July 28, 2019

3149 words 15 mins read

Paper Group ANR 460

Universal Reasoning, Rational Argumentation and Human-Machine Interaction. Equivalence between LINE and Matrix Factorization. Understanding and Comparing Deep Neural Networks for Age and Gender Classification. Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables. Co-clustering through Optimal Transp …

Universal Reasoning, Rational Argumentation and Human-Machine Interaction


Title	Universal Reasoning, Rational Argumentation and Human-Machine Interaction
Authors	Christoph Benzmüller
Abstract	Classical higher-order logic, when utilized as a meta-logic in which various other (classical and non-classical) logics can be shallowly embedded, is well suited for realising a universal logic reasoning approach. Universal logic reasoning in turn, as envisioned already by Leibniz, may support the rigorous formalisation and deep logical analysis of rational arguments within machines. A respective universal logic reasoning framework is described and a range of exemplary applications are discussed. In the future, universal logic reasoning in combination with appropriate, controlled forms of rational argumentation may serve as a communication layer between humans and intelligent machines.
Tasks
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09620v1
PDF	http://arxiv.org/pdf/1703.09620v1.pdf
PWC	https://paperswithcode.com/paper/universal-reasoning-rational-argumentation
Repo
Framework

Equivalence between LINE and Matrix Factorization


Title	Equivalence between LINE and Matrix Factorization
Authors	Qiao Wang, Zheng Wang, Xiaojun Ye
Abstract	LINE [1], as an efficient network embedding method, has shown its effectiveness in dealing with large-scale undirected, directed, and/or weighted networks. Particularly, it proposes to preserve both the local structure (represented by First-order Proximity) and global structure (represented by Second-order Proximity) of the network. In this study, we prove that LINE with these two proximities (LINE(1st) and LINE(2nd)) are actually factoring two different matrices separately. Specifically, LINE(1st) is factoring a matrix M (1), whose entries are the doubled Pointwise Mutual Information (PMI) of vertex pairs in undirected networks, shifted by a constant. LINE(2nd) is factoring a matrix M (2), whose entries are the PMI of vertex and context pairs in directed networks, shifted by a constant. We hope this finding would provide a basis for further extensions and generalizations of LINE.
Tasks	Network Embedding
Published	2017-07-19
URL	http://arxiv.org/abs/1707.05926v2
PDF	http://arxiv.org/pdf/1707.05926v2.pdf
PWC	https://paperswithcode.com/paper/equivalence-between-line-and-matrix
Repo
Framework

Understanding and Comparing Deep Neural Networks for Age and Gender Classification


Title	Understanding and Comparing Deep Neural Networks for Age and Gender Classification
Authors	Sebastian Lapuschkin, Alexander Binder, Klaus-Robert Müller, Wojciech Samek
Abstract	Recently, deep neural networks have demonstrated excellent performances in recognizing the age and gender on human face images. However, these models were applied in a black-box manner with no information provided about which facial features are actually used for prediction and how these features depend on image preprocessing, model initialization and architecture choice. We present a study investigating these different effects. In detail, our work compares four popular neural network architectures, studies the effect of pretraining, evaluates the robustness of the considered alignment preprocessings via cross-method test set swapping and intuitively visualizes the model’s prediction strategies in given preprocessing conditions using the recent Layer-wise Relevance Propagation (LRP) algorithm. Our evaluations on the challenging Adience benchmark show that suitable parameter initialization leads to a holistic perception of the input, compensating artefactual data representations. With a combination of simple preprocessing steps, we reach state of the art performance in gender recognition.
Tasks	Age And Gender Classification
Published	2017-08-25
URL	http://arxiv.org/abs/1708.07689v1
PDF	http://arxiv.org/pdf/1708.07689v1.pdf
PWC	https://paperswithcode.com/paper/understanding-and-comparing-deep-neural
Repo
Framework

Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables


Title	Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables
Authors	Masaaki Takada, Taiji Suzuki, Hironori Fujisawa
Abstract	Sparse regularization such as $\ell_1$ regularization is a quite powerful and widely used strategy for high dimensional learning problems. The effectiveness of sparse regularization has been supported practically and theoretically by several studies. However, one of the biggest issues in sparse regularization is that its performance is quite sensitive to correlations between features. Ordinary $\ell_1$ regularization can select variables correlated with each other, which results in deterioration of not only its generalization error but also interpretability. In this paper, we propose a new regularization method, “Independently Interpretable Lasso” (IILasso). Our proposed regularizer suppresses selecting correlated variables, and thus each active variable independently affects the objective variable in the model. Hence, we can interpret regression coefficients intuitively and also improve the performance by avoiding overfitting. We analyze theoretical property of IILasso and show that the proposed method is much advantageous for its sign recovery and achieves almost minimax optimal convergence rate. Synthetic and real data analyses also indicate the effectiveness of IILasso.
Tasks
Published	2017-11-06
URL	http://arxiv.org/abs/1711.01796v2
PDF	http://arxiv.org/pdf/1711.01796v2.pdf
PWC	https://paperswithcode.com/paper/independently-interpretable-lasso-a-new
Repo
Framework

Co-clustering through Optimal Transport


Title	Co-clustering through Optimal Transport
Authors	Charlotte Laclau, Ievgen Redko, Basarab Matei, Younès Bennani, Vincent Brault
Abstract	In this paper, we present a novel method for co-clustering, an unsupervised learning approach that aims at discovering homogeneous groups of data instances and features by grouping them simultaneously. The proposed method uses the entropy regularized optimal transport between empirical measures defined on data instances and features in order to obtain an estimated joint probability density function represented by the optimal coupling matrix. This matrix is further factorized to obtain the induced row and columns partitions using multiscale representations approach. To justify our method theoretically, we show how the solution of the regularized optimal transport can be seen from the variational inference perspective thus motivating its use for co-clustering. The algorithm derived for the proposed method and its kernelized version based on the notion of Gromov-Wasserstein distance are fast, accurate and can determine automatically the number of both row and column clusters. These features are vividly demonstrated through extensive experimental evaluations.
Tasks
Published	2017-05-17
URL	http://arxiv.org/abs/1705.06189v3
PDF	http://arxiv.org/pdf/1705.06189v3.pdf
PWC	https://paperswithcode.com/paper/co-clustering-through-optimal-transport
Repo
Framework

Optimizing Cost-Sensitive SVM for Imbalanced Data :Connecting Cluster to Classification


Title	Optimizing Cost-Sensitive SVM for Imbalanced Data :Connecting Cluster to Classification
Authors	Qiuyan Yan, Shixiong Xia, Fanrong Meng
Abstract	Class imbalance is one of the challenging problems for machine learning in many real-world applications, such as coal and gas burst accident monitoring: the burst premonition data is extreme smaller than the normal data, however, which is the highlight we truly focus on. Cost-sensitive adjustment approach is a typical algorithm-level method resisting the data set imbalance. For SVMs classifier, which is modified to incorporate varying penalty parameter(C) for each of considered groups of examples. However, the C value is determined empirically, or is calculated according to the evaluation metric, which need to be computed iteratively and time consuming. This paper presents a novel cost-sensitive SVM method whose penalty parameter C optimized on the basis of cluster probability density function(PDF) and the cluster PDF is estimated only according to similarity matrix and some predefined hyper-parameters. Experimental results on various standard benchmark data sets and real-world data with different ratios of imbalance show that the proposed method is effective in comparison with commonly used cost-sensitive techniques.
Tasks
Published	2017-02-06
URL	http://arxiv.org/abs/1702.01504v1
PDF	http://arxiv.org/pdf/1702.01504v1.pdf
PWC	https://paperswithcode.com/paper/optimizing-cost-sensitive-svm-for-imbalanced
Repo
Framework

