Paper Group ANR 436
Quantum Entanglement in Corpuses of Documents. Pneumonia Detection in Chest Radiographs. Dropout Model Evaluation in MOOCs. Adversarial Active Learning for Deep Networks: a Margin Based Approach. Crowd Counting with Density Adaption Networks. Proprties of biclustering algorithms and a novel biclustering technique based on relative density. K-medoid …
Quantum Entanglement in Corpuses of Documents
| Title | Quantum Entanglement in Corpuses of Documents |
| Authors | Lester Beltran, Suzette Geriente |
| Abstract | We show that data collected from corpuses of documents violate the Clauser-Horne-Shimony-Holt version of Bell’s inequality (CHSH inequality) and therefore indicate the presence of quantum entanglement in their structure. We obtain this result by considering two concepts and their combination and coincidence operations consisting of searches of co-occurrences of exemplars of these concepts in specific corpuses of documents. Measuring the frequencies of these co-occurrences and calculating the relative frequencies as approximate probabilities entering in the CHSH inequality, we obtain manifest violations of the latter for all considered corpuses of documents. In comparing these violations with those analogously obtained in an earlier work for the same combined concepts in psychological coincidence experiments with human participants, also violating the CHSH inequality, we identify the entanglement as being carried by the meaning connection between the two considered concepts within the combination they form. We explain the stronger violation for the corpuses of documents, as compared to the violation in the psychology experiments, as being due to the superior meaning domain of the human mind and, on the other side, to the latter reaching a broader domain of meaning and being possibly also actively influenced during the experimentation. We mention some of the issues to be analyzed in future work such as the violations of the CHSH inequality being larger than the `Cirel’son bound’ for all of the considered corpuses of documents. | |
| Tasks | |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.12114v1 |
| http://arxiv.org/pdf/1810.12114v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-entanglement-in-corpuses-of-documents |
| Repo | |
| Framework | |
Pneumonia Detection in Chest Radiographs
| Title | Pneumonia Detection in Chest Radiographs |
| Authors | The DeepRadiology Team |
| Abstract | In this work, we describe our approach to pneumonia classification and localization in chest radiographs. This method uses only \emph{open-source} deep learning object detection and is based on CoupleNet, a fully convolutional network which incorporates global and local features for object detection. Our approach achieves robustness through critical modifications of the training process and a novel ensembling algorithm which merges bounding boxes from several models. We tested our detection algorithm tested on a dataset of 3000 chest radiographs as part of the 2018 RSNA Pneumonia Challenge; our solution was recognized as a winning entry in a contest which attracted more than 1400 participants worldwide. |
| Tasks | Object Detection, Pneumonia Detection |
| Published | 2018-11-21 |
| URL | http://arxiv.org/abs/1811.08939v1 |
| http://arxiv.org/pdf/1811.08939v1.pdf | |
| PWC | https://paperswithcode.com/paper/pneumonia-detection-in-chest-radiographs |
| Repo | |
| Framework | |
Dropout Model Evaluation in MOOCs
| Title | Dropout Model Evaluation in MOOCs |
| Authors | Josh Gardner, Christopher Brooks |
| Abstract | The field of learning analytics needs to adopt a more rigorous approach for predictive model evaluation that matches the complex practice of model-building. In this work, we present a procedure to statistically test hypotheses about model performance which goes beyond the state-of-the-practice in the community to analyze both algorithms and feature extraction methods from raw data. We apply this method to a series of algorithms and feature sets derived from a large sample of Massive Open Online Courses (MOOCs). While a complete comparison of all potential modeling approaches is beyond the scope of this paper, we show that this approach reveals a large gap in dropout prediction performance between forum-, assignment-, and clickstream-based feature extraction methods, where the latter is significantly better than the former two, which are in turn indistinguishable from one another. This work has methodological implications for evaluating predictive or AI-based models of student success, and practical implications for the design and targeting of at-risk student models and interventions. |
