Paper Group ANR 177
Closing the U.S. gender wage gap requires understanding its heterogeneity. Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks. Stochastic bandits robust to adversarial corruptions. Aspect Sentiment Model for Micro Reviews. Adversarial Resilience Learning - Towards Systemic Vulnerability Analysis for Large and Complex …
Closing the U.S. gender wage gap requires understanding its heterogeneity
| Title | Closing the U.S. gender wage gap requires understanding its heterogeneity |
| Authors | Philipp Bach, Victor Chernozhukov, Martin Spindler |
| Abstract | In 2016, the majority of full-time employed women in the U.S. earned significantly less than comparable men. The extent to which women were affected by gender inequality in earnings, however, depended greatly on socio-economic characteristics, such as marital status or educational attainment. In this paper, we analyzed data from the 2016 American Community Survey using a high-dimensional wage regression and applying double lasso to quantify heterogeneity in the gender wage gap. We found that the gap varied substantially across women and was driven primarily by marital status, having children at home, race, occupation, industry, and educational attainment. We recommend that policy makers use these insights to design policies that will reduce discrimination and unequal pay more effectively. |
| Tasks | |
| Published | 2018-12-11 |
| URL | http://arxiv.org/abs/1812.04345v1 |
| http://arxiv.org/pdf/1812.04345v1.pdf | |
| PWC | https://paperswithcode.com/paper/closing-the-us-gender-wage-gap-requires |
| Repo | |
| Framework | |
Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks
| Title | Competition vs. Concatenation in Skip Connections of Fully Convolutional Networks |
| Authors | Santiago Estrada, Sailesh Conjeti, Muneer Ahmad, Nassir Navab, Martin Reuter |
| Abstract | Increased information sharing through short and long-range skip connections between layers in fully convolutional networks have demonstrated significant improvement in performance for semantic segmentation. In this paper, we propose Competitive Dense Fully Convolutional Networks (CDFNet) by introducing competitive maxout activations in place of naive feature concatenation for inducing competition amongst layers. Within CDFNet, we propose two architectural contributions, namely competitive dense block (CDB) and competitive unpooling block (CUB) to induce competition at local and global scales for short and long-range skip connections respectively. This extension is demonstrated to boost learning of specialized sub-networks targeted at segmenting specific anatomies, which in turn eases the training of complex tasks. We present the proof-of-concept on the challenging task of whole body segmentation in the publicly available VISCERAL benchmark and demonstrate improved performance over multiple learning and registration based state-of-the-art methods. |
| Tasks | Semantic Segmentation |
| Published | 2018-07-20 |
| URL | http://arxiv.org/abs/1807.07803v1 |
| http://arxiv.org/pdf/1807.07803v1.pdf | |
| PWC | https://paperswithcode.com/paper/competition-vs-concatenation-in-skip |
| Repo | |
| Framework | |
Stochastic bandits robust to adversarial corruptions
| Title | Stochastic bandits robust to adversarial corruptions |
| Authors | Thodoris Lykouris, Vahab Mirrokni, Renato Paes Leme |
| Abstract | We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm, e.g., click fraud, fake reviews and email spam. The goal of this model is to encourage the design of bandit algorithms that (i) work well in mixed adversarial and stochastic models, and (ii) whose performance deteriorates gracefully as we move from fully stochastic to fully adversarial models. In our model, the rewards for all arms are initially drawn from a distribution and are then altered by an adaptive adversary. We provide a simple algorithm whose performance gracefully degrades with the total corruption the adversary injected in the data, measured by the sum across rounds of the biggest alteration the adversary made in the data in that round; this total corruption is denoted by $C$. Our algorithm provides a guarantee that retains the optimal guarantee (up to a logarithmic term) if the input is stochastic and whose performance degrades linearly to the amount of corruption $C$, while crucially being agnostic to it. We also provide a lower bound showing that this linear degradation is necessary if the algorithm achieves optimal performance in the stochastic setting (the lower bound works even for a known amount of corruption, a special case in which our algorithm achieves optimal performance without the extra logarithm). |