Multivariate Confidence Intervals


Title	Multivariate Confidence Intervals
Authors	Jussi Korpela, Emilia Oikarinen, Kai Puolamäki, Antti Ukkonen
Abstract	Confidence intervals are a popular way to visualize and analyze data distributions. Unlike p-values, they can convey information both about statistical significance as well as effect size. However, very little work exists on applying confidence intervals to multivariate data. In this paper we define confidence intervals for multivariate data that extend the one-dimensional definition in a natural way. In our definition every variable is associated with its own confidence interval as usual, but a data vector can be outside of a few of these, and still be considered to be within the confidence area. We analyze the problem and show that the resulting confidence areas retain the good qualities of their one-dimensional counterparts: they are informative and easy to interpret. Furthermore, we show that the problem of finding multivariate confidence intervals is hard, but provide efficient approximate algorithms to solve the problem.
Tasks
Published	2017-01-20
URL	http://arxiv.org/abs/1701.05763v1
PDF	http://arxiv.org/pdf/1701.05763v1.pdf
PWC	https://paperswithcode.com/paper/multivariate-confidence-intervals
Repo
Framework

Subspace Approximation for Approximate Nearest Neighbor Search in NLP


Title	Subspace Approximation for Approximate Nearest Neighbor Search in NLP
Authors	Jing Wang
Abstract	Most natural language processing tasks can be formulated as the approximated nearest neighbor search problem, such as word analogy, document similarity, machine translation. Take the question-answering task as an example, given a question as the query, the goal is to search its nearest neighbor in the training dataset as the answer. However, existing methods for approximate nearest neighbor search problem may not perform well owing to the following practical challenges: 1) there are noise in the data; 2) the large scale dataset yields a huge retrieval space and high search time complexity. In order to solve these problems, we propose a novel approximate nearest neighbor search framework which i) projects the data to a subspace based spectral analysis which eliminates the influence of noise; ii) partitions the training dataset to different groups in order to reduce the search space. Specifically, the retrieval space is reduced from $O(n)$ to $O(\log n)$ (where $n$ is the number of data points in the training dataset). We prove that the retrieved nearest neighbor in the projected subspace is the same as the one in the original feature space. We demonstrate the outstanding performance of our framework on real-world natural language processing tasks.
Tasks	Machine Translation, Question Answering
Published	2017-08-25
URL	http://arxiv.org/abs/1708.07775v1
PDF	http://arxiv.org/pdf/1708.07775v1.pdf
PWC	https://paperswithcode.com/paper/subspace-approximation-for-approximate
Repo
Framework

On the Effective Use of Pretraining for Natural Language Inference


Title	On the Effective Use of Pretraining for Natural Language Inference
Authors	Ignacio Cases, Minh-Thang Luong, Christopher Potts
Abstract	Neural networks have excelled at many NLP tasks, but there remain open questions about the performance of pretrained distributed word representations and their interaction with weight initialization and other hyperparameters. We address these questions empirically using attention-based sequence-to-sequence models for natural language inference (NLI). Specifically, we compare three types of embeddings: random, pretrained (GloVe, word2vec), and retrofitted (pretrained plus WordNet information). We show that pretrained embeddings outperform both random and retrofitted ones in a large NLI corpus. Further experiments on more controlled data sets shed light on the contexts for which retrofitted embeddings can be useful. We also explore two principled approaches to initializing the rest of the model parameters, Gaussian and orthogonal, showing that the latter yields gains of up to 2.9% in the NLI task.
Tasks	Natural Language Inference
Published	2017-10-05
URL	http://arxiv.org/abs/1710.02076v1
PDF	http://arxiv.org/pdf/1710.02076v1.pdf
PWC	https://paperswithcode.com/paper/on-the-effective-use-of-pretraining-for
Repo
Framework

“Is there anything else I can help you with?": Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent


Title	“Is there anything else I can help you with?": Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent
Authors	Ting-Hao Kenneth Huang, Walter S. Lasecki, Amos Azaria, Jeffrey P. Bigham
Abstract	Intelligent conversational assistants, such as Apple’s Siri, Microsoft’s Cortana, and Amazon’s Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with them as they would with human dialog partners. This limits our ability to observe how users really want to interact with the underlying system. To address this problem, we developed a crowd-powered conversational assistant, Chorus, and deployed it to see how users and workers would interact together when mediated by the system. Chorus sophisticatedly converses with end users over time by recruiting workers on demand, which in turn decide what might be the best response for each user sentence. Up to the first month of our deployment, 59 users have held conversations with Chorus during 320 conversational sessions. In this paper, we present an account of Chorus’ deployment, with a focus on four challenges: (i) identifying when conversations are over, (ii) malicious users and workers, (iii) on-demand recruiting, and (iv) settings in which consensus is not enough. Our observations could assist the deployment of crowd-powered conversation systems and crowd-powered systems in general.
Tasks
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03044v1
PDF	http://arxiv.org/pdf/1708.03044v1.pdf
PWC	https://paperswithcode.com/paper/is-there-anything-else-i-can-help-you-with
Repo
Framework

