January 29, 2020

2923 words 14 mins read

Paper Group ANR 497

Truth Discovery via Proxy Voting. Trimmed Constrained Mixed Effects Models: Formulations and Algorithms. NNE: A Dataset for Nested Named Entity Recognition in English Newswire. Quantum Computing based Hybrid Solution Strategies for Large-scale Discrete-Continuous Optimization Problems. Minimal model of permutation symmetry in unsupervised learning. …

Truth Discovery via Proxy Voting


Title	Truth Discovery via Proxy Voting
Authors	Reshef Meir, Ofra Amir, Gal Cohensius, Omer Ben-Porat, Lirong Xia
Abstract	Truth discovery is a general name for a broad range of statistical methods aimed to extract the correct answers to questions, based on multiple answers coming from noisy sources. For example, workers in a crowdsourcing platform. In this paper, we design simple truth discovery methods inspired by \emph{proxy voting}, that give higher weight to workers whose answers are close to those of other workers. We prove that under standard statistical assumptions, proxy-based truth discovery (\PTD) allows us to estimate the true competence of each worker, whether workers face questions whose answers are real-valued, categorical, or rankings. We then demonstrate through extensive empirical study on synthetic and real data that \PTD is substantially better than unweighted aggregation, and competes well with other truth discovery methods, in all of the above domains.
Tasks
Published	2019-05-02
URL	http://arxiv.org/abs/1905.00629v1
PDF	http://arxiv.org/pdf/1905.00629v1.pdf
PWC	https://paperswithcode.com/paper/truth-discovery-via-proxy-voting
Repo
Framework

Trimmed Constrained Mixed Effects Models: Formulations and Algorithms


Title	Trimmed Constrained Mixed Effects Models: Formulations and Algorithms
Authors	Peng Zheng, Aleksandr Y. Aravkin, Ryan Barber, Reed J. D. Sorensen, Christopher J. L. Murray
Abstract	Mixed effects (ME) models inform a vast array of problems in the physical and social sciences, and are pervasive in meta-analysis. We consider ME models where the random effects component is linear. We then develop an efficient approach for a broad problem class that allows nonlinear measurements, priors, and constraints, and finds robust estimates in all of these cases using trimming in the associated marginal likelihood. We illustrate the efficacy of the approach on a range of applications for meta-analysis of global health data. Constraints and priors are used to impose monotonicity, convexity and other characteristics on dose-response relationships, while nonlinear observations enable new epidemiological analyses in place of approximations. Robust extensions ensure that spurious studies do not drive our understanding of between-study heterogeneity. The software accompanying this paper is disseminated as an open-source Python package called limeTR.
Tasks
Published	2019-09-24
URL	https://arxiv.org/abs/1909.10700v1
PDF	https://arxiv.org/pdf/1909.10700v1.pdf
PWC	https://paperswithcode.com/paper/trimmed-constrained-mixed-effects-models
Repo
Framework

NNE: A Dataset for Nested Named Entity Recognition in English Newswire


Title	NNE: A Dataset for Nested Named Entity Recognition in English Newswire
Authors	Nicky Ringland, Xiang Dai, Ben Hachey, Sarvnaz Karimi, Cecile Paris, James R. Curran
Abstract	Named entity recognition (NER) is widely used in natural language processing applications and downstream tasks. However, most NER tools target flat annotation from popular datasets, eschewing the semantic information available in nested entity mentions. We describe NNE—a fine-grained, nested named entity dataset over the full Wall Street Journal portion of the Penn Treebank (PTB). Our annotation comprises 279,795 mentions of 114 entity types with up to 6 layers of nesting. We hope the public release of this large dataset for English newswire will encourage development of new techniques for nested NER.
Tasks	Named Entity Recognition, Nested Named Entity Recognition
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01359v1
PDF	https://arxiv.org/pdf/1906.01359v1.pdf
PWC	https://paperswithcode.com/paper/nne-a-dataset-for-nested-named-entity
Repo
Framework

