, Qi Wang
Abstract	Human actions captured in video sequences contain two crucial factors for action recognition, i.e., visual appearance and motion dynamics. To model these two aspects, Convolutional and Recurrent Neural Networks (CNNs and RNNs) are adopted in most existing successful methods for recognizing actions. However, CNN based methods are limited in modeling long-term motion dynamics. RNNs are able to learn temporal motion dynamics but lack effective ways to tackle unsteady dynamics in long-duration motion. In this work, we propose a memory-augmented temporal dynamic learning network, which learns to write the most evident information into an external memory module and ignore irrelevant ones. In particular, we present a differential memory controller to make a discrete decision on whether the external memory module should be updated with current feature. The discrete memory controller takes in the memory history, context embedding and current feature as inputs and controls information flow into the external memory module. Additionally, we train this discrete memory controller using straight-through estimator. We evaluate this end-to-end system on benchmark datasets (UCF101 and HMDB51) of human action recognition. The experimental results show consistent improvements on both datasets over prior works and our baselines.
Tasks	Temporal Action Localization
Published	2019-04-30
URL	http://arxiv.org/abs/1904.13080v1
PDF	http://arxiv.org/pdf/1904.13080v1.pdf
PWC	https://paperswithcode.com/paper/memory-augmented-temporal-dynamic-learning
Repo
Framework

Relation Structure-Aware Heterogeneous Information Network Embedding


Title	Relation Structure-Aware Heterogeneous Information Network Embedding
Authors	Yuanfu Lu, Chuan Shi, Linmei Hu, Zhiyuan Liu
Abstract	Heterogeneous information network (HIN) embedding aims to embed multiple types of nodes into a low-dimensional space. Although most existing HIN embedding methods consider heterogeneous relations in HINs, they usually employ one single model for all relations without distinction, which inevitably restricts the capability of network embedding. In this paper, we take the structural characteristics of heterogeneous relations into consideration and propose a novel Relation structure-aware Heterogeneous Information Network Embedding model (RHINE). By exploring the real-world networks with thorough mathematical analysis, we present two structure-related measures which can consistently distinguish heterogeneous relations into two categories: Affiliation Relations (ARs) and Interaction Relations (IRs). To respect the distinctive characteristics of relations, in our RHINE, we propose different models specifically tailored to handle ARs and IRs, which can better capture the structures and semantics of the networks. At last, we combine and optimize these models in a unified and elegant manner. Extensive experiments on three real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods in various tasks, including node clustering, link prediction, and node classification.
Tasks	Link Prediction, Network Embedding, Node Classification
Published	2019-05-15
URL	https://arxiv.org/abs/1905.08027v1
PDF	https://arxiv.org/pdf/1905.08027v1.pdf
PWC	https://paperswithcode.com/paper/relation-structure-aware-heterogeneous
Repo
Framework

Empirical Hypothesis Space Reduction


Title	Empirical Hypothesis Space Reduction
Authors	Akihiro Yabe, Takanori Maehara
Abstract	Selecting appropriate regularization coefficients is critical to performance with respect to regularized empirical risk minimization problems. Existing theoretical approaches attempt to determine the coefficients in order for regularized empirical objectives to be upper-bounds of true objectives, uniformly over a hypothesis space. Such an approach is, however, known to be over-conservative, especially in high-dimensional settings with large hypothesis space. In fact, an existing generalization error bound in variance-based regularization is $O(\sqrt{d \log n/n})$, where $d$ is the dimension of hypothesis space, and thus the number of samples required for convergence linearly increases with respect to $d$. This paper proposes an algorithm that calculates regularization coefficient, one which results in faster convergence of generalization error $O(\sqrt{\log n/n})$ and whose leading term is independent of the dimension $d$. This faster convergence without dependence on the size of the hypothesis space is achieved by means of empirical hypothesis space reduction, which, with high probability, successfully reduces a hypothesis space without losing the true optimum solution. Calculation of uniform upper bounds over reduced spaces, then, enables acceleration of the convergence of generalization error.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01576v1
PDF	https://arxiv.org/pdf/1909.01576v1.pdf
PWC	https://paperswithcode.com/paper/empirical-hypothesis-space-reduction
Repo
Framework