| Tasks | |
| Published | 2018-02-16 |
| URL | http://arxiv.org/abs/1802.06009v1 |
| http://arxiv.org/pdf/1802.06009v1.pdf | |
| PWC | https://paperswithcode.com/paper/dropout-model-evaluation-in-moocs |
| Repo | |
| Framework | |
Adversarial Active Learning for Deep Networks: a Margin Based Approach
| Title | Adversarial Active Learning for Deep Networks: a Margin Based Approach |
| Authors | Melanie Ducoffe, Frederic Precioso |
| Abstract | We propose a new active learning strategy designed for deep neural networks. The goal is to minimize the number of data annotation queried from an oracle during training. Previous active learning strategies scalable for deep networks were mostly based on uncertain sample selection. In this work, we focus on examples lying close to the decision boundary. Based on theoretical works on margin theory for active learning, we know that such examples may help to considerably decrease the number of annotations. While measuring the exact distance to the decision boundaries is intractable, we propose to rely on adversarial examples. We do not consider anymore them as a threat instead we exploit the information they provide on the distribution of the input space in order to approximate the distance to decision boundaries. We demonstrate empirically that adversarial active queries yield faster convergence of CNNs trained on MNIST, the Shoe-Bag and the Quick-Draw datasets. |
| Tasks | Active Learning |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09841v1 |
| http://arxiv.org/pdf/1802.09841v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-active-learning-for-deep-networks |
| Repo | |
| Framework | |
Crowd Counting with Density Adaption Networks
| Title | Crowd Counting with Density Adaption Networks |
| Authors | Li Wang, Weiyuan Shao, Yao Lu, Hao Ye, Jian Pu, Yingbin Zheng |
| Abstract | Crowd counting is one of the core tasks in various surveillance applications. A practical system involves estimating accurate head counts in dynamic scenarios under different lightning, camera perspective and occlusion states. Previous approaches estimate head counts despite that they can vary dramatically in different density settings; the crowd is often unevenly distributed and the results are therefore unsatisfactory. In this paper, we propose a lightweight deep learning framework that can automatically estimate the crowd density level and adaptively choose between different counter networks that are explicitly trained for different density domains. Experiments on two recent crowd counting datasets, UCF_CC_50 and ShanghaiTech, show that the proposed mechanism achieves promising improvements over state-of-the-art methods. Moreover, runtime speed is 20 FPS on a single GPU. |
| Tasks | Crowd Counting |
| Published | 2018-06-26 |
| URL | http://arxiv.org/abs/1806.10040v1 |
| http://arxiv.org/pdf/1806.10040v1.pdf | |
| PWC | https://paperswithcode.com/paper/crowd-counting-with-density-adaption-networks |
| Repo | |
| Framework | |
Proprties of biclustering algorithms and a novel biclustering technique based on relative density
| Title | Proprties of biclustering algorithms and a novel biclustering technique based on relative density |
| Authors | Namita Jain, Susmita Ghosh, C. A. Murthy |
| Abstract | Biclustering is found to be useful in areas like data mining and bioinformatics. The term biclustering involves searching subsets of observations and features forming coherent structure. This can be interpreted in different ways like spatial closeness, relation between features for selected observations etc. This article discusses different properties, objectives and approaches of biclustering algorithms. We also present an algorithm which detects feature relation based biclusters using density based techniques. Here we use relative density of regions to identify biclusters embedded in the data. Properties of this algorithm are discussed and demonstrated using artificial datasets. The proposed method is seen to provide better results on both artificial and real datasets. Paired right tailed t test is used for artificial datasets. |
| Tasks | |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04661v2 |
| http://arxiv.org/pdf/1811.04661v2.pdf | |
| PWC | https://paperswithcode.com/paper/proprties-of-biclustering-algorithms-and-a |
| Repo | |
| Framework | |
K-medoids Clustering of Data Sequences with Composite Distributions
| Title | K-medoids Clustering of Data Sequences with Composite Distributions |
| Authors | Tiexing Wang, Qunwei Li, Donald J. Bucci, Yingbin Liang, Biao Chen, Pramod K. Varshney |
