Paper Group ANR 25
XCSP3: An Integrated Format for Benchmarking Combinatorial Constrained Problems. Semi-supervised and Unsupervised Methods for Categorizing Posts in Web Discussion Forums. Bootstrapping Face Detection with Hard Negative Examples. End-to-End Data Visualization by Metric Learning and Coordinate Transformation. Tree Space Prototypes: Another Look at Ma …
XCSP3: An Integrated Format for Benchmarking Combinatorial Constrained Problems
| Title | XCSP3: An Integrated Format for Benchmarking Combinatorial Constrained Problems |
| Authors | Frederic Boussemart, Christophe Lecoutre, Gilles Audemard, Cédric Piette |
| Abstract | We propose a major revision of the format XCSP 2.1, called XCSP3, to build integrated representations of combinatorial constrained problems. This new format is able to deal with mono/multi optimization, many types of variables, cost functions, reification, views, annotations, variable quantification, distributed, probabilistic and qualitative reasoning. The new format is made compact, highly readable, and rather easy to parse. Interestingly, it captures the structure of the problem models, through the possibilities of declaring arrays of variables, and identifying syntactic and semantic groups of constraints. The number of constraints is kept under control by introducing a limited set of basic constraint forms, and producing almost automatically some of their variations through lifting, restriction, sliding, logical combination and relaxation mechanisms. As a result, XCSP3 encompasses practically all constraints that can be found in major constraint solvers developed by the CP community. A website, which is developed conjointly with the format, contains many models and series of instances. The user can make sophisticated queries for selecting instances from very precise criteria. The objective of XCSP3 is to ease the effort required to test and compare different algorithms by providing a common test-bed of combinatorial constrained instances. |
| Tasks | |
| Published | 2016-11-10 |
| URL | http://arxiv.org/abs/1611.03398v2 |
| http://arxiv.org/pdf/1611.03398v2.pdf | |
| PWC | https://paperswithcode.com/paper/xcsp3-an-integrated-format-for-benchmarking |
| Repo | |
| Framework | |
Semi-supervised and Unsupervised Methods for Categorizing Posts in Web Discussion Forums
| Title | Semi-supervised and Unsupervised Methods for Categorizing Posts in Web Discussion Forums |
| Authors | Krish Perumal |
| Abstract | Web discussion forums are used by millions of people worldwide to share information belonging to a variety of domains such as automotive vehicles, pets, sports, etc. They typically contain posts that fall into different categories such as problem, solution, feedback, spam, etc. Automatic identification of these categories can aid information retrieval that is tailored for specific user requirements. Previously, a number of supervised methods have attempted to solve this problem; however, these depend on the availability of abundant training data. A few existing unsupervised and semi-supervised approaches are either focused on identifying a single category or do not report category-specific performance. In contrast, this work proposes unsupervised and semi-supervised methods that require no or minimal training data to achieve this objective without compromising on performance. A fine-grained analysis is also carried out to discuss their limitations. The proposed methods are based on sequence models (specifically, Hidden Markov Models) that can model language for each category using word and part-of-speech probability distributions, and manually specified features. Empirical evaluations across domains demonstrate that the proposed methods are better suited for this task than existing ones. |
| Tasks | Information Retrieval |
| Published | 2016-04-01 |
| URL | http://arxiv.org/abs/1604.00119v3 |
| http://arxiv.org/pdf/1604.00119v3.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-and-unsupervised-methods-for |
| Repo | |
| Framework | |
Bootstrapping Face Detection with Hard Negative Examples
| Title | Bootstrapping Face Detection with Hard Negative Examples |
| Authors | Shaohua Wan, Zhijun Chen, Tao Zhang, Bo Zhang, Kong-kat Wong |
| Abstract | Recently significant performance improvement in face detection was made possible by deeply trained convolutional networks. In this report, a novel approach for training state-of-the-art face detector is described. The key is to exploit the idea of hard negative mining and iteratively update the Faster R-CNN based face detector with the hard negatives harvested from a large set of background examples. We demonstrate that our face detector outperforms state-of-the-art detectors on the FDDB dataset, which is the de facto standard for evaluating face detection algorithms. |