Are Key-Foreign Key Joins Safe to Avoid when Learning High-Capacity Classifiers?


Title	Are Key-Foreign Key Joins Safe to Avoid when Learning High-Capacity Classifiers?
Authors	Vraj Shah, Arun Kumar, Xiaojin Zhu
Abstract	Machine learning (ML) over relational data is a booming area of the database industry and academia. While several projects aim to build scalable and fast ML systems, little work has addressed the pains of sourcing data and features for ML tasks. Real-world relational databases typically have many tables (often, dozens) and data scientists often struggle to even obtain and join all possible tables that provide features for ML. In this context, Kumar et al. showed recently that key-foreign key dependencies (KFKDs) between tables often lets us avoid such joins without significantly affecting prediction accuracy–an idea they called avoiding joins safely. While initially controversial, this idea has since been used by multiple companies to reduce the burden of data sourcing for ML. But their work applied only to linear classifiers. In this work, we verify if their results hold for three popular complex classifiers: decision trees, SVMs, and ANNs. We conduct an extensive experimental study using both real-world datasets and simulations to analyze the effects of avoiding KFK joins on such models. Our results show that these high-capacity classifiers are surprisingly and counter-intuitively more robust to avoiding KFK joins compared to linear classifiers, refuting an intuition from the prior work’s analysis. We explain this behavior intuitively and identify open questions at the intersection of data management and ML theoretical research. All of our code and datasets are available for download from http://cseweb.ucsd.edu/~arunkk/hamlet.
Tasks
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00485v3
PDF	http://arxiv.org/pdf/1704.00485v3.pdf
PWC	https://paperswithcode.com/paper/are-key-foreign-key-joins-safe-to-avoid-when
Repo
Framework

A Many-Objective Evolutionary Algorithm with Angle-Based Selection and Shift-Based Density Estimation


Title	A Many-Objective Evolutionary Algorithm with Angle-Based Selection and Shift-Based Density Estimation
Authors	Zhi-Zhong Liu, Yong Wang, Pei-Qiu Huang
Abstract	Evolutionary many-objective optimization has been gaining increasing attention from the evolutionary computation research community. Much effort has been devoted to addressing this issue by improving the scalability of multiobjective evolutionary algorithms, such as Pareto-based, decomposition-based, and indicator-based approaches. Different from current work, we propose a novel algorithm in this paper called AnD, which consists of an angle-based selection strategy and a shift-based density estimation strategy. These two strategies are employed in the environmental selection to delete the poor individuals one by one. Specifically, the former is devised to find a pair of individuals with the minimum vector angle, which means that these two individuals share the most similar search direction. The latter, which takes both the diversity and convergence into account, is adopted to compare these two individuals and to delete the worse one. AnD has a simple structure, few parameters, and no complicated operators. The performance of AnD is compared with that of seven state-of-the-art many-objective evolutionary algorithms on a variety of benchmark test problems with up to 15 objectives. The experimental results suggest that AnD can achieve highly competitive performance. In addition, we also verify that AnD can be readily extended to solve constrained many-objective optimization problems.
Tasks	Density Estimation
Published	2017-09-30
URL	http://arxiv.org/abs/1710.00175v1
PDF	http://arxiv.org/pdf/1710.00175v1.pdf
PWC	https://paperswithcode.com/paper/a-many-objective-evolutionary-algorithm-with-1
Repo
Framework