Quantum Computing based Hybrid Solution Strategies for Large-scale Discrete-Continuous Optimization Problems


Title	Quantum Computing based Hybrid Solution Strategies for Large-scale Discrete-Continuous Optimization Problems
Authors	Akshay Ajagekar, Travis Humble, Fengqi You
Abstract	Quantum computing (QC) has gained popularity due to its unique capabilities that are quite different from that of classical computers in terms of speed and methods of operations. This paper proposes hybrid models and methods that effectively leverage the complementary strengths of deterministic algorithms and QC techniques to overcome combinatorial complexity for solving large-scale mixed-integer programming problems. Four applications, namely the molecular conformation problem, job-shop scheduling problem, manufacturing cell formation problem, and the vehicle routing problem, are specifically addressed. Large-scale instances of these application problems across multiple scales ranging from molecular design to logistics optimization are computationally challenging for deterministic optimization algorithms on classical computers. To address the computational challenges, hybrid QC-based algorithms are proposed and extensive computational experimental results are presented to demonstrate their applicability and efficiency. The proposed QC-based solution strategies enjoy high computational efficiency in terms of solution quality and computation time, by utilizing the unique features of both classical and quantum computers.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13045v1
PDF	https://arxiv.org/pdf/1910.13045v1.pdf
PWC	https://paperswithcode.com/paper/quantum-computing-based-hybrid-solution
Repo
Framework

Minimal model of permutation symmetry in unsupervised learning


Title	Minimal model of permutation symmetry in unsupervised learning
Authors	Tianqi Hou, K. Y. Michael Wong, Haiping Huang
Abstract	Permutation of any two hidden units yields invariant properties in typical deep generative neural networks. This permutation symmetry plays an important role in understanding the computation performance of a broad class of neural networks with two or more hidden units. However, a theoretical study of the permutation symmetry is still lacking. Here, we propose a minimal model with only two hidden units in a restricted Boltzmann machine, which aims to address how the permutation symmetry affects the critical learning data size at which the concept-formation (or spontaneous symmetry breaking in physics language) starts, and moreover semi-rigorously prove a conjecture that the critical data size is independent of the number of hidden units once this number is finite. Remarkably, we find that the embedded correlation between two receptive fields of hidden units reduces the critical data size. In particular, the weakly-correlated receptive fields have the benefit of significantly reducing the minimal data size that triggers the transition, given less noisy data. Inspired by the theory, we also propose an efficient fully-distributed algorithm to infer the receptive fields of hidden units. Furthermore, our minimal model reveals that the permutation symmetry can also be spontaneously broken following the spontaneous symmetry breaking. Overall, our results demonstrate that the unsupervised learning is a progressive combination of spontaneous symmetry breaking and permutation symmetry breaking which are both spontaneous processes driven by data streams (observations). All these effects can be analytically probed based on the minimal model, providing theoretical insights towards understanding unsupervised learning in a more general context.
Tasks
Published	2019-04-30
URL	https://arxiv.org/abs/1904.13052v2
PDF	https://arxiv.org/pdf/1904.13052v2.pdf
PWC	https://paperswithcode.com/paper/minimal-model-of-permutation-symmetry-in
Repo
Framework

AntMan: Sparse Low-Rank Compression to Accelerate RNN inference


Title	AntMan: Sparse Low-Rank Compression to Accelerate RNN inference
Authors	Samyam Rajbhandari, Harsh Shrivastava, Yuxiong He
Abstract	Wide adoption of complex RNN based models is hindered by their inference performance, cost and memory requirements. To address this issue, we develop AntMan, combining structured sparsity with low-rank decomposition synergistically, to reduce model computation, size and execution time of RNNs while attaining desired accuracy. AntMan extends knowledge distillation based training to learn the compressed models efficiently. Our evaluation shows that AntMan offers up to 100x computation reduction with less than 1pt accuracy drop for language and machine reading comprehension models. Our evaluation also shows that for a given accuracy target, AntMan produces 5x smaller models than the state-of-art. Lastly, we show that AntMan offers super-linear speed gains compared to theoretical speedup, demonstrating its practical value on commodity hardware.
Tasks	Machine Reading Comprehension, Reading Comprehension
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01740v1
PDF	https://arxiv.org/pdf/1910.01740v1.pdf
PWC	https://paperswithcode.com/paper/antman-sparse-low-rank-compression-to-1
Repo
Framework

