July 29, 2019

3078 words 15 mins read

Paper Group ANR 27

Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks. Fast Singular Value Shrinkage with Chebyshev Polynomial Approximation Based on Signal Sparsity. Machine Learning with World Knowledge: The Position and Survey. PSO-Optimized Hopfield Neural Network-Based Multipath Routing for Mobile Ad-hoc Networks …

Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks


Title	Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks
Authors	Guohao Li, Hang Su, Wenwu Zhu
Abstract	Visual Question Answering (VQA) has attracted much attention since it offers insight into the relationships between the multi-modal analysis of images and natural language. Most of the current algorithms are incapable of answering open-domain questions that require to perform reasoning beyond the image contents. To address this issue, we propose a novel framework which endows the model capabilities in answering more complex questions by leveraging massive external knowledge with dynamic memory networks. Specifically, the questions along with the corresponding images trigger a process to retrieve the relevant information in external knowledge bases, which are embedded into a continuous vector space by preserving the entity-relation structures. Afterwards, we employ dynamic memory networks to attend to the large body of facts in the knowledge graph and images, and then perform reasoning over these facts to generate corresponding answers. Extensive experiments demonstrate that our model not only achieves the state-of-the-art performance in the visual question answering task, but can also answer open-domain questions effectively by leveraging the external knowledge.
Tasks	Question Answering, Visual Question Answering
Published	2017-12-03
URL	http://arxiv.org/abs/1712.00733v1
PDF	http://arxiv.org/pdf/1712.00733v1.pdf
PWC	https://paperswithcode.com/paper/incorporating-external-knowledge-to-answer
Repo
Framework

Fast Singular Value Shrinkage with Chebyshev Polynomial Approximation Based on Signal Sparsity


Title	Fast Singular Value Shrinkage with Chebyshev Polynomial Approximation Based on Signal Sparsity
Authors	Masaki Onuki, Shunsuke Ono, Keiichiro Shirai, Yuichi Tanaka
Abstract	We propose an approximation method for thresholding of singular values using Chebyshev polynomial approximation (CPA). Many signal processing problems require iterative application of singular value decomposition (SVD) for minimizing the rank of a given data matrix with other cost functions and/or constraints, which is called matrix rank minimization. In matrix rank minimization, singular values of a matrix are shrunk by hard-thresholding, soft-thresholding, or weighted soft-thresholding. However, the computational cost of SVD is generally too expensive to handle high dimensional signals such as images; hence, in this case, matrix rank minimization requires enormous computation time. In this paper, we leverage CPA to (approximately) manipulate singular values without computing singular values and vectors. The thresholding of singular values is expressed by a multiplication of certain matrices, which is derived from a characteristic of CPA. The multiplication is also efficiently computed using the sparsity of signals. As a result, the computational cost is significantly reduced. Experimental results suggest the effectiveness of our method through several image processing applications based on matrix rank minimization with nuclear norm relaxation in terms of computation time and approximation precision.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07112v1
PDF	http://arxiv.org/pdf/1705.07112v1.pdf
PWC	https://paperswithcode.com/paper/fast-singular-value-shrinkage-with-chebyshev
Repo
Framework

Machine Learning with World Knowledge: The Position and Survey


Title	Machine Learning with World Knowledge: The Position and Survey
Authors	Yangqiu Song, Dan Roth
Abstract	Machine learning has become pervasive in multiple domains, impacting a wide variety of applications, such as knowledge discovery and data mining, natural language processing, information retrieval, computer vision, social and health informatics, ubiquitous computing, etc. Two essential problems of machine learning are how to generate features and how to acquire labels for machines to learn. Particularly, labeling large amount of data for each domain-specific problem can be very time consuming and costly. It has become a key obstacle in making learning protocols realistic in applications. In this paper, we will discuss how to use the existing general-purpose world knowledge to enhance machine learning processes, by enriching the features or reducing the labeling work. We start from the comparison of world knowledge with domain-specific knowledge, and then introduce three key problems in using world knowledge in learning processes, i.e., explicit and implicit feature representation, inference for knowledge linking and disambiguation, and learning with direct or indirect supervision. Finally we discuss the future directions of this research topic.
Tasks	Information Retrieval
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02908v1
PDF	http://arxiv.org/pdf/1705.02908v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-with-world-knowledge-the
Repo
Framework