| Tasks | |
| Published | 2018-03-25 |
| URL | http://arxiv.org/abs/1803.09353v1 |
| http://arxiv.org/pdf/1803.09353v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-bandits-robust-to-adversarial |
| Repo | |
| Framework | |
Aspect Sentiment Model for Micro Reviews
| Title | Aspect Sentiment Model for Micro Reviews |
| Authors | Reinald Kim Amplayo, Seung-won Hwang |
| Abstract | This paper aims at an aspect sentiment model for aspect-based sentiment analysis (ABSA) focused on micro reviews. This task is important in order to understand short reviews majority of the users write, while existing topic models are targeted for expert-level long reviews with sufficient co-occurrence patterns to observe. Current methods on aggregating micro reviews using metadata information may not be effective as well due to metadata absence, topical heterogeneity, and cold start problems. To this end, we propose a model called Micro Aspect Sentiment Model (MicroASM). MicroASM is based on the observation that short reviews 1) are viewed with sentiment-aspect word pairs as building blocks of information, and 2) can be clustered into larger reviews. When compared to the current state-of-the-art aspect sentiment models, experiments show that our model provides better performance on aspect-level tasks such as aspect term extraction and document-level tasks such as sentiment classification. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis, Topic Models |
| Published | 2018-06-14 |
| URL | http://arxiv.org/abs/1806.05499v1 |
| http://arxiv.org/pdf/1806.05499v1.pdf | |
| PWC | https://paperswithcode.com/paper/aspect-sentiment-model-for-micro-reviews |
| Repo | |
| Framework | |
Adversarial Resilience Learning - Towards Systemic Vulnerability Analysis for Large and Complex Systems
| Title | Adversarial Resilience Learning - Towards Systemic Vulnerability Analysis for Large and Complex Systems |
| Authors | Lars Fischer, Jan-Menno Memmen, Eric MSP Veith, Martin Tröschel |
| Abstract | This paper introduces Adversarial Resilience Learning (ARL), a concept to model, train, and analyze artificial neural networks as representations of competitive agents in highly complex systems. In our examples, the agents normally take the roles of attackers or defenders that aim at worsening or improving-or keeping, respectively-defined performance indicators of the system. Our concept provides adaptive, repeatable, actor-based testing with a chance of detecting previously unknown attack vectors. We provide the constitutive nomenclature of ARL and, based on it, the description of experimental setups and results of a preliminary implementation of ARL in simulated power systems. |
| Tasks | |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06447v1 |
| http://arxiv.org/pdf/1811.06447v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-resilience-learning-towards |
| Repo | |
| Framework | |
Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks
| Title | Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks |
| Authors | Siyue Wang, Xiao Wang, Pu Zhao, Wujie Wen, David Kaeli, Peter Chin, Xue Lin |
| Abstract | Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. This work provides a solution to hardening DNNs under adversarial attacks through defensive dropout. Besides using dropout during training for the best test accuracy, we propose to use dropout also at test time to achieve strong defense effects. We consider the problem of building robust DNNs as an attacker-defender two-player game, where the attacker and the defender know each others’ strategies and try to optimize their own strategies towards an equilibrium. Based on the observations of the effect of test dropout rate on test accuracy and attack success rate, we propose a defensive dropout algorithm to determine an optimal test dropout rate given the neural network model and the attacker’s strategy for generating adversarial examples.We also investigate the mechanism behind the outstanding defense effects achieved by the proposed defensive dropout. Comparing with stochastic activation pruning (SAP), another defense method through introducing randomness into the DNN model, we find that our defensive dropout achieves much larger variances of the gradients, which is the key for the improved defense effects (much lower attack success rate). For example, our defensive dropout can reduce the attack success rate from 100% to 13.89% under the currently strongest attack i.e., C&W attack on MNIST dataset. |