“President Vows to Cut Hair”: Dataset and Analysis of Creative Text Editing for Humorous Headlines


Title	“President Vows to Cut Hair”: Dataset and Analysis of Creative Text Editing for Humorous Headlines
Authors	Nabil Hossain, John Krumm, Michael Gamon
Abstract	We introduce, release, and analyze a new dataset, called Humicroedit, for research in computational humor. Our publicly available data consists of regular English news headlines paired with versions of the same headlines that contain simple replacement edits designed to make them funny. We carefully curated crowdsourced editors to create funny headlines and judges to score a to a total of 15,095 edited headlines, with five judges per headline. The simple edits, usually just a single word replacement, mean we can apply straightforward analysis techniques to determine what makes our edited headlines humorous. We show how the data support classic theories of humor, such as incongruity, superiority, and setup/punchline. Finally, we develop baseline classifiers that can predict whether or not an edited headline is funny, which is a first step toward automatically generating humorous headlines as an approach to creating topical humor.
Tasks
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00274v1
PDF	https://arxiv.org/pdf/1906.00274v1.pdf
PWC	https://paperswithcode.com/paper/190600274
Repo
Framework

Deep Learning Based Online Power Control for Large Energy Harvesting Networks


Title	Deep Learning Based Online Power Control for Large Energy Harvesting Networks
Authors	Mohit K Sharma, Alessio Zappone, Merouane Debbah, Mohamad Assaad
Abstract	In this paper, we propose a deep learning based approach to design online power control policies for large EH networks, which are often intractable stochastic control problems. In the proposed approach, for a given EH network, the optimal online power control rule is learned by training a deep neural network (DNN), using the solution of offline policy design problem. Under the proposed scheme, in a given time slot, the transmit power is obtained by feeding the current system state to the trained DNN. Our results illustrate that the DNN based online power control scheme outperforms a Markov decision process based policy. In general, the proposed deep learning based approach can be used to find solutions to large intractable stochastic control problems.
Tasks
Published	2019-03-08
URL	http://arxiv.org/abs/1903.03652v1
PDF	http://arxiv.org/pdf/1903.03652v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-online-power-control-for
Repo
Framework

Biomedical Named Entity Recognition via Reference-Set Augmented Bootstrapping


Title	Biomedical Named Entity Recognition via Reference-Set Augmented Bootstrapping
Authors	Joel Mathew, Shobeir Fakhraei, José Luis Ambite
Abstract	We present a weakly-supervised data augmentation approach to improve Named Entity Recognition (NER) in a challenging domain: extracting biomedical entities (e.g., proteins) from the scientific literature. First, we train a neural NER (NNER) model over a small seed of fully-labeled examples. Second, we use a reference set of entity names (e.g., proteins in UniProt) to identify entity mentions with high precision, but low recall, on an unlabeled corpus. Third, we use the NNER model to assign weak labels to the corpus. Finally, we retrain our NNER model iteratively over the augmented training set, including the seed, the reference-set examples, and the weakly-labeled examples, which improves model performance. We show empirically that this augmented bootstrapping process significantly improves NER performance, and discuss the factors impacting the efficacy of the approach.
Tasks	Data Augmentation, Named Entity Recognition
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00282v1
PDF	https://arxiv.org/pdf/1906.00282v1.pdf
PWC	https://paperswithcode.com/paper/190600282
Repo
Framework