PSO-Optimized Hopfield Neural Network-Based Multipath Routing for Mobile Ad-hoc Networks


Title	PSO-Optimized Hopfield Neural Network-Based Multipath Routing for Mobile Ad-hoc Networks
Authors	Mansour Sheikhan, Ehsan Hemmati
Abstract	Mobile ad-hoc network (MANET) is a dynamic collection of mobile computers without the need for any existing infrastructure. Nodes in a MANET act as hosts and routers. Designing of robust routing algorithms for MANETs is a challenging task. Disjoint multipath routing protocols address this problem and increase the reliability, security and lifetime of network. However, selecting an optimal multipath is an NP-complete problem. In this paper, Hopfield neural network (HNN) which its parameters are optimized by particle swarm optimization (PSO) algorithm is proposed as multipath routing algorithm. Link expiration time (LET) between each two nodes is used as the link reliability estimation metric. This approach can find either node-disjoint or link-disjoint paths in single phase route discovery. Simulation results confirm that PSO-HNN routing algorithm has better performance as compared to backup path set selection algorithm (BPSA) in terms of the path set reliability and number of paths in the set.
Tasks
Published	2017-11-16
URL	http://arxiv.org/abs/1712.07019v1
PDF	http://arxiv.org/pdf/1712.07019v1.pdf
PWC	https://paperswithcode.com/paper/pso-optimized-hopfield-neural-network-based
Repo
Framework

Extractive Multi Document Summarization using Dynamical Measurements of Complex Networks


Title	Extractive Multi Document Summarization using Dynamical Measurements of Complex Networks
Authors	Jorge V. Tohalino, Diego R. Amancio
Abstract	Due to the large amount of textual information available on Internet, it is of paramount relevance to use techniques that find relevant and concise content. A typical task devoted to the identification of informative sentences in documents is the so called extractive document summarization task. In this paper, we use complex network concepts to devise an extractive Multi Document Summarization (MDS) method, which extracts the most central sentences from several textual sources. In the proposed model, texts are represented as networks, where nodes represent sentences and the edges are established based on the number of shared words. Differently from previous works, the identification of relevant terms is guided by the characterization of nodes via dynamical measurements of complex networks, including symmetry, accessibility and absorption time. The evaluation of the proposed system revealed that excellent results were obtained with particular dynamical measurements, including those based on the exploration of networks via random walks.
Tasks	Document Summarization, Extractive Document Summarization, Multi-Document Summarization
Published	2017-08-05
URL	http://arxiv.org/abs/1708.01769v1
PDF	http://arxiv.org/pdf/1708.01769v1.pdf
PWC	https://paperswithcode.com/paper/extractive-multi-document-summarization-using-1
Repo
Framework

Empirical Evaluation of Abstract Argumentation: Supporting the Need for Bipolar and Probabilistic Approaches


Title	Empirical Evaluation of Abstract Argumentation: Supporting the Need for Bipolar and Probabilistic Approaches
Authors	Sylwia Polberg, Anthony Hunter
Abstract	In dialogical argumentation it is often assumed that the involved parties always correctly identify the intended statements posited by each other, realize all of the associated relations, conform to the three acceptability states (accepted, rejected, undecided), adjust their views when new and correct information comes in, and that a framework handling only attack relations is sufficient to represent their opinions. Although it is natural to make these assumptions as a starting point for further research, removing them or even acknowledging that such removal should happen is more challenging for some of these concepts than for others. Probabilistic argumentation is one of the approaches that can be harnessed for more accurate user modelling. The epistemic approach allows us to represent how much a given argument is believed by a given person, offering us the possibility to express more than just three agreement states. It is equipped with a wide range of postulates, including those that do not make any restrictions concerning how initial arguments should be viewed, thus potentially being more adequate for handling beliefs of the people that have not fully disclosed their opinions in comparison to Dung’s semantics. The constellation approach can be used to represent the views of different people concerning the structure of the framework we are dealing with, including cases in which not all relations are acknowledged or when they are seen differently than intended. Finally, bipolar argumentation frameworks can be used to express both positive and negative relations between arguments. In this paper we describe the results of an experiment in which participants judged dialogues in terms of agreement and structure. We compare our findings with the aforementioned assumptions as well as with the constellation and epistemic approaches to probabilistic argumentation and bipolar argumentation.
Tasks	Abstract Argumentation
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09324v2
PDF	http://arxiv.org/pdf/1707.09324v2.pdf
PWC	https://paperswithcode.com/paper/empirical-evaluation-of-abstract
Repo
Framework