| Tasks | |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.05165v1 |
| http://arxiv.org/pdf/1809.05165v1.pdf | |
| PWC | https://paperswithcode.com/paper/defensive-dropout-for-hardening-deep-neural |
| Repo | |
| Framework | |
Multi-view registration of unordered range scans by fast correspondence propagation of multi-scale descriptors
| Title | Multi-view registration of unordered range scans by fast correspondence propagation of multi-scale descriptors |
| Authors | Jihua Zhu, Siyu Xu, Zutao Jiang, Shanmin Pang, Jun Wang, Zhongyu Li |
| Abstract | This paper proposes a global approach for the multi-view registration of unordered range scans. As the basis of multi-view registration, pair-wise registration is very pivotal. Therefore, we first select a good descriptor and accelerate its correspondence propagation for the pair-wise registration. Then, we design an effective rule to judge the reliability of pair-wise registration results. Subsequently, we propose a model augmentation method, which can utilize reliable results of pair-wise registration to augment the model shape. Finally, multi-view registration can be accomplished by operating the pair-wise registration and judgment, and model augmentation alternately. Experimental results on public available data sets show, that this approach can automatically achieve the multi-view registration of unordered range scans with good accuracy and effectiveness. |
| Tasks | |
| Published | 2018-04-21 |
| URL | http://arxiv.org/abs/1804.07926v1 |
| http://arxiv.org/pdf/1804.07926v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-registration-of-unordered-range |
| Repo | |
| Framework | |
Handling Verb Phrase Anaphora with Dependent Types and Events
| Title | Handling Verb Phrase Anaphora with Dependent Types and Events |
| Authors | Daniyar Itegulov, Ekaterina Lebedeva |
| Abstract | This paper studies how dependent typed events can be used to treat verb phrase anaphora. We introduce a framework that extends Dependent Type Semantics (DTS) with a new atomic type for neo-Davidsonian events and an extended @-operator that can return new events that share properties of events referenced by verb phrase anaphora. The proposed framework, along with illustrative examples of its use, are presented after a brief overview of the necessary background and of the major challenges posed by verb phrase anaphora. |
| Tasks | |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10421v1 |
| http://arxiv.org/pdf/1803.10421v1.pdf | |
| PWC | https://paperswithcode.com/paper/handling-verb-phrase-anaphora-with-dependent |
| Repo | |
| Framework | |
Correspondence Analysis of Government Expenditure Patterns
| Title | Correspondence Analysis of Government Expenditure Patterns |
| Authors | Hsiang Hsu, Flavio P. Calmon, José Cândido Silveira Santos Filho, Andre P. Calmon, Salman Salamatian |
| Abstract | We analyze expenditure patterns of discretionary funds by Brazilian congress members. This analysis is based on a large dataset containing over $7$ million expenses made publicly available by the Brazilian government. This dataset has, up to now, remained widely untouched by machine learning methods. Our main contributions are two-fold: (i) we provide a novel dataset benchmark for machine learning-based efforts for government transparency to the broader research community, and (ii) introduce a neural network-based approach for analyzing and visualizing outlying expense patterns. Our hope is that the approach presented here can inspire new machine learning methodologies for government transparency applicable to other developing nations. |
| Tasks | |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1812.01105v1 |
| http://arxiv.org/pdf/1812.01105v1.pdf | |
| PWC | https://paperswithcode.com/paper/correspondence-analysis-of-government |
| Repo | |
| Framework | |
Real-time coherent diffraction inversion using deep generative networks
| Title | Real-time coherent diffraction inversion using deep generative networks |
| Authors | Mathew J. Cherukara, Youssef S. G. Nashed, Ross J. Harder |