| Abstract | This paper studies clustering of data sequences using the k-medoids algorithm. All the data sequences are assumed to be generated from \emph{unknown} continuous distributions, which form clusters with each cluster containing a composite set of closely located distributions (based on a certain distance metric between distributions). The maximum intra-cluster distance is assumed to be smaller than the minimum inter-cluster distance, and both values are assumed to be known. The goal is to group the data sequences together if their underlying generative distributions (which are unknown) belong to one cluster. Distribution distance metrics based k-medoids algorithms are proposed for known and unknown number of distribution clusters. Upper bounds on the error probability and convergence results in the large sample regime are also provided. It is shown that the error probability decays exponentially fast as the number of samples in each data sequence goes to infinity. The error exponent has a simple form regardless of the distance metric applied when certain conditions are satisfied. In particular, the error exponent is characterized when either the Kolmogrov-Smirnov distance or the maximum mean discrepancy are used as the distance metric. Simulation results are provided to validate the analysis. |
| Tasks | |
| Published | 2018-07-31 |
| URL | http://arxiv.org/abs/1807.11620v1 |
| http://arxiv.org/pdf/1807.11620v1.pdf | |
| PWC | https://paperswithcode.com/paper/k-medoids-clustering-of-data-sequences-with |
| Repo | |
| Framework | |
Optimizing Segmentation Granularity for Neural Machine Translation
| Title | Optimizing Segmentation Granularity for Neural Machine Translation |
| Authors | Elizabeth Salesky, Andrew Runge, Alex Coda, Jan Niehues, Graham Neubig |
| Abstract | In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair encoding (BPE) and its variants are the predominant approach to generating these subwords, as they are unsupervised, resource-free, and empirically effective. However, the granularity of these subword units is a hyperparameter to be tuned for each language and task, using methods such as grid search. Tuning may be done inexhaustively or skipped entirely due to resource constraints, leading to sub-optimal performance. In this paper, we propose a method to automatically tune this parameter using only one training pass. We incrementally introduce new vocabulary online based on the held-out validation loss, beginning with smaller, general subwords and adding larger, more specific units over the course of training. Our method matches the results found with grid search, optimizing segmentation granularity without any additional training time. We also show benefits in training efficiency and performance improvements for rare words due to the way embeddings for larger units are incrementally constructed by combining those from smaller units. |
| Tasks | Machine Translation |
| Published | 2018-10-19 |
| URL | http://arxiv.org/abs/1810.08641v1 |
| http://arxiv.org/pdf/1810.08641v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-segmentation-granularity-for |
| Repo | |
| Framework | |
Backpropagation with N-D Vector-Valued Neurons Using Arbitrary Bilinear Products
| Title | Backpropagation with N-D Vector-Valued Neurons Using Arbitrary Bilinear Products |
| Authors | Zhe-Cheng Fan, Tak-Shing T. Chan, Yi-Hsuan Yang, Jyh-Shing R. Jang |
| Abstract | Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this paper, we propose a new vector neural architecture called the Arbitrary BIlinear Product Neural Network (ABIPNN), which processes information as vectors in each neuron, and the feedforward projections are defined using arbitrary bilinear products. Such bilinear products can include circular convolution, seven-dimensional vector product, skew circular convolution, reversed- time circular convolution, or other new products not seen in previous work. As a proof-of-concept, we apply our proposed network to multispectral image denoising and singing voice sepa- ration. Experimental results show that ABIPNN gains substantial improvements when compared to conventional NNs, suggesting that associations are learned during training. |
| Tasks | Denoising, Image Denoising |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.09621v1 |
| http://arxiv.org/pdf/1805.09621v1.pdf | |
| PWC | https://paperswithcode.com/paper/backpropagation-with-n-d-vector-valued |
| Repo | |
| Framework | |
Nonparametric Hawkes Processes: Online Estimation and Generalization Bounds
| Title | Nonparametric Hawkes Processes: Online Estimation and Generalization Bounds |
| Authors | Yingxiang Yang, Jalal Etesami, Niao He, Negar Kiyavash |