| Tasks | Face Detection |
| Published | 2016-08-07 |
| URL | http://arxiv.org/abs/1608.02236v1 |
| http://arxiv.org/pdf/1608.02236v1.pdf | |
| PWC | https://paperswithcode.com/paper/bootstrapping-face-detection-with-hard |
| Repo | |
| Framework | |
End-to-End Data Visualization by Metric Learning and Coordinate Transformation
| Title | End-to-End Data Visualization by Metric Learning and Coordinate Transformation |
| Authors | Lilei Zheng, Ying Zhang, Stefan Duffner, Khalid Idrissi, Christophe Garcia, Atilla Baskurt |
| Abstract | This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset. We propose the Triangular Similarity and prove its equivalence to the Cosine Similarity in measuring a data pair. Based on this novel similarity, a geometrically motivated loss function - the triangular loss - is then developed for optimizing a metric learning system comprising two identical CNNs. It is shown that this deep nonlinear system can be efficiently trained by a hybrid algorithm based on the conventional backpropagation algorithm. More interestingly, benefiting from classical manifold learning theories, the proposed system offers two different views to visualize the outputs, the second of which provides better classification results than the state-of-the-art methods in the visualizable spaces. |
| Tasks | Metric Learning |
| Published | 2016-12-27 |
| URL | http://arxiv.org/abs/1612.08499v1 |
| http://arxiv.org/pdf/1612.08499v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-data-visualization-by-metric |
| Repo | |
| Framework | |
Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable
| Title | Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable |
| Authors | Sarah Tan, Matvey Soloviev, Giles Hooker, Martin T. Wells |
| Abstract | Ensembles of decision trees are known to perform well on many problems, but are not interpretable. In contrast to existing explanations of tree ensembles that explain relationships between features and predictions, we propose an alternative approach to interpreting tree ensembles by surfacing representative points for each class, in which we explain a prediction by presenting points with similar predictions – prototypes. We introduce a new distance for Gradient Boosted Tree models, and propose new prototype selection methods with theoretical guarantees, with the flexibility to choose a different number of prototypes in each class. We demonstrate our methods on random forests and gradient boosted trees, showing that our found prototypes perform as well as or even better than the original tree ensemble when used as a nearest-prototype classifier. We also present a use case of debugging dataset errors using our proposed methods. |
| Tasks | |
| Published | 2016-11-22 |
| URL | https://arxiv.org/abs/1611.07115v2 |
| https://arxiv.org/pdf/1611.07115v2.pdf | |
| PWC | https://paperswithcode.com/paper/tree-space-prototypes-another-look-at-making |
| Repo | |
| Framework | |
Nonnegative Matrix Factorization for identification of unknown number of sources emitting delayed signals
| Title | Nonnegative Matrix Factorization for identification of unknown number of sources emitting delayed signals |
| Authors | Filip L. Iliev, Valentin G. Stanev, Velimir V. Vesselinov, Boian S. Alexandrov |
| Abstract | Factor analysis is broadly used as a powerful unsupervised machine learning tool for reconstruction of hidden features in recorded mixtures of signals. In the case of a linear approximation, the mixtures can be decomposed by a variety of model-free Blind Source Separation (BSS) algorithms. Most of the available BSS algorithms consider an instantaneous mixing of signals, while the case when the mixtures are linear combinations of signals with delays is less explored. Especially difficult is the case when the number of sources of the signals with delays is unknown and has to be determined from the data as well. To address this problem, in this paper, we present a new method based on Nonnegative Matrix Factorization (NMF) that is capable of identifying: (a) the unknown number of the sources, (b) the delays and speed of propagation of the signals, and (c) the locations of the sources. Our method can be used to decompose records of mixtures of signals with delays emitted by an