Embedding Visual Hierarchy with Deep Networks for Large-Scale Visual Recognition


Title	Embedding Visual Hierarchy with Deep Networks for Large-Scale Visual Recognition
Authors	Tianyi Zhao, Baopeng Zhang, Wei Zhang, Ning Zhou, Jun Yu, Jianping Fan
Abstract	In this paper, a level-wise mixture model (LMM) is developed by embedding visual hierarchy with deep networks to support large-scale visual recognition (i.e., recognizing thousands or even tens of thousands of object classes), and a Bayesian approach is used to adapt a pre-trained visual hierarchy automatically to the improvements of deep features (that are used for image and object class representation) when more representative deep networks are learned along the time. Our LMM model can provide an end-to-end approach for jointly learning: (a) the deep networks to extract more discriminative deep features for image and object class representation; (b) the tree classifier for recognizing large numbers of object classes hierarchically; and (c) the visual hierarchy adaptation for achieving more accurate indexing of large numbers of object classes hierarchically. By supporting joint learning of the tree classifier, the deep networks and the visual hierarchy adaptation, our LMM algorithm can provide an effective approach for controlling inter-level error propagation effectively, thus it can achieve better accuracy rates on large-scale visual recognition. Our experiments are carried on ImageNet1K and ImageNet10K image sets, and our LMM algorithm can achieve very competitive results on both the accuracy rates and the computation efficiency as compared with the baseline methods.
Tasks	Object Recognition
Published	2017-07-08
URL	http://arxiv.org/abs/1707.02406v1
PDF	http://arxiv.org/pdf/1707.02406v1.pdf
PWC	https://paperswithcode.com/paper/embedding-visual-hierarchy-with-deep-networks
Repo
Framework

Recognizing Gender from Human Facial Regions using Genetic Algorithm


Title	Recognizing Gender from Human Facial Regions using Genetic Algorithm
Authors	Avirup Bhattacharyya, Rajkumar Saini, Partha Pratim Roy, Debi Prosad Dogra, Samarjit Kar
Abstract	Recently, recognition of gender from facial images has gained a lot of importance. There exist a handful of research work that focus on feature extraction to obtain gender specific information from facial images. However, analyzing different facial regions and their fusion help in deciding the gender of a person from facial images. In this paper, we propose a new approach to identify gender from frontal facial images that is robust to background, illumination, intensity, and facial expression. In our framework, first the frontal face image is divided into a number of distinct regions based on facial landmark points that are obtained by the Chehra model proposed by Asthana et al. The model provides 49 facial landmark points covering different regions of the face, e.g. forehead, left eye, right eye, lips. Next, a face image is segmented into facial regions using landmark points and features are extracted from each region. The Compass LBP feature, a variant of LBP feature, has been used in our framework to obtain discriminative gender-specific information. Following this, a Support Vector Machine based classifier has been used to compute the probability scores from each facial region. Finally, the classification scores obtained from individual regions are combined with a genetic algorithm based learning to improve the overall classification accuracy. The experiments have been performed on popular face image datasets such as Adience, cFERET (color FERET), LFW and two sketch datasets, namely CUFS and CUFSF. Through experiments, we have observed that, the proposed method outperforms existing approaches.
Tasks
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01661v1
PDF	http://arxiv.org/pdf/1712.01661v1.pdf
PWC	https://paperswithcode.com/paper/recognizing-gender-from-human-facial-regions
Repo
Framework

Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings


Title	Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings
Authors	Hanan Aldarmaki, Mahesh Mohan, Mona Diab
Abstract	Most existing methods for automatic bilingual dictionary induction rely on prior alignments between the source and target languages, such as parallel corpora or seed dictionaries. For many language pairs, such supervised alignments are not readily available. We propose an unsupervised approach for learning a bilingual dictionary for a pair of languages given their independently-learned monolingual word embeddings. The proposed method exploits local and global structures in monolingual vector spaces to align them such that similar words are mapped to each other. We show empirically that the performance of bilingual correspondents learned using our proposed unsupervised method is comparable to that of using supervised bilingual correspondents from a seed dictionary.
Tasks	Word Embeddings
Published	2017-12-19
URL	http://arxiv.org/abs/1712.06961v2
PDF	http://arxiv.org/pdf/1712.06961v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-word-mapping-using-structural
Repo
Framework