| Abstract | Phase retrieval, or the process of recovering phase information in reciprocal space to reconstruct images from measured intensity alone, is the underlying basis to a variety of imaging applications including coherent diffraction imaging (CDI). Typical phase retrieval algorithms are iterative in nature, and hence, are time-consuming and computationally expensive, precluding real-time imaging. Furthermore, iterative phase retrieval algorithms struggle to converge to the correct solution especially in the presence of strong phase structures. In this work, we demonstrate the training and testing of CDI NN, a pair of deep deconvolutional networks trained to predict structure and phase in real space of a 2D object from its corresponding far-field diffraction intensities alone. Once trained, CDI NN can invert a diffraction pattern to an image within a few milliseconds of compute time on a standard desktop machine, opening the door to real-time imaging. |
| Tasks | |
| Published | 2018-06-07 |
| URL | http://arxiv.org/abs/1806.03992v1 |
| http://arxiv.org/pdf/1806.03992v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-coherent-diffraction-inversion |
| Repo | |
| Framework | |
On Statistical Learning of Simplices: Unmixing Problem Revisited
| Title | On Statistical Learning of Simplices: Unmixing Problem Revisited |
| Authors | Amir Najafi, Saeed Ilchi, Amir H. Saberi, Abolfazl Motahari, Babak H. Khalaj, Hamid R. Rabiee |
| Abstract | We study the sample complexity of learning a high-dimensional simplex from a set of points uniformly sampled from its interior. Learning of simplices is a long studied problem in computer science and has applications in computational biology and remote sensing, mostly under the name of `spectral unmixing’. We theoretically show that a sufficient sample complexity for reliable learning of a $K$-dimensional simplex is $O\left(K^2\log K\right)$, which yields a significant improvement over the existing bounds. Based on our new theoretical framework, we also propose a heuristic approach for the inference of simplices. Experimental results on synthetic and real-world datasets demonstrate a comparable performance for our method on noiseless samples, while we outperform the state-of-the-art in noisy cases. | |
| Tasks | |
| Published | 2018-10-18 |
| URL | https://arxiv.org/abs/1810.07845v3 |
| https://arxiv.org/pdf/1810.07845v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-statistical-learning-of-simplices-unmixing |
| Repo | |
| Framework | |
Heuristic Optimization of Electrical Energy Systems: Refined Metrics to Compare the Solutions
| Title | Heuristic Optimization of Electrical Energy Systems: Refined Metrics to Compare the Solutions |
| Authors | Gianfranco Chicco, Andrea Mazza |
| Abstract | Many optimization problems admit a number of local optima, among which there is the global optimum. For these problems, various heuristic optimization methods have been proposed. Comparing the results of these solvers requires the definition of suitable metrics. In the electrical energy systems literature, simple metrics such as best value obtained, the mean value, the median or the standard deviation of the solutions are still used. However, the comparisons carried out with these metrics are rather weak, and on these bases a somehow uncontrolled proliferation of heuristic solvers is taking place. This paper addresses the overall issue of understanding the reasons of this proliferation, showing a conceptual scheme that indicates how the assessment of the best solver may result in the unlimited formulation of new solvers. Moreover, this paper shows how the use of more refined metrics defined to compare the optimization result, associated with the definition of appropriate benchmarks, may make the comparisons among the solvers more robust. The proposed metrics are based on the concept of first-order stochastic dominance and are defined for the cases in which: (i) the globally optimal solution can be found (for testing purposes); and (ii) the number of possible solutions is so large that practically it cannot be guaranteed that the global optimum has been found. Illustrative examples are provided for a typical problem in the electrical energy systems area-distribution network reconfiguration. The conceptual results obtained are generally valid to compare the results of other optimization problems. |
| Tasks | |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.02196v2 |
| http://arxiv.org/pdf/1810.02196v2.pdf | |
| PWC | https://paperswithcode.com/paper/heuristic-optimization-of-electrical-energy |
| Repo | |
| Framework | |
Personalized neural language models for real-world query auto completion
| Title | Personalized neural language models for real-world query auto completion |
| Authors | Nicolas Fiorini, Zhiyong Lu |