unknown number of sources in a nondispersive medium, based only on recorded data. This is the case, for example, when electromagnetic signals from multiple antennas are received asynchronously; or mixtures of acoustic or seismic signals recorded by sensors located at different positions; or when a shift in frequency is induced by the Doppler effect. By applying our method to synthetic datasets, we demonstrate its ability to identify the unknown number of sources as well as the waveforms, the delays, and the strengths of the signals. Using Bayesian analysis, we also evaluate estimation uncertainties and identify the region of likelihood where the positions of the sources can be found. |
| Tasks | |
| Published | 2016-12-12 |
| URL | http://arxiv.org/abs/1612.03950v2 |
| http://arxiv.org/pdf/1612.03950v2.pdf | |
| PWC | https://paperswithcode.com/paper/nonnegative-matrix-factorization-for |
| Repo | |
| Framework | |
Predicting health inspection results from online restaurant reviews
| Title | Predicting health inspection results from online restaurant reviews |
| Authors | Samantha Wong, Hamidreza Chinaei, Frank Rudzicz |
| Abstract | Informatics around public health are increasingly shifting from the professional to the public spheres. In this work, we apply linguistic analytics to restaurant reviews, from Yelp, in order to automatically predict official health inspection reports. We consider two types of feature sets, i.e., keyword detection and topic model features, and use these in several classification methods. Our empirical analysis shows that these extracted features can predict public health inspection reports with over 90% accuracy using simple support vector machines. |
| Tasks | |
| Published | 2016-03-17 |
| URL | http://arxiv.org/abs/1603.05673v1 |
| http://arxiv.org/pdf/1603.05673v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-health-inspection-results-from |
| Repo | |
| Framework | |
General Vector Machine
| Title | General Vector Machine |
| Authors | Hong Zhao |
| Abstract | The support vector machine (SVM) is an important class of learning machines for function approach, pattern recognition, and time-serious prediction, etc. It maps samples into the feature space by so-called support vectors of selected samples, and then feature vectors are separated by maximum margin hyperplane. The present paper presents the general vector machine (GVM) to replace the SVM. The support vectors are replaced by general project vectors selected from the usual vector space, and a Monte Carlo (MC) algorithm is developed to find the general vectors. The general project vectors improves the feature-extraction ability, and the MC algorithm can control the width of the separation margin of the hyperplane. By controlling the separation margin, we show that the maximum margin hyperplane can usually induce the overlearning, and the best learning machine is achieved with a proper separation margin. Applications in function approach, pattern recognition, and classification indicate that the developed method is very successful, particularly for small-set training problems. Additionally, our algorithm may induce some particular applications, such as for the transductive inference. |
| Tasks | |
| Published | 2016-02-12 |
| URL | http://arxiv.org/abs/1602.03950v1 |
| http://arxiv.org/pdf/1602.03950v1.pdf | |
| PWC | https://paperswithcode.com/paper/general-vector-machine |
| Repo | |
| Framework | |
Learning to Push by Grasping: Using multiple tasks for effective learning
| Title | Learning to Push by Grasping: Using multiple tasks for effective learning |
| Authors | Lerrel Pinto, Abhinav Gupta |
| Abstract | Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due to their huge data requirements for learning a task. The argument of the difficulty in scalability to multiple tasks is well founded, since training these tasks often require hundreds or thousands of examples. But do end-to-end approaches need to learn a unique model for every task? Intuitively, it seems that sharing across tasks should help since all tasks require some common understanding of the environment. In this paper, we attempt to take the next step in data-driven end-to-end learning frameworks: move from the realm of task-specific models to joint learning of multiple robot tasks. In an astonishing result we show that models with multi-task learning tend to perform better than task-specific models trained with same amounts of data. For example, a deep-network learned with 2.5K grasp and 2.5K push examples performs better on grasping than a network trained on 5K grasp examples. |