Classification of Perceived Human Stress using Physiological Signals


Title	Classification of Perceived Human Stress using Physiological Signals
Authors	Aamir Arsalan, Muhammad Majid, Syed Muhammad Anwar, Ulas Bagci
Abstract	In this paper, we present an experimental study for the classification of perceived human stress using non-invasive physiological signals. These include electroencephalography (EEG), galvanic skin response (GSR), and photoplethysmography (PPG). We conducted experiments consisting of steps including data acquisition, feature extraction, and perceived human stress classification. The physiological data of $28$ participants are acquired in an open eye condition for a duration of three minutes. Four different features are extracted in time domain from EEG, GSR and PPG signals and classification is performed using multiple classifiers including support vector machine, the Naive Bayes, and multi-layer perceptron (MLP). The best classification accuracy of 75% is achieved by using MLP classifier. Our experimental results have shown that our proposed scheme outperforms existing perceived stress classification methods, where no stress inducers are used.
Tasks	EEG, Photoplethysmography (PPG)
Published	2019-05-13
URL	https://arxiv.org/abs/1905.06384v1
PDF	https://arxiv.org/pdf/1905.06384v1.pdf
PWC	https://paperswithcode.com/paper/classification-of-perceived-human-stress
Repo
Framework

ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal


Title	ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
Authors	Bin Ding, Chengjiang Long, Ling Zhang, Chunxia Xiao
Abstract	In this paper we propose an attentive recurrent generative adversarial network (ARGAN) to detect and remove shadows in an image. The generator consists of multiple progressive steps. At each step a shadow attention detector is firstly exploited to generate an attention map which specifies shadow regions in the input image.Given the attention map, a negative residual by a shadow remover encoder will recover a shadow-lighter or even a shadow-free image. A discriminator is designed to classify whether the output image in the last progressive step is real or fake. Moreover, ARGAN is suitable to be trained with a semi-supervised strategy to make full use of sufficient unsupervised data. The experiments on four public datasets have demonstrated that our ARGAN is robust to detect both simple and complex shadows and to produce more realistic shadow removal results. It outperforms the state-of-the-art methods, especially in detail of recovering shadow areas.
Tasks	Shadow Detection, Shadow Detection And Removal
Published	2019-08-04
URL	https://arxiv.org/abs/1908.01323v1
PDF	https://arxiv.org/pdf/1908.01323v1.pdf
PWC	https://paperswithcode.com/paper/argan-attentive-recurrent-generative
Repo
Framework

Automatically Batching Control-Intensive Programs for Modern Accelerators


Title	Automatically Batching Control-Intensive Programs for Modern Accelerators
Authors	Alexey Radul, Brian Patton, Dougal Maclaurin, Matthew D. Hoffman, Rif A. Saurous
Abstract	We present a general approach to batching arbitrary computations for accelerators such as GPUs. We show orders-of-magnitude speedups using our method on the No U-Turn Sampler (NUTS), a workhorse algorithm in Bayesian statistics. The central challenge of batching NUTS and other Markov chain Monte Carlo algorithms is data-dependent control flow and recursion. We overcome this by mechanically transforming a single-example implementation into a form that explicitly tracks the current program point for each batch member, and only steps forward those in the same place. We present two different batching algorithms: a simpler, previously published one that inherits recursion from the host Python, and a more complex, novel one that implemenents recursion directly and can batch across it. We implement these batching methods as a general program transformation on Python source. Both the batching system and the NUTS implementation presented here are available as part of the popular TensorFlow Probability software package.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.11141v2
PDF	https://arxiv.org/pdf/1910.11141v2.pdf
PWC	https://paperswithcode.com/paper/automatically-batching-control-intensive
Repo
Framework

InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers


Title	InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers
Authors	Tan M. Nguyen, Animesh Garg, Richard G. Baraniuk, Anima Anandkumar
Abstract	Continuous Normalizing Flows (CNFs) have emerged as promising deep generative models for a wide range of tasks thanks to their invertibility and exact likelihood estimation. However, conditioning CNFs on signals of interest for conditional image generation and downstream predictive tasks is inefficient due to the high-dimensional latent code generated by the model, which needs to be of the same size as the input data. In this paper, we propose InfoCNF, an efficient conditional CNF that partitions the latent space into a class-specific supervised code and an unsupervised code that shared among all classes for efficient use of labeled information. Since the partitioning strategy (slightly) increases the number of function evaluations (NFEs), InfoCNF also employs gating networks to learn the error tolerances of its ordinary differential equation (ODE) solvers for better speed and performance. We show empirically that InfoCNF improves the test accuracy over the baseline while yielding comparable likelihood scores and reducing the NFEs on CIFAR10. Furthermore, applying the same partitioning strategy in InfoCNF on time-series data helps improve extrapolation performance.
Tasks	Conditional Image Generation, Image Generation, Time Series
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03978v1
PDF	https://arxiv.org/pdf/1912.03978v1.pdf
PWC	https://paperswithcode.com/paper/infocnf-an-efficient-conditional-continuous
Repo
Framework

Quantifying Confounding Bias in Neuroimaging Datasets with Causal Inference


Title	Quantifying Confounding Bias in Neuroimaging Datasets with Causal Inference
Authors	Christian Wachinger, Benjamin Gutierrez Becker, Anna Rieckmann, Sebastian Pölsterl
Abstract	Neuroimaging datasets keep growing in size to address increasingly complex medical questions. However, even the largest datasets today alone are too small for training complex machine learning models. A potential solution is to increase sample size by pooling scans from several datasets. In this work, we combine 12,207 MRI scans from 15 studies and show that simple pooling is often ill-advised due to introducing various types of biases in the training data. First, we systematically define these biases. Second, we detect bias by experimentally showing that scans can be correctly assigned to their respective dataset with 73.3% accuracy. Finally, we propose to tell causal from confounding factors by quantifying the extent of confounding and causality in a single dataset using causal inference. We achieve this by finding the simplest graphical model in terms of Kolmogorov complexity. As Kolmogorov complexity is not directly computable, we employ the minimum description length to approximate it. We empirically show that our approach is able to estimate plausible causal relationships from real neuroimaging data.
Tasks	Causal Inference
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04102v1
PDF	https://arxiv.org/pdf/1907.04102v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-confounding-bias-in-neuroimaging
Repo
Framework

Deep Learning for Bridge Load Capacity Estimation in Post-Disaster and -Conflict Zones


Title	Deep Learning for Bridge Load Capacity Estimation in Post-Disaster and -Conflict Zones
Authors	Arya Pamuncak, Weisi Guo, Ahmed Soliman Khaled, Irwanda Laory
Abstract	Many post-disaster and -conflict regions do not have sufficient data on their transportation infrastructure assets, hindering both mobility and reconstruction. In particular, as the number of aging and deteriorating bridges increase, it is necessary to quantify their load characteristics in order to inform maintenance and prevent failure. The load carrying capacity and the design load are considered as the main aspects of any civil structures. Human examination can be costly and slow when expertise is lacking in challenging scenarios. In this paper, we propose to employ deep learning as method to estimate the load carrying capacity from crowd sourced images. A new convolutional neural network architecture is trained on data from over 6000 bridges, which will benefit future research and applications. We tackle significant variations in the dataset (e.g. class interval, image completion, image colour) and quantify their impact on the prediction accuracy, precision, recall and F1 score. Finally, practical optimisation is performed by converting multiclass classification into binary classification to achieve a promising field use performance.
Tasks
Published	2019-02-05
URL	http://arxiv.org/abs/1902.05391v1
PDF	http://arxiv.org/pdf/1902.05391v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-bridge-load-capacity
Repo
Framework