Paper Group ANR 360
A Rule for Committee Selection with Soft Diversity Constraints. Internal Model from Observations for Reward Shaping. Application of a semantic segmentation convolutional neural network for accurate automatic detection and mapping of solar photovoltaic arrays in aerial imagery. Clause Vivification by Unit Propagation in CDCL SAT Solvers. Quantitativ …
A Rule for Committee Selection with Soft Diversity Constraints
| Title | A Rule for Committee Selection with Soft Diversity Constraints |
| Authors | Haris Aziz |
| Abstract | Committee selection with diversity or distributional constraints is a ubiquitous problem. However, many of the formal approaches proposed so far have certain drawbacks including (1) computationally intractability in general, and (2) inability to suggest a solution for certain instances where the hard constraints cannot be met. We propose a practical and polynomial-time algorithm for diverse committee selection that draws on the idea of using soft bounds and satisfies natural axioms. |
| Tasks | |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11437v1 |
| http://arxiv.org/pdf/1803.11437v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-rule-for-committee-selection-with-soft |
| Repo | |
| Framework | |
Internal Model from Observations for Reward Shaping
| Title | Internal Model from Observations for Reward Shaping |
| Authors | Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana, Sakyasingha Dasgupta |
| Abstract | Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several methods for reward estimation by using expert state trajectories and action pairs. However, there are cases where complete or good action information cannot be obtained from expert demonstrations. We propose a novel reinforcement learning method in which the agent learns an internal model of observation on the basis of expert-demonstrated state trajectories to estimate rewards without completely learning the dynamics of the external environment from state-action pairs. The internal model is obtained in the form of a predictive model for the given expert state distribution. During reinforcement learning, the agent predicts the reward as a function of the difference between the actual state and the state predicted by the internal model. We conducted multiple experiments in environments of varying complexity, including the Super Mario Bros and Flappy Bird games. We show our method successfully trains good policies directly from expert game-play videos. |
| Tasks | |
| Published | 2018-06-02 |
| URL | http://arxiv.org/abs/1806.01267v4 |
| http://arxiv.org/pdf/1806.01267v4.pdf | |
| PWC | https://paperswithcode.com/paper/internal-model-from-observations-for-reward |
| Repo | |
| Framework | |
Application of a semantic segmentation convolutional neural network for accurate automatic detection and mapping of solar photovoltaic arrays in aerial imagery
| Title | Application of a semantic segmentation convolutional neural network for accurate automatic detection and mapping of solar photovoltaic arrays in aerial imagery |
| Authors | Joseph Camilo, Rui Wang, Leslie M. Collins, Kyle Bradbury, Jordan M. Malof |
| Abstract | We consider the problem of automatically detecting small-scale solar photovoltaic arrays for behind-the-meter energy resource assessment in high resolution aerial imagery. Such algorithms offer a faster and more cost-effective solution to collecting information on distributed solar photovoltaic (PV) arrays, such as their location, capacity, and generated energy. The surface area of PV arrays, a characteristic which can be estimated from aerial imagery, provides an important proxy for array capacity and energy generation. In this work, we employ a state-of-the-art convolutional neural network architecture, called SegNet (Badrinarayanan et. al., 2015), to semantically segment (or map) PV arrays in aerial imagery. This builds on previous work focused on identifying the locations of PV arrays, as opposed to their specific shapes and sizes. We measure the ability of our SegNet implementation to estimate the surface area of PV arrays on a large, publicly available, dataset that has been employed in several previous studies. The results indicate that the SegNet model yields substantial performance improvements with respect to estimating shape and size as compared to a recently proposed convolutional neural network PV detection algorithm. |
| Tasks | Semantic Segmentation |