Searching for Accurate Binary Neural Architectures


Title	Searching for Accurate Binary Neural Architectures
Authors	Mingzhu Shen, Kai Han, Chunjing Xu, Yunhe Wang
Abstract	Binary neural networks have attracted tremendous attention due to the efficiency for deploying them on mobile devices. Since the weak expression ability of binary weights and features, their accuracy is usually much lower than that of full-precision (i.e. 32-bit) models. Here we present a new frame work for automatically searching for compact but accurate binary neural networks. In practice, number of channels in each layer will be encoded into the search space and optimized using the evolutionary algorithm. Experiments conducted on benchmark datasets and neural architectures demonstrate that our searched binary networks can achieve the performance of full-precision models with acceptable increments on model sizes and calculations.
Tasks
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07378v1
PDF	https://arxiv.org/pdf/1909.07378v1.pdf
PWC	https://paperswithcode.com/paper/searching-for-accurate-binary-neural
Repo
Framework

RNNSecureNet: Recurrent neural networks for Cyber security use-cases


Title	RNNSecureNet: Recurrent neural networks for Cyber security use-cases
Authors	Mohammed Harun Babu R, Vinayakumar R, Soman KP
Abstract	Recurrent neural network (RNN) is an effective neural network in solving very complex supervised and unsupervised tasks. There has been a significant improvement in RNN field such as natural language processing, speech processing, computer vision and other multiple domains. This paper deals with RNN application on different use cases like Incident Detection, Fraud Detection, and Android Malware Classification. The best performing neural network architecture is chosen by conducting different chain of experiments for different network parameters and structures. The network is run up to 1000 epochs with learning rate set in the range of 0.01 to 0.5.Obviously, RNN performed very well when compared to classical machine learning algorithms. This is mainly possible because RNNs implicitly extracts the underlying features and also identifies the characteristics of the data. This helps to achieve better accuracy.
Tasks	Fraud Detection, Malware Classification
Published	2019-01-05
URL	http://arxiv.org/abs/1901.04281v1
PDF	http://arxiv.org/pdf/1901.04281v1.pdf
PWC	https://paperswithcode.com/paper/rnnsecurenet-recurrent-neural-networks-for
Repo
Framework

Contextual One-Class Classification in Data Streams


Title	Contextual One-Class Classification in Data Streams
Authors	Richard Hugh Moulton, Herna L. Viktor, Nathalie Japkowicz, João Gama
Abstract	In machine learning, the one-class classification problem occurs when training instances are only available from one class. It has been observed that making use of this class’s structure, or its different contexts, may improve one-class classifier performance. Although this observation has been demonstrated for static data, a rigorous application of the idea within the data stream environment is lacking. To address this gap, we propose the use of context to guide one-class classifier learning in data streams, paying particular attention to the challenges presented by the dynamic learning environment. We present three frameworks that learn contexts and conduct experiments with synthetic and benchmark data streams. We conclude that the paradigm of contexts in data streams can be used to improve the performance of streaming one-class classifiers.
Tasks	One-class classifier
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04233v1
PDF	https://arxiv.org/pdf/1907.04233v1.pdf
PWC	https://paperswithcode.com/paper/contextual-one-class-classification-in-data
Repo
Framework

Intrinsic Calibration of Depth Cameras for Mobile Robots using a Radial Laser Scanner


Title	Intrinsic Calibration of Depth Cameras for Mobile Robots using a Radial Laser Scanner
Authors	David Zuñiga-Noël, Jose-Raul Ruiz-Sarmiento, Javier Gonzalez-Jimenez
Abstract	Depth cameras, typically in RGB-D configurations, are common devices in mobile robotic platforms given their appealing features: high frequency and resolution, low price and power requirements, among others. These sensors may come with significant, non-linear errors in the depth measurements that jeopardize robot tasks, like free-space detection, environment reconstruction or visual robot-human interaction. This paper presents a method to calibrate such systematic errors with the help of a second, more precise range sensor, in our case a radial laser scanner. In contrast to what it may seem at first, this does not mean a serious limitation in practice since these two sensors are often mounted jointly in many mobile robotic platforms, as they complement well each other. Moreover, the laser scanner can be used just for the calibration process and get rid of it after that. The main contributions of the paper are: i) the calibration is formulated from a probabilistic perspective through a Maximum Likelihood Estimation problem, and ii) the proposed method can be easily executed automatically by mobile robotic platforms. To validate the proposed approach we evaluated for both, local distortion of 3D planar reconstructions and global shifts in the measurements, obtaining considerably more accurate results. A C++ open-source implementation of the presented method has been released for the benefit of the community.
Tasks	Calibration
Published	2019-07-03
URL	https://arxiv.org/abs/1907.01839v1
PDF	https://arxiv.org/pdf/1907.01839v1.pdf
PWC	https://paperswithcode.com/paper/intrinsic-calibration-of-depth-cameras-for
Repo
Framework