Learning Discrete Distributions from Untrusted Batches


Title	Learning Discrete Distributions from Untrusted Batches
Authors	Mingda Qiao, Gregory Valiant
Abstract	We consider the problem of learning a discrete distribution in the presence of an $\epsilon$ fraction of malicious data sources. Specifically, we consider the setting where there is some underlying distribution, $p$, and each data source provides a batch of $\ge k$ samples, with the guarantee that at least a $(1-\epsilon)$ fraction of the sources draw their samples from a distribution with total variation distance at most $\eta$ from $p$. We make no assumptions on the data provided by the remaining $\epsilon$ fraction of sources–this data can even be chosen as an adversarial function of the $(1-\epsilon)$ fraction of “good” batches. We provide two algorithms: one with runtime exponential in the support size, $n$, but polynomial in $k$, $1/\epsilon$ and $1/\eta$ that takes $O((n+k)/\epsilon^2)$ batches and recovers $p$ to error $O(\eta+\epsilon/\sqrt{k})$. This recovery accuracy is information theoretically optimal, to constant factors, even given an infinite number of data sources. Our second algorithm applies to the $\eta = 0$ setting and also achieves an $O(\epsilon/\sqrt{k})$ recover guarantee, though it runs in $\mathrm{poly}((nk)^k)$ time. This second algorithm, which approximates a certain tensor via a rank-1 tensor minimizing $\ell_1$ distance, is surprising in light of the hardness of many low-rank tensor approximation problems, and may be of independent interest.
Tasks
Published	2017-11-22
URL	http://arxiv.org/abs/1711.08113v1
PDF	http://arxiv.org/pdf/1711.08113v1.pdf
PWC	https://paperswithcode.com/paper/learning-discrete-distributions-from
Repo
Framework

$1 Today or $2 Tomorrow? The Answer is in Your Facebook Likes


Title	$1 Today or $2 Tomorrow? The Answer is in Your Facebook Likes
Authors	Tao Ding, Warren K. Bickel, Shimei Pan
Abstract	In economics and psychology, delay discounting is often used to characterize how individuals choose between a smaller immediate reward and a larger delayed reward. People with higher delay discounting rate (DDR) often choose smaller but more immediate rewards (a “today person”). In contrast, people with a lower discounting rate often choose a larger future rewards (a “tomorrow person”). Since the ability to modulate the desire of immediate gratification for long term rewards plays an important role in our decision-making, the lower discounting rate often predicts better social, academic and health outcomes. In contrast, the higher discounting rate is often associated with problematic behaviors such as alcohol/drug abuse, pathological gambling and credit card default. Thus, research on understanding and moderating delay discounting has the potential to produce substantial societal benefits.
Tasks	Decision Making
Published	2017-03-22
URL	http://arxiv.org/abs/1703.07726v3
PDF	http://arxiv.org/pdf/1703.07726v3.pdf
PWC	https://paperswithcode.com/paper/1-today-or-2-tomorrow-the-answer-is-in-your
Repo
Framework

Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results


Title	Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results
Authors	Bingshui Da, Yew-Soon Ong, Liang Feng, A. K. Qin, Abhishek Gupta, Zexuan Zhu, Chuan-Kang Ting, Ke Tang, Xin Yao
Abstract	In this report, we suggest nine test problems for multi-task single-objective optimization (MTSOO), each of which consists of two single-objective optimization tasks that need to be solved simultaneously. The relationship between tasks varies between different test problems, which would be helpful to have a comprehensive evaluation of the MFO algorithms. It is expected that the proposed test problems will germinate progress the field of the MTSOO research.
Tasks
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03470v1
PDF	http://arxiv.org/pdf/1706.03470v1.pdf
PWC	https://paperswithcode.com/paper/evolutionary-multitasking-for-single
Repo
Framework

