January 31, 2020

3168 words 15 mins read

Paper Group ANR 186

Probabilistic Kernel Support Vector Machines. Learning Generative Models across Incomparable Spaces. Geometric Interpretation of side-sharing and point-sharing solutions in the P3P Problem. Text Analysis in Adversarial Settings: Does Deception Leave a Stylistic Trace?. Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?. Generat …

Probabilistic Kernel Support Vector Machines


Title	Probabilistic Kernel Support Vector Machines
Authors	Yongxin Chen, Tryphon T. Georgiou, Allen R. Tannenbaum
Abstract	We propose a probabilistic enhancement of standard kernel Support Vector Machines for binary classification, in order to address the case when, along with given data sets, a description of uncertainty (e.g., error bounds) may be available on each datum. In the present paper, we specifically consider Gaussian distributions to model uncertainty. Thereby, our data consist of pairs $(x_i,\Sigma_i)$, $i\in{1,\ldots,N}$, along with an indicator $y_i\in{-1,1}$ to declare membership in one of two categories for each pair. These pairs may be viewed to represent the mean and covariance, respectively, of random vectors $\xi_i$ taking values in a suitable linear space (typically $\mathbb R^n$). Thus, our setting may also be viewed as a modification of Support Vector Machines to classify distributions, albeit, at present, only Gaussian ones. We outline the formalism that allows computing suitable classifiers via a natural modification of the standard “kernel trick.” The main contribution of this work is to point out a suitable kernel function for applying Support Vector techniques to the setting of uncertain data for which a detailed uncertainty description is also available (herein, “Gaussian points”).
Tasks
Published	2019-04-14
URL	https://arxiv.org/abs/1904.06762v2
PDF	https://arxiv.org/pdf/1904.06762v2.pdf
PWC	https://paperswithcode.com/paper/probabilistic-kernel-support-vector-machines
Repo
Framework

Learning Generative Models across Incomparable Spaces


Title	Learning Generative Models across Incomparable Spaces
Authors	Charlotte Bunne, David Alvarez-Melis, Andreas Krause, Stefanie Jegelka
Abstract	Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only learn some aspects (e.g., cluster or manifold structure), while modifying others (e.g., style, orientation or dimension). In this work, we propose an approach to learn generative models across such incomparable spaces, and demonstrate how to steer the learned distribution towards target properties. A key component of our model is the Gromov-Wasserstein distance, a notion of discrepancy that compares distributions relationally rather than absolutely. While this framework subsumes current generative models in identically reproducing distributions, its inherent flexibility allows application to tasks in manifold learning, relational learning and cross-domain learning.
Tasks	Relational Reasoning
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05461v2
PDF	https://arxiv.org/pdf/1905.05461v2.pdf
PWC	https://paperswithcode.com/paper/learning-generative-models-across
Repo
Framework


Title	Geometric Interpretation of side-sharing and point-sharing solutions in the P3P Problem
Authors	Bo wang, Hao Hu, Caixia Zhang
Abstract	It is well known that the P3P problem could have 1, 2, 3 and at most 4 positive solutions under different configurations among its 3 control points and the position of the optical center. Since in any real applications, the knowledge on the exact number of possible solutions is a prerequisite for selecting the right one among all the possible solutions, the study on the phenomenon of multiple solutions in the P3P problem has been an active topic . In this work, we provide some new geometric interpretations on the multi-solution phenomenon in the P3P problem, our main results include: (1): The necessary and sufficient condition for the P3P problem to have a pair of side-sharing solutions is the two optical centers of the solutions both lie on one of the 3 vertical planes to the base plane of control points; (2): The necessary and sufficient condition for the P3P problem to have a pair of point-sharing solutions is the two optical centers of the solutions both lie on one of the 3 so-called skewed danger cylinders;(3): If the P3P problem has other solutions in addition to a pair of side-sharing ( point-sharing) solutions, these remaining solutions must be a point-sharing ( side-sharing ) pair. In a sense, the side-sharing pair and the point-sharing pair are companion pairs. In sum, our results provide some new insights into the nature of the multi-solution phenomenon in the P3P problem, in addition to their academic value, they could also be used as some theoretical guidance for practitioners in real applications to avoid occurrence of multiple solutions by properly arranging the control points.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1902.00105v1
PDF	http://arxiv.org/pdf/1902.00105v1.pdf
PWC	https://paperswithcode.com/paper/geometric-interpretation-of-side-sharing-and
Repo
Framework

Text Analysis in Adversarial Settings: Does Deception Leave a Stylistic Trace?