| Tasks | Multi-Task Learning |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.09025v1 |
| http://arxiv.org/pdf/1609.09025v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-push-by-grasping-using-multiple |
| Repo | |
| Framework | |
Multiple-View Spectral Clustering for Group-wise Functional Community Detection
| Title | Multiple-View Spectral Clustering for Group-wise Functional Community Detection |
| Authors | Nathan D. Cahill, Harmeet Singh, Chao Zhang, Daryl A. Corcoran, Alison M. Prengaman, Paul S. Wenger, John F. Hamilton, Peter Bajorski, Andrew M. Michael |
| Abstract | Functional connectivity analysis yields powerful insights into our understanding of the human brain. Group-wise functional community detection aims to partition the brain into clusters, or communities, in which functional activity is inter-regionally correlated in a common manner across a group of subjects. In this article, we show how to use multiple-view spectral clustering to perform group-wise functional community detection. In a series of experiments on 291 subjects from the Human Connectome Project, we compare three versions of multiple-view spectral clustering: MVSC (uniform weights), MVSCW (weights based on subject-specific embedding quality), and AASC (weights optimized along with the embedding) with the competing technique of Joint Diagonalization of Laplacians (JDL). Results show that multiple-view spectral clustering not only yields group-wise functional communities that are more consistent than JDL when using randomly selected subsets of individual brains, but it is several orders of magnitude faster than JDL. |
| Tasks | Community Detection |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1611.06981v1 |
| http://arxiv.org/pdf/1611.06981v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-view-spectral-clustering-for-group |
| Repo | |
| Framework | |
Pairwise Quantization
| Title | Pairwise Quantization |
| Authors | Artem Babenko, Relja Arandjelović, Victor Lempitsky |
| Abstract | We consider the task of lossy compression of high-dimensional vectors through quantization. We propose the approach that learns quantization parameters by minimizing the distortion of scalar products and squared distances between pairs of points. This is in contrast to previous works that obtain these parameters through the minimization of the reconstruction error of individual points. The proposed approach proceeds by finding a linear transformation of the data that effectively reduces the minimization of the pairwise distortions to the minimization of individual reconstruction errors. After such transformation, any of the previously-proposed quantization approaches can be used. Despite the simplicity of this transformation, the experiments demonstrate that it achieves considerable reduction of the pairwise distortions compared to applying quantization directly to the untransformed data. |
| Tasks | Quantization |
| Published | 2016-06-05 |
| URL | http://arxiv.org/abs/1606.01550v1 |
| http://arxiv.org/pdf/1606.01550v1.pdf | |
| PWC | https://paperswithcode.com/paper/pairwise-quantization |
| Repo | |
| Framework | |
Attention Correctness in Neural Image Captioning
| Title | Attention Correctness in Neural Image Captioning |
| Authors | Chenxi Liu, Junhua Mao, Fei Sha, Alan Yuille |
| Abstract | Attention mechanisms have recently been introduced in deep learning for various tasks in natural language processing and computer vision. But despite their popularity, the “correctness” of the implicitly-learned attention maps has only been assessed qualitatively by visualization of several examples. In this paper we focus on evaluating and improving the correctness of attention in neural image captioning models. Specifically, we propose a quantitative evaluation metric for the consistency between the generated attention maps and human annotations, using recently released datasets with alignment between regions in images and entities in captions. We then propose novel models with different levels of explicit supervision for learning attention maps during training. The supervision can be strong when alignment between regions and caption entities are available, or weak when only object segments and categories are provided. We show on the popular Flickr30k and COCO datasets that introducing supervision of attention maps during training solidly improves both attention correctness and caption quality, showing the promise of making machine perception more human-like. |