A comparison of evaluation methods in coevolution


Title	A comparison of evaluation methods in coevolution
Authors	Ting-Shuo Yo, Edwin de Jong
Abstract	In this research, we compare four different evaluation methods in coevolution on the Majority Function problem. The size of the problem is selected such that evaluation against all possible test cases is feasible. Two measures are used for the comparisons, i.e., the objective fitness derived from evaluating solutions against all test cases, and the objective fitness correlation (OFC), which is defined as the correlation coefficient between subjective and objective fitness. The results of our experiments suggest that a combination of average score and weighted informativeness may provide a more accurate evaluation in coevolution. In order to confirm this difference, a series of t-tests on the preference between each pair of the evaluation methods is performed. The resulting significance is affirmative, and the tests for two quality measures show similar preference on four evaluation methods. %This study is the first time OFC is actually computed on a real problem. Experiments on Majority Function problems with larger sizes and Parity problems are in progress, and their results will be added in the final version.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08723v1
PDF	https://arxiv.org/pdf/1905.08723v1.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-evaluation-methods-in
Repo
Framework

Weakly and Semi Supervised Detection in Medical Imaging via Deep Dual Branch Net


Title	Weakly and Semi Supervised Detection in Medical Imaging via Deep Dual Branch Net
Authors	Ran Bakalo, Jacob Goldberger, Rami Ben-Ari
Abstract	This study presents a novel deep learning architecture for multi-class classification and localization of abnormalities in medical imaging illustrated through experiments on mammograms. The proposed network combines two learning branches. One branch is for region classification with a newly added normal-region class. Second branch is region detection branch for ranking regions relative to one another. Our method enables detection of abnormalities at full mammogram resolution for both weakly and semi-supervised settings. A novel objective function allows for the incorporation of local annotations into the model. We present the impact of our schemes on several performance measures for classification and localization, to evaluate the cost effectiveness of the lesion annotation effort. Our evaluation was primarily conducted over a large multi-center mammography dataset of $\sim$3,000 mammograms with various findings. The results for weakly supervised learning showed significant improvement compared to previous approaches. We show that the time consuming local annotations involved in supervised learning can be addressed by a weakly supervised method that can leverage a subset of locally annotated data. Weakly and semi-supervised methods coupled with detection can produce a cost effective and explainable model to be adopted by radiologists in the field.
Tasks
Published	2019-04-29
URL	https://arxiv.org/abs/1904.12589v3
PDF	https://arxiv.org/pdf/1904.12589v3.pdf
PWC	https://paperswithcode.com/paper/a-dual-branch-deep-neural-network-for
Repo
Framework

Modelling Bahdanau Attention using Election methods aided by Q-Learning


Title	Modelling Bahdanau Attention using Election methods aided by Q-Learning
Authors	Rakesh Bal, Sayan Sinha
Abstract	Neural Machine Translation has lately gained a lot of “attention” with the advent of more and more sophisticated but drastically improved models. Attention mechanism has proved to be a boon in this direction by providing weights to the input words, making it easy for the decoder to identify words representing the present context. But by and by, as newer attention models with more complexity came into development, they involved large computation, making inference slow. In this paper, we have modelled the attention network using techniques resonating with social choice theory. Along with that, the attention mechanism, being a Markov Decision Process, has been represented by reinforcement learning techniques. Thus, we propose to use an election method ($k$-Borda), fine-tuned using Q-learning, as a replacement for attention networks. The inference time for this network is less than a standard Bahdanau translator, and the results of the translation are comparable. This not only experimentally verifies the claims stated above but also helped provide a faster inference.
Tasks	Machine Translation, Q-Learning
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03853v2
PDF	https://arxiv.org/pdf/1911.03853v2.pdf
PWC	https://paperswithcode.com/paper/modelling-bahdanau-attention-using-election
Repo
Framework