Title	Text Analysis in Adversarial Settings: Does Deception Leave a Stylistic Trace?
Authors	Tommi Gröndahl, N. Asokan
Abstract	Textual deception constitutes a major problem for online security. Many studies have argued that deceptiveness leaves traces in writing style, which could be detected using text classification techniques. By conducting an extensive literature review of existing empirical work, we demonstrate that while certain linguistic features have been indicative of deception in certain corpora, they fail to generalize across divergent semantic domains. We suggest that deceptiveness as such leaves no content-invariant stylistic trace, and textual similarity measures provide superior means of classifying texts as potentially deceptive. Additionally, we discuss forms of deception beyond semantic content, focusing on hiding author identity by writing style obfuscation. Surveying the literature on both author identification and obfuscation techniques, we conclude that current style transformation methods fail to achieve reliable obfuscation while simultaneously ensuring semantic faithfulness to the original text. We propose that future work in style transformation should pay particular attention to disallowing semantically drastic changes.
Tasks	Text Classification
Published	2019-02-24
URL	http://arxiv.org/abs/1902.08939v2
PDF	http://arxiv.org/pdf/1902.08939v2.pdf
PWC	https://paperswithcode.com/paper/text-analysis-in-adversarial-settings-does
Repo
Framework

Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?


Title	Recovering from Biased Data: Can Fairness Constraints Improve Accuracy?
Authors	Avrim Blum, Kevin Stangl
Abstract	Multiple fairness constraints have been proposed in the literature, motivated by a range of concerns about how demographic groups might be treated unfairly by machine learning classifiers. In this work we consider a different motivation; learning from biased training data. We posit several ways in which training data may be biased, including having a more noisy or negatively biased labeling process on members of a disadvantaged group, or a decreased prevalence of positive or negative examples from the disadvantaged group, or both. Given such biased training data, Empirical Risk Minimization (ERM) may produce a classifier that not only is biased but also has suboptimal accuracy on the true data distribution. We examine the ability of fairness-constrained ERM to correct this problem. In particular, we find that the Equal Opportunity fairness constraint (Hardt, Price, and Srebro 2016) combined with ERM will provably recover the Bayes Optimal Classifier under a range of bias models. We also consider other recovery methods including reweighting the training data, Equalized Odds, and Demographic Parity. These theoretical results provide additional motivation for considering fairness interventions even if an actor cares primarily about accuracy.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.01094v1
PDF	https://arxiv.org/pdf/1912.01094v1.pdf
PWC	https://paperswithcode.com/paper/recovering-from-biased-data-can-fairness
Repo
Framework

Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation


Title	Generative Visual Dialogue System via Adaptive Reasoning and Weighted Likelihood Estimation
Authors	Heming Zhang, Shalini Ghosh, Larry Heck, Stephen Walsh, Junting Zhang, Jie Zhang, C. -C. Jay Kuo
Abstract	The key challenge of generative Visual Dialogue (VD) systems is to respond to human queries with informative answers in natural and contiguous conversation flow. Traditional Maximum Likelihood Estimation (MLE)-based methods only learn from positive responses but ignore the negative responses, and consequently tend to yield safe or generic responses. To address this issue, we propose a novel training scheme in conjunction with weighted likelihood estimation (WLE) method. Furthermore, an adaptive multi-modal reasoning module is designed, to accommodate various dialogue scenarios automatically and select relevant information accordingly. The experimental results on the VisDial benchmark demonstrate the superiority of our proposed algorithm over other state-of-the-art approaches, with an improvement of 5.81% on recall@10.
Tasks	Visual Dialog
Published	2019-02-26
URL	https://arxiv.org/abs/1902.09818v2
PDF	https://arxiv.org/pdf/1902.09818v2.pdf
PWC	https://paperswithcode.com/paper/generative-visual-dialogue-system-via
Repo
Framework