| Tasks | Image Captioning |
| Published | 2016-05-31 |
| URL | http://arxiv.org/abs/1605.09553v2 |
| http://arxiv.org/pdf/1605.09553v2.pdf | |
| PWC | https://paperswithcode.com/paper/attention-correctness-in-neural-image |
| Repo | |
| Framework | |
Representing Verbs with Rich Contexts: an Evaluation on Verb Similarity
| Title | Representing Verbs with Rich Contexts: an Evaluation on Verb Similarity |
| Authors | Emmanuele Chersoni, Enrico Santus, Alessandro Lenci, Philippe Blache, Chu-Ren Huang |
| Abstract | Several studies on sentence processing suggest that the mental lexicon keeps track of the mutual expectations between words. Current DSMs, however, represent context words as separate features, thereby loosing important information for word expectations, such as word interrelations. In this paper, we present a DSM that addresses this issue by defining verb contexts as joint syntactic dependencies. We test our representation in a verb similarity task on two datasets, showing that joint contexts achieve performances comparable to single dependencies or even better. Moreover, they are able to overcome the data sparsity problem of joint feature spaces, in spite of the limited size of our training corpus. |
| Tasks | |
| Published | 2016-07-07 |
| URL | http://arxiv.org/abs/1607.02061v2 |
| http://arxiv.org/pdf/1607.02061v2.pdf | |
| PWC | https://paperswithcode.com/paper/representing-verbs-with-rich-contexts-an |
| Repo | |
| Framework | |
Partially blind domain adaptation for age prediction from DNA methylation data
| Title | Partially blind domain adaptation for age prediction from DNA methylation data |
| Authors | Lisa Handl, Adrin Jalali, Michael Scherer, Nico Pfeifer |
| Abstract | Over the last years, huge resources of biological and medical data have become available for research. This data offers great chances for machine learning applications in health care, e.g. for precision medicine, but is also challenging to analyze. Typical challenges include a large number of possibly correlated features and heterogeneity in the data. One flourishing field of biological research in which this is relevant is epigenetics. Here, especially large amounts of DNA methylation data have emerged. This epigenetic mark has been used to predict a donor’s ‘epigenetic age’ and increased epigenetic aging has been linked to lifestyle and disease history. In this paper we propose an adaptive model which performs feature selection for each test sample individually based on the distribution of the input data. The method can be seen as partially blind domain adaptation. We apply the model to the problem of age prediction based on DNA methylation data from a variety of tissues, and compare it to a standard model, which does not take heterogeneity into account. The standard approach has particularly bad performance on one tissue type on which we show substantial improvement with our new adaptive approach even though no samples of that tissue were part of the training data. |
| Tasks | Domain Adaptation, Feature Selection |
| Published | 2016-12-20 |
| URL | http://arxiv.org/abs/1612.06650v1 |
| http://arxiv.org/pdf/1612.06650v1.pdf | |
| PWC | https://paperswithcode.com/paper/partially-blind-domain-adaptation-for-age |
| Repo | |
| Framework | |
Towards Unifying Hamiltonian Monte Carlo and Slice Sampling
| Title | Towards Unifying Hamiltonian Monte Carlo and Slice Sampling |
| Authors | Yizhe Zhang, Xiangyu Wang, Changyou Chen, Ricardo Henao, Kai Fan, Lawrence Carin |
| Abstract | We unify slice sampling and Hamiltonian Monte Carlo (HMC) sampling, demonstrating their connection via the Hamiltonian-Jacobi equation from Hamiltonian mechanics. This insight enables extension of HMC and slice sampling to a broader family of samplers, called Monomial Gamma Samplers (MGS). We provide a theoretical analysis of the mixing performance of such samplers, proving that in the limit of a single parameter, the MGS draws decorrelated samples from the desired target distribution. We further show that as this parameter tends toward this limit, performance gains are achieved at a cost of increasing numerical difficulty and some practical convergence issues. Our theoretical results are validated with synthetic data and real-world applications. |
| Tasks | |
| Published | 2016-02-25 |
| URL | http://arxiv.org/abs/1602.07800v5 |
| http://arxiv.org/pdf/1602.07800v5.pdf | |
| PWC | https://paperswithcode.com/paper/towards-unifying-hamiltonian-monte-carlo-and |
| Repo | |
| Framework | |