Cross-media Similarity Metric Learning with Unified Deep Networks


Title	Cross-media Similarity Metric Learning with Unified Deep Networks
Authors	Jinwei Qi, Xin Huang, Yuxin Peng
Abstract	As a highlighting research topic in the multimedia area, cross-media retrieval aims to capture the complex correlations among multiple media types. Learning better shared representation and distance metric for multimedia data is important to boost the cross-media retrieval. Motivated by the strong ability of deep neural network in feature representation and comparison functions learning, we propose the Unified Network for Cross-media Similarity Metric (UNCSM) to associate cross-media shared representation learning with distance metric in a unified framework. First, we design a two-pathway deep network pretrained with contrastive loss, and employ double triplet similarity loss for fine-tuning to learn the shared representation for each media type by modeling the relative semantic similarity. Second, the metric network is designed for effectively calculating the cross-media similarity of the shared representation, by modeling the pairwise similar and dissimilar constraints. Compared to the existing methods which mostly ignore the dissimilar constraints and only use sample distance metric as Euclidean distance separately, our UNCSM approach unifies the representation learning and distance metric to preserve the relative similarity as well as embrace more complex similarity functions for further improving the cross-media retrieval accuracy. The experimental results show that our UNCSM approach outperforms 8 state-of-the-art methods on 4 widely-used cross-media datasets.
Tasks	Metric Learning, Representation Learning, Semantic Similarity, Semantic Textual Similarity
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04333v1
PDF	http://arxiv.org/pdf/1704.04333v1.pdf
PWC	https://paperswithcode.com/paper/cross-media-similarity-metric-learning-with
Repo
Framework

Prioritized Norms in Formal Argumentation


Title	Prioritized Norms in Formal Argumentation
Authors	Beishui Liao, Nir Oren, Leendert van der Torre, Serena Villata
Abstract	To resolve conflicts among norms, various nonmonotonic formalisms can be used to perform prioritized normative reasoning. Meanwhile, formal argumentation provides a way to represent nonmonotonic logics. In this paper, we propose a representation of prioritized normative reasoning by argumentation. Using hierarchical abstract normative systems, we define three kinds of prioritized normative reasoning approaches, called Greedy, Reduction, and Optimization. Then, after formulating an argumentation theory for a hierarchical abstract normative system, we show that for a totally ordered hierarchical abstract normative system, Greedy and Reduction can be represented in argumentation by applying the weakest link and the last link principles respectively, and Optimization can be represented by introducing additional defeats capturing the idea that for each argument that contains a norm not belonging to the maximal obeyable set then this argument should be rejected.
Tasks
Published	2017-09-23
URL	http://arxiv.org/abs/1709.08034v2
PDF	http://arxiv.org/pdf/1709.08034v2.pdf
PWC	https://paperswithcode.com/paper/prioritized-norms-in-formal-argumentation
Repo
Framework

Measuring Territorial Control in Civil Wars Using Hidden Markov Models: A Data Informatics-Based Approach


Title	Measuring Territorial Control in Civil Wars Using Hidden Markov Models: A Data Informatics-Based Approach
Authors	Therese Anders, Hong Xu, Cheng Cheng, T. K. Satish Kumar
Abstract	Territorial control is a key aspect shaping the dynamics of civil war. Despite its importance, we lack data on territorial control that are fine-grained enough to account for subnational spatio-temporal variation and that cover a large set of conflicts. To resolve this issue, we propose a theoretical model of the relationship between territorial control and tactical choice in civil war and outline how Hidden Markov Models (HMMs) are suitable to capture theoretical intuitions and estimate levels of territorial control. We discuss challenges of using HMMs in this application and mitigation strategies for future work.
Tasks
Published	2017-11-18
URL	http://arxiv.org/abs/1711.06786v2
PDF	http://arxiv.org/pdf/1711.06786v2.pdf
PWC	https://paperswithcode.com/paper/measuring-territorial-control-in-civil-wars
Repo
Framework