| Abstract | Query auto completion (QAC) systems are a standard part of search engines in industry, helping users formulate their query. Such systems update their suggestions after the user types each character, predicting the user’s intent using various signals - one of the most common being popularity. Recently, deep learning approaches have been proposed for the QAC task, to specifically address the main limitation of previous popularity-based methods: the inability to predict unseen queries. In this work we improve previous methods based on neural language modeling, with the goal of building an end-to-end system. We particularly focus on using real-world data by integrating user information for personalized suggestions when possible. We also make use of time information and study how to increase diversity in the suggestions while studying the impact on scalability. Our empirical results demonstrate a marked improvement on two separate datasets over previous best methods in both accuracy and scalability, making a step towards neural query auto-completion in production search engines. |
| Tasks | Language Modelling |
| Published | 2018-04-17 |
| URL | http://arxiv.org/abs/1804.06439v3 |
| http://arxiv.org/pdf/1804.06439v3.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-neural-language-models-for-real |
| Repo | |
| Framework | |
Multi-modal Egocentric Activity Recognition using Audio-Visual Features
| Title | Multi-modal Egocentric Activity Recognition using Audio-Visual Features |
| Authors | Mehmet Ali Arabacı, Fatih Özkan, Elif Surer, Peter Jančovič, Alptekin Temizel |
| Abstract | Egocentric activity recognition in first-person videos has an increasing importance with a variety of applications such as lifelogging, summarization, assisted-living and activity tracking. Existing methods for this task are based on interpretation of various sensor information using pre-determined weights for each feature. In this work, we propose a new framework for egocentric activity recognition problem based on combining audio-visual features with multi-kernel learning (MKL) and multi-kernel boosting (MKBoost). For that purpose, firstly grid optical-flow, virtual-inertia feature, log-covariance, cuboid are extracted from the video. The audio signal is characterized using a “supervector”, obtained based on Gaussian mixture modelling of frame-level features, followed by a maximum a-posteriori adaptation. Then, the extracted multi-modal features are adaptively fused by MKL classifiers in which both the feature and kernel selection/weighing and recognition tasks are performed together. The proposed framework was evaluated on a number of egocentric datasets. The results showed that using multi-modal features with MKL outperforms the existing methods. |
| Tasks | Activity Recognition, Egocentric Activity Recognition, Optical Flow Estimation |
| Published | 2018-07-02 |
| URL | http://arxiv.org/abs/1807.00612v2 |
| http://arxiv.org/pdf/1807.00612v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-egocentric-activity-recognition |
| Repo | |
| Framework | |
Multi-layer Kernel Ridge Regression for One-class Classification
| Title | Multi-layer Kernel Ridge Regression for One-class Classification |
| Authors | Chandan Gautam, Aruna Tiwari, Sundaram Suresh, Alexandros Iosifidis |
| Abstract | In this paper, a multi-layer architecture (in a hierarchical fashion) by stacking various Kernel Ridge Regression (KRR) based Auto-Encoder for one-class classification is proposed and is referred as MKOC. MKOC has many layers of Auto-Encoders to project the input features into new feature space and the last layer was regression based one class classifier. The Auto-Encoders use an unsupervised approach of learning and the final layer uses semi-supervised (trained by only positive samples) approach of learning. The proposed MKOC is experimentally evaluated on 15 publicly available benchmark datasets. Experimental results verify the effectiveness of the proposed approach over 11 existing state-of-the-art kernel-based one-class classifiers. Friedman test is also performed to verify the statistical significance of the claim of the superiority of the proposed one-class classifiers over the existing state-of-the-art methods. |
| Tasks | One-class classifier |
| Published | 2018-05-20 |
| URL | http://arxiv.org/abs/1805.07808v2 |
| http://arxiv.org/pdf/1805.07808v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-layer-kernel-ridge-regression-for-one |
| Repo | |
| Framework | |