Distributional Semantics and Linguistic Theory


Title	Distributional Semantics and Linguistic Theory
Authors	Gemma Boleda
Abstract	Distributional semantics provides multi-dimensional, graded, empirically induced word representations that successfully capture many aspects of meaning in natural languages, as shown in a large body of work in computational linguistics; yet, its impact in theoretical linguistics has so far been limited. This review provides a critical discussion of the literature on distributional semantics, with an emphasis on methods and results that are of relevance for theoretical linguistics, in three areas: semantic change, polysemy and composition, and the grammar-semantics interface (specifically, the interface of semantics with syntax and with derivational morphology). The review aims at fostering greater cross-fertilization of theoretical and computational approaches to language, as a means to advance our collective knowledge of how it works.
Tasks
Published	2019-05-06
URL	https://arxiv.org/abs/1905.01896v4
PDF	https://arxiv.org/pdf/1905.01896v4.pdf
PWC	https://paperswithcode.com/paper/distributional-semantics-and-linguistic
Repo
Framework

Hybridized Threshold Clustering for Massive Data


Title	Hybridized Threshold Clustering for Massive Data
Authors	Jianmei Luo, ChandraVyas Annakula, Aruna Sai Kannamareddy, Jasjeet S. Sekhon, William Henry Hsu, Michael Higgins
Abstract	As the size $n$ of datasets become massive, many commonly-used clustering algorithms (for example, $k$-means or hierarchical agglomerative clustering (HAC) require prohibitive computational cost and memory. In this paper, we propose a solution to these clustering problems by extending threshold clustering (TC) to problems of instance selection. TC is a recently developed clustering algorithm designed to partition data into many small clusters in linearithmic time (on average). Our proposed clustering method is as follows. First, TC is performed and clusters are reduced into single “prototype” points. Then, TC is applied repeatedly on these prototype points until sufficient data reduction has been obtained. Finally, a more sophisticated clustering algorithm is applied to the reduced prototype points, thereby obtaining a clustering on all $n$ data points. This entire procedure for clustering is called iterative hybridized threshold clustering (IHTC). Through simulation results and by applying our methodology on several real datasets, we show that IHTC combined with $k$-means or HAC substantially reduces the run time and memory usage of the original clustering algorithms while still preserving their performance. Additionally, IHTC helps prevent singular data points from being overfit by clustering algorithms.
Tasks
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02907v1
PDF	https://arxiv.org/pdf/1907.02907v1.pdf
PWC	https://paperswithcode.com/paper/hybridized-threshold-clustering-for-massive
Repo
Framework

Ensemble Prediction of Time to Event Outcomes with Competing Risks: A Case Study of Surgical Complications in Crohn’s Disease


Title	Ensemble Prediction of Time to Event Outcomes with Competing Risks: A Case Study of Surgical Complications in Crohn’s Disease
Authors	Michael C Sachs, Andrea Discacciati, Åsa Everhov, Ola Olén, Erin E Gabriel
Abstract	We develop a novel algorithm to predict the occurrence of major abdominal surgery within 5 years following Crohn’s disease diagnosis using a panel of 29 baseline covariates from the Swedish population registers. We model pseudo-observations based on the Aalen-Johansen estimator of the cause-specific cumulative incidence with an ensemble of modern machine learning approaches. Pseudo-observation pre-processing easily extends all existing or new machine learning procedures to right-censored event history data. We propose pseudo-observation based estimators for the area under the time varying ROC curve, for optimizing the ensemble, and the predictiveness curve, for evaluating and summarizing predictive performance.
Tasks
Published	2019-02-07
URL	http://arxiv.org/abs/1902.02533v1
PDF	http://arxiv.org/pdf/1902.02533v1.pdf
PWC	https://paperswithcode.com/paper/ensemble-prediction-of-time-to-event-outcomes
Repo
Framework