| Abstract | In this paper, we design a nonparametric online algorithm for estimating the triggering functions of multivariate Hawkes processes. Unlike parametric estimation, where evolutionary dynamics can be exploited for fast computation of the gradient, and unlike typical function learning, where representer theorem is readily applicable upon proper regularization of the objective function, nonparametric estimation faces the challenges of (i) inefficient evaluation of the gradient, (ii) lack of representer theorem, and (iii) computationally expensive projection necessary to guarantee positivity of the triggering functions. In this paper, we offer solutions to the above challenges, and design an online estimation algorithm named NPOLE-MHP that outputs estimations with a $\mathcal{O}(1/T)$ regret, and a $\mathcal{O}(1/T)$ stability. Furthermore, we design an algorithm, NPOLE-MMHP, for estimation of multivariate marked Hawkes processes. We test the performance of NPOLE-MHP on various synthetic and real datasets, and demonstrate, under different evaluation metrics, that NPOLE-MHP performs as good as the optimal maximum likelihood estimation (MLE), while having a run time as little as parametric online algorithms. |
| Tasks | |
| Published | 2018-01-25 |
| URL | http://arxiv.org/abs/1801.08273v1 |
| http://arxiv.org/pdf/1801.08273v1.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-hawkes-processes-online |
| Repo | |
| Framework | |
Analysis of Wikipedia-based Corpora for Question Answering
| Title | Analysis of Wikipedia-based Corpora for Question Answering |
| Authors | Tomasz Jurczyk, Amit Deshmane, Jinho D. Choi |
| Abstract | This paper gives comprehensive analyses of corpora based on Wikipedia for several tasks in question answering. Four recent corpora are collected,WikiQA, SelQA, SQuAD, and InfoQA, and first analyzed intrinsically by contextual similarities, question types, and answer categories. These corpora are then analyzed extrinsically by three question answering tasks, answer retrieval, selection, and triggering. An indexing-based method for the creation of a silver-standard dataset for answer retrieval using the entire Wikipedia is also presented. Our analysis shows the uniqueness of these corpora and suggests a better use of them for statistical question answering learning. |
| Tasks | Question Answering |
| Published | 2018-01-06 |
| URL | http://arxiv.org/abs/1801.02073v2 |
| http://arxiv.org/pdf/1801.02073v2.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-wikipedia-based-corpora-for |
| Repo | |
| Framework | |
Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration
| Title | Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration |
| Authors | Xiaoshuai Zhang, Yiping Lu, Jiaying Liu, Bin Dong |
| Abstract | In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels in one model. The proposed control problem contains a restoration dynamics which is modeled by an RNN. The moving endpoint, which is essentially the terminal time of the associated dynamics, is determined by a policy network. We call the proposed model the dynamically unfolding recurrent restorer (DURR). Numerical experiments show that DURR is able to achieve state-of-the-art performances on blind image denoising and JPEG image deblocking. Furthermore, DURR can well generalize to images with higher degradation levels that are not included in the training stage. |
| Tasks | Denoising, Image Denoising, Image Restoration |
| Published | 2018-05-20 |
| URL | http://arxiv.org/abs/1805.07709v2 |
| http://arxiv.org/pdf/1805.07709v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamically-unfolding-recurrent-restorer-a |
| Repo | |
| Framework | |
Image Denoising via Collaborative Dual-Domain Patch Filtering
| Title | Image Denoising via Collaborative Dual-Domain Patch Filtering |
| Authors | Muzammil Behzad |
| Abstract | In this paper, we propose a novel image denoising algorithm exploiting features from both spatial as well as transformed domain. We implement intensity-invariance based improved grouping for collaborative support-agnostic sparse reconstruction. For collaboration firstly, we stack similar-structured patches via intensity-invariant correlation measure. The grouped patches collaborate to yield desirable sparse estimates for noise filtering. This is because similar patches share the same support in the transformed domain, such similar supports can be used as probabilities of active taps to refine the sparse estimates. This ultimately produces a very useful patch estimate thus increasing the quality of recovered image by discarding the noise-causing components. A region growing based spatially developed post-processor is then applied to further enhance the smooth regions by extracting the spatial domain features. We also extend our proposed method for denoising of color images. Comparison results with the state-of-the-art algorithms in terms of peak signal-to-noise ratio (PNSR) and structural similarity (SSIM) index from extensive experimentations via a broad range of scenarios demonstrate the superiority of our proposed algorithm. |