Sketch-Specific Data Augmentation for Freehand Sketch Recognition


Title	Sketch-Specific Data Augmentation for Freehand Sketch Recognition
Authors	Ying Zheng, Hongxun Yao, Xiaoshuai Sun, Shengping Zhang, Sicheng Zhao, Fatih Porikli
Abstract	Sketch recognition remains a significant challenge due to the limited training data and the substantial intra-class variance of freehand sketches for the same object. Conventional methods for this task often rely on the availability of the temporal order of sketch strokes, additional cues acquired from different modalities and supervised augmentation of sketch datasets with real images, which also limit the applicability and feasibility of these methods in real scenarios. In this paper, we propose a novel sketch-specific data augmentation (SSDA) method that leverages the quantity and quality of the sketches automatically. From the aspect of quantity, we introduce a Bezier pivot based deformation (BPD) strategy to enrich the training data. Towards quality improvement, we present a mean stroke reconstruction (MSR) approach to generate a set of novel types of sketches with smaller intra-class variances. Both of these solutions are unrestricted from any multi-source data and temporal cues of sketches. Furthermore, we show that some recent deep convolutional neural network models that are trained on generic classes of real images can be better choices than most of the elaborate architectures that are designed explicitly for sketch recognition. As SSDA can be integrated with any convolutional neural networks, it has a distinct advantage over the existing methods. Our extensive experimental evaluations demonstrate that the proposed method achieves state-of-the-art results (84.27%) on the TU-Berlin dataset, outperforming the human performance by a remarkable 11.17% increase. We also present a new benchmark named Sketchy-R to facilitate future research in sketch recognition. Finally, more experiments show the practical value of our approach to the task of sketch-based image retrieval.
Tasks	Data Augmentation, Image Retrieval, Sketch-Based Image Retrieval, Sketch Recognition
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06038v1
PDF	https://arxiv.org/pdf/1910.06038v1.pdf
PWC	https://paperswithcode.com/paper/sketch-specific-data-augmentation-for
Repo
Framework

UniSent: Universal Adaptable Sentiment Lexica for 1000+ Languages


Title	UniSent: Universal Adaptable Sentiment Lexica for 1000+ Languages
Authors	Ehsaneddin Asgari, Fabienne Braune, Benjamin Roth, Christoph Ringlstetter, Mohammad R. K. Mofrad
Abstract	In this paper, we introduce UniSent universal sentiment lexica for $1000+$ languages. Sentiment lexica are vital for sentiment analysis in absence of document-level annotations, a very common scenario for low-resource languages. To the best of our knowledge, UniSent is the largest sentiment resource to date in terms of the number of covered languages, including many low resource ones. In this work, we use a massively parallel Bible corpus to project sentiment information from English to other languages for sentiment analysis on Twitter data. We introduce a method called DomDrift to mitigate the huge domain mismatch between Bible and Twitter by a confidence weighting scheme that uses domain-specific embeddings to compare the nearest neighbors for a candidate sentiment word in the source (Bible) and target (Twitter) domain. We evaluate the quality of UniSent in a subset of languages for which manually created ground truth was available, Macedonian, Czech, German, Spanish, and French. We show that the quality of UniSent is comparable to manually created sentiment resources when it is used as the sentiment seed for the task of word sentiment prediction on top of embedding representations. In addition, we show that emoticon sentiments could be reliably predicted in the Twitter domain using only UniSent and monolingual embeddings in German, Spanish, French, and Italian. With the publication of this paper, we release the UniSent sentiment lexica.
Tasks	Domain Adaptation, Sentiment Analysis, Unsupervised Domain Adaptation
Published	2019-04-21
URL	https://arxiv.org/abs/1904.09678v2
PDF	https://arxiv.org/pdf/1904.09678v2.pdf
PWC	https://paperswithcode.com/paper/unisent-universal-adaptable-sentiment-lexica
Repo
Framework