Self-supervised Learning of Detailed 3D Face Reconstruction


Title	Self-supervised Learning of Detailed 3D Face Reconstruction
Authors	Yajing Chen, Fanzi Wu, Zeyu Wang, Yibing Song, Yonggen Ling, Linchao Bao
Abstract	In this paper, we present an end-to-end learning framework for detailed 3D face reconstruction from a single image. Our approach uses a 3DMM-based coarse model and a displacement map in UV-space to represent a 3D face. Unlike previous work addressing the problem, our learning framework does not require supervision of surrogate ground-truth 3D models computed with traditional approaches. Instead, we utilize the input image itself as supervision during learning. In the first stage, we combine a photometric loss and a facial perceptual loss between the input face and the rendered face, to regress a 3DMM-based coarse model. In the second stage, both the input image and the regressed texture of the coarse model are unwrapped into UV-space, and then sent through an image-toimage translation network to predict a displacement map in UVspace. The displacement map and the coarse model are used to render a final detailed face, which again can be compared with the original input image to serve as a photometric loss for the second stage. The advantage of learning displacement map in UV-space is that face alignment can be explicitly done during the unwrapping, thus facial details are easier to learn from large amount of data. Extensive experiments demonstrate the superiority of the proposed method over previous work.
Tasks	3D Face Reconstruction, Face Alignment, Face Reconstruction
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11791v1
PDF	https://arxiv.org/pdf/1910.11791v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-learning-of-detailed-3d-face
Repo
Framework

A data-driven proxy to Stoke’s flow in porous media


Title	A data-driven proxy to Stoke’s flow in porous media
Authors	Ali Takbiri-Borujeni, Hadi Kazemi, Nasser Nasrabadi
Abstract	The objective for this work is to develop a data-driven proxy to high-fidelity numerical flow simulations using digital images. The proposed model can capture the flow field and permeability in a large verity of digital porous media based on solid grain geometry and pore size distribution by detailed analyses of the local pore geometry and the local flow fields. To develop the model, the detailed pore space geometry and simulation runs data from 3500 two-dimensional high-fidelity Lattice Boltzmann simulation runs are used to train and to predict the solutions with a high accuracy in much less computational time. The proposed methodology harness the enormous amount of generated data from high-fidelity flow simulations to decode the often under-utilized patterns in simulations and to accurately predict solutions to new cases. The developed model can truly capture the physics of the problem and enhance prediction capabilities of the simulations at a much lower cost. These predictive models, in essence, do not spatio-temporally reduce the order of the problem. They, however, possess the same numerical resolutions as their Lattice Boltzmann simulations equivalents do with the great advantage that their solutions can be achieved by significant reduction in computational costs (speed and memory).
Tasks
Published	2019-04-25
URL	http://arxiv.org/abs/1905.06327v1
PDF	http://arxiv.org/pdf/1905.06327v1.pdf
PWC	https://paperswithcode.com/paper/190506327
Repo
Framework

All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting


Title	All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
Authors	Hao Wang, Pu Lu, Hui Zhang, Mingkun Yang, Xiang Bai, Yongchao Xu, Mengchao He, Yongpan Wang, Wenyu Liu
Abstract	Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision. Different from the existing approaches that formulate text detection as bounding box extraction or instance segmentation, we localize a set of points on the boundary of each text instance. With the representation of such boundary points, we establish a simple yet effective scheme for end-to-end text spotting, which can read the text of arbitrary shapes. Experiments on three challenging datasets, including ICDAR2015, TotalText and COCO-Text demonstrate that the proposed method consistently surpasses the state-of-the-art in both scene text detection and end-to-end text recognition tasks.
Tasks	Instance Segmentation, Scene Text Detection, Semantic Segmentation, Text Spotting
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09550v1
PDF	https://arxiv.org/pdf/1911.09550v1.pdf
PWC	https://paperswithcode.com/paper/all-you-need-is-boundary-toward-arbitrary
Repo
Framework

Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements


Title	Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements
Authors	Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Allison Woodruff, Christine Luu, Pierre Kreitmann, Jonathan Bischof, Ed H. Chi
Abstract	As more researchers have become aware of and passionate about algorithmic fairness, there has been an explosion in papers laying out new metrics, suggesting algorithms to address issues, and calling attention to issues in existing applications of machine learning. This research has greatly expanded our understanding of the concerns and challenges in deploying machine learning, but there has been much less work in seeing how the rubber meets the road. In this paper we provide a case-study on the application of fairness in machine learning research to a production classification system, and offer new insights in how to measure and address algorithmic fairness issues. We discuss open questions in implementing equality of opportunity and describe our fairness metric, conditional equality, that takes into account distributional differences. Further, we provide a new approach to improve on the fairness metric during model training and demonstrate its efficacy in improving performance for a real-world product
Tasks
Published	2019-01-14
URL	http://arxiv.org/abs/1901.04562v1
PDF	http://arxiv.org/pdf/1901.04562v1.pdf
PWC	https://paperswithcode.com/paper/putting-fairness-principles-into-practice
Repo
Framework

Acceleration of Radiation Transport Solves Using Artificial Neural Networks


Title	Acceleration of Radiation Transport Solves Using Artificial Neural Networks
Authors	Mauricio Tano, Jean Ragusa
Abstract	Discontinuous Finite Element Methods (DFEM) have been widely used for solving $S_n$ radiation transport problems in participative and non-participative media. In the DFEM $S_n$ methodology, the transport equation is discretized into a set of algebraic equations that have to be solved for each spatial cell and angular direction, strictly preserving the following of radiation in the system. At the core of a DFEM solver a small matrix-vector system (of 8 independent equations for tri-linear DFEM in 3D hexehdral cells) has to be assembled and solved for each cell, angle, energy group, and time step. These systems are generally solved by direct Gaussian Elimination. The computational cost of the Gaussian Elimination, repeated for each phase-space cell, amounts to a large fraction to the total compute time. Here, we have designed a Machine Learning algorithm based in a shallow Artificial Neural Networks (ANNs) to replace that Gaussian Elimination step, enabling a sizeable speed up in the solution process. The key idea is to train an ANN with a large set of solutions of random one-cell transport problems and then to use the trained ANN to replace Gaussian Elimination large scale transport solvers. It has been observed that ANNs decrease the solution times by at least a factor of 4, while introducing mean absolute errors between 1-3 % in large scale transport solutions.
Tasks
Published	2019-06-06
URL	https://arxiv.org/abs/1906.04017v1
PDF	https://arxiv.org/pdf/1906.04017v1.pdf
PWC	https://paperswithcode.com/paper/acceleration-of-radiation-transport-solves
Repo
Framework

Flexible distribution-free conditional predictive bands using density estimators


Title	Flexible distribution-free conditional predictive bands using density estimators
Authors	Rafael Izbicki, Gilson T. Shimizu, Rafael B. Stern
Abstract	Conformal methods create prediction bands that control average coverage under no assumptions besides i.i.d. data. Besides average coverage, one might also desire to control conditional coverage, that is, coverage for every new testing point. However, without strong assumptions, conditional coverage is unachievable. Given this limitation, the literature has focused on methods with asymptotical conditional coverage. In order to obtain this property, these methods require strong conditions on the dependence between the target variable and the features. We introduce two conformal methods based on conditional density estimators that do not depend on this type of assumption to obtain asymptotic conditional coverage: Dist-split and CD-split. While Dist-split asymptotically obtains optimal intervals, which are easier to interpret than general regions, CD-split obtains optimal size regions, which are smaller than intervals. CD-split also obtains local coverage by creating a data-driven partition of the feature space that scales to high-dimensional settings and by generating prediction bands locally on the partition elements. In a wide variety of simulated scenarios, our methods have a better control of conditional coverage and have smaller length than previously proposed methods.
Tasks
Published	2019-10-12
URL	https://arxiv.org/abs/1910.05575v2
PDF	https://arxiv.org/pdf/1910.05575v2.pdf
PWC	https://paperswithcode.com/paper/distribution-free-conditional-predictive
Repo
Framework