| Tasks | Denoising, Image Denoising |
| Published | 2018-05-01 |
| URL | http://arxiv.org/abs/1805.00472v1 |
| http://arxiv.org/pdf/1805.00472v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-denoising-via-collaborative-dual-domain |
| Repo | |
| Framework | |
Cardiac Motion Scoring with Segment- and Subject-level Non-Local Modeling
| Title | Cardiac Motion Scoring with Segment- and Subject-level Non-Local Modeling |
| Authors | Wufeng Xue, Gary Brahm, Stephanie Leung, Ogla Shmuilovich, Shuo Li |
| Abstract | Motion scoring of cardiac myocardium is of paramount importance for early detection and diagnosis of various cardiac disease. It aims at identifying regional wall motions into one of the four types including normal, hypokinetic, akinetic, and dyskinetic, and is extremely challenging due to the complex myocardium deformation and subtle inter-class difference of motion patterns. All existing work on automated motion analysis are focused on binary abnormality detection to avoid the much more demanding motion scoring, which is urgently required in real clinical practice yet has never been investigated before. In this work, we propose Cardiac-MOS, the first powerful method for cardiac motion scoring from cardiac MR sequences based on deep convolution neural network. Due to the locality of convolution, the relationship between distant non-local responses of the feature map cannot be explored, which is closely related to motion difference between segments. In Cardiac-MOS, such non-local relationship is modeled with non-local neural network within each segment and across all segments of one subject, i.e., segment- and subject-level non-local modeling, and lead to obvious performance improvement. Besides, Cardiac-MOS can effectively extract motion information from MR sequences of various lengths by interpolating the convolution kernel along the temporal dimension, therefore can be applied to MR sequences of multiple sources. Experiments on 1440 myocardium segments of 90 subjects from short axis MR sequences of multiple lengths prove that Cardiac-MOS achieves reliable performance, with correlation of 0.926 for motion score index estimation and accuracy of 77.4% for motion scoring. Cardiac-MOS also outperforms all existing work for binary abnormality detection. As the first automatic motion scoring solution, Cardiac-MOS demonstrates great potential in future clinical application. |
| Tasks | Anomaly Detection |
| Published | 2018-06-14 |
| URL | http://arxiv.org/abs/1806.05569v1 |
| http://arxiv.org/pdf/1806.05569v1.pdf | |
| PWC | https://paperswithcode.com/paper/cardiac-motion-scoring-with-segment-and |
| Repo | |
| Framework | |
Analyzing Federated Learning through an Adversarial Lens
| Title | Analyzing Federated Learning through an Adversarial Lens |
| Authors | Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal, Seraphin Calo |
| Abstract | Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this work, we explore the threat of model poisoning attacks on federated learning initiated by a single, non-colluding malicious agent where the adversarial objective is to cause the model to misclassify a set of chosen inputs with high confidence. We explore a number of strategies to carry out this attack, starting with simple boosting of the malicious agent’s update to overcome the effects of other agents’ updates. To increase attack stealth, we propose an alternating minimization strategy, which alternately optimizes for the training loss and the adversarial objective. We follow up by using parameter estimation for the benign agents’ updates to improve on attack success. Finally, we use a suite of interpretability techniques to generate visual explanations of model decisions for both benign and malicious models and show that the explanations are nearly visually indistinguishable. Our results indicate that even a highly constrained adversary can carry out model poisoning attacks while simultaneously maintaining stealth, thus highlighting the vulnerability of the federated learning setting and the need to develop effective defense strategies. |
| Tasks | |
| Published | 2018-11-29 |
| URL | https://arxiv.org/abs/1811.12470v4 |
| https://arxiv.org/pdf/1811.12470v4.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-federated-learning-through-an |
| Repo | |
| Framework | |