Run-and-Inspect Method for Nonconvex Optimization and Global Optimality Bounds for R-Local Minimizers


Title	Run-and-Inspect Method for Nonconvex Optimization and Global Optimality Bounds for R-Local Minimizers
Authors	Yifan Chen, Yuejiao Sun, Wotao Yin
Abstract	Many optimization algorithms converge to stationary points. When the underlying problem is nonconvex, they may get trapped at local minimizers and occasionally stagnate near saddle points. We propose the Run-and-Inspect Method, which adds an “inspect” phase to existing algorithms that helps escape from non-global stationary points. The inspection samples a set of points in a radius $R$ around the current point. When a sample point yields a sufficient decrease in the objective, we move there and resume an existing algorithm. If no sufficient decrease is found, the current point is called an approximate $R$-local minimizer. We show that an $R$-local minimizer is globally optimal, up to a specific error depending on $R$, if the objective function can be implicitly decomposed into a smooth convex function plus a restricted function that is possibly nonconvex, nonsmooth. For high-dimensional problems, we introduce blockwise inspections to overcome the curse of dimensionality while still maintaining optimality bounds up to a factor equal to the number of blocks. Our method performs well on a set of artificial and realistic nonconvex problems by coupling with gradient descent, coordinate descent, EM, and prox-linear algorithms.
Tasks
Published	2017-11-22
URL	http://arxiv.org/abs/1711.08172v2
PDF	http://arxiv.org/pdf/1711.08172v2.pdf
PWC	https://paperswithcode.com/paper/run-and-inspect-method-for-nonconvex
Repo
Framework

Compatible extensions and consistent closures: a fuzzy approach


Title	Compatible extensions and consistent closures: a fuzzy approach
Authors	Irina Georgescu
Abstract	In this paper $\ast$–compatible extensions of fuzzy relations are studied, generalizing some results obtained by Duggan in case of crisp relations. From this general result are obtained as particular cases fuzzy versions of some important extension theorems for crisp relations (Szpilrajn, Hansson, Suzumura). Two notions of consistent closure of a fuzzy relation are introduced.
Tasks
Published	2017-05-22
URL	http://arxiv.org/abs/1705.07961v1
PDF	http://arxiv.org/pdf/1705.07961v1.pdf
PWC	https://paperswithcode.com/paper/compatible-extensions-and-consistent-closures
Repo
Framework

Toward the automated analysis of complex diseases in genome-wide association studies using genetic programming


Title	Toward the automated analysis of complex diseases in genome-wide association studies using genetic programming
Authors	Andrew Sohn, Randal S. Olson, Jason H. Moore
Abstract	Machine learning has been gaining traction in recent years to meet the demand for tools that can efficiently analyze and make sense of the ever-growing databases of biomedical data in health care systems around the world. However, effectively using machine learning methods requires considerable domain expertise, which can be a barrier of entry for bioinformaticians new to computational data science methods. Therefore, off-the-shelf tools that make machine learning more accessible can prove invaluable for bioinformaticians. To this end, we have developed an open source pipeline optimization tool (TPOT-MDR) that uses genetic programming to automatically design machine learning pipelines for bioinformatics studies. In TPOT-MDR, we implement Multifactor Dimensionality Reduction (MDR) as a feature construction method for modeling higher-order feature interactions, and combine it with a new expert knowledge-guided feature selector for large biomedical data sets. We demonstrate TPOT-MDR’s capabilities using a combination of simulated and real world data sets from human genetics and find that TPOT-MDR significantly outperforms modern machine learning methods such as logistic regression and eXtreme Gradient Boosting (XGBoost). We further analyze the best pipeline discovered by TPOT-MDR for a real world problem and highlight TPOT-MDR’s ability to produce a high-accuracy solution that is also easily interpretable.
Tasks	Dimensionality Reduction
Published	2017-02-06
URL	http://arxiv.org/abs/1702.01780v1
PDF	http://arxiv.org/pdf/1702.01780v1.pdf
PWC	https://paperswithcode.com/paper/toward-the-automated-analysis-of-complex
Repo
Framework