| Published | 2018-01-11 |
| URL | http://arxiv.org/abs/1801.04018v1 |
| http://arxiv.org/pdf/1801.04018v1.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-a-semantic-segmentation |
| Repo | |
| Framework | |
Clause Vivification by Unit Propagation in CDCL SAT Solvers
| Title | Clause Vivification by Unit Propagation in CDCL SAT Solvers |
| Authors | Chu-Min Li, Fan Xiao, Mao Luo, Felip Manyà, Zhipeng Lü, Yu Li |
| Abstract | Original and learnt clauses in Conflict-Driven Clause Learning (CDCL) SAT solvers often contain redundant literals. This may have a negative impact on performance because redundant literals may deteriorate both the effectiveness of Boolean constraint propagation and the quality of subsequent learnt clauses. To overcome this drawback, we propose a clause vivification approach that eliminates redundant literals by applying unit propagation. The proposed clause vivification is activated before the SAT solver triggers some selected restarts, and only affects a subset of original and learnt clauses, which are considered to be more relevant according to metrics like the literal block distance (LBD). Moreover, we conducted an empirical investigation with instances coming from the hard combinatorial and application categories of recent SAT competitions. The results show that a remarkable number of additional instances are solved when the proposed approach is incorporated into five of the best performing CDCL SAT solvers (Glucose, TC_Glucose, COMiniSatPS, MapleCOMSPS and MapleCOMSPS_LRB). More importantly, the empirical investigation includes an in-depth analysis of the effectiveness of clause vivification. It is worth mentioning that one of the SAT solvers described here was ranked first in the main track of SAT Competition 2017 thanks to the incorporation of the proposed clause vivification. That solver was further improved in this paper and won the bronze medal in the main track of SAT Competition 2018. |
| Tasks | |
| Published | 2018-07-29 |
| URL | http://arxiv.org/abs/1807.11061v1 |
| http://arxiv.org/pdf/1807.11061v1.pdf | |
| PWC | https://paperswithcode.com/paper/clause-vivification-by-unit-propagation-in |
| Repo | |
| Framework | |
Quantitatively Evaluating GANs With Divergences Proposed for Training
| Title | Quantitatively Evaluating GANs With Divergences Proposed for Training |
| Authors | Daniel Jiwoong Im, He Ma, Graham Taylor, Kristin Branson |
| Abstract | Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in terms of both theory and application. However, we currently lack quantitative methods for model assessment. Because of this, while many GAN variants are being proposed, we have relatively little understanding of their relative abilities. In this paper, we evaluate the performance of various types of GANs using divergence and distance functions typically used only for training. We observe consistency across the various proposed metrics and, interestingly, the test-time metrics do not favour networks that use the same training-time criterion. We also compare the proposed metrics to human perceptual scores. |
| Tasks | |
| Published | 2018-03-02 |
| URL | http://arxiv.org/abs/1803.01045v2 |
| http://arxiv.org/pdf/1803.01045v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantitatively-evaluating-gans-with |
| Repo | |
| Framework | |
RetGK: Graph Kernels based on Return Probabilities of Random Walks
| Title | RetGK: Graph Kernels based on Return Probabilities of Random Walks |
| Authors | Zhen Zhang, Mianzhi Wang, Yijian Xiang, Yan Huang, Arye Nehorai |
| Abstract | Graph-structured data arise in wide applications, such as computer vision, bioinformatics, and social networks. Quantifying similarities among graphs is a fundamental problem. In this paper, we develop a framework for computing graph kernels, based on return probabilities of random walks. The advantages of our proposed kernels are that they can effectively exploit various node attributes, while being scalable to large datasets. We conduct extensive graph classification experiments to evaluate our graph kernels. The experimental results show that our graph kernels significantly outperform existing state-of-the-art approaches in both accuracy and computational efficiency. |
| Tasks | Graph Classification |
| Published | 2018-09-07 |
| URL | http://arxiv.org/abs/1809.02670v1 |
| http://arxiv.org/pdf/1809.02670v1.pdf | |
| PWC | https://paperswithcode.com/paper/retgk-graph-kernels-based-on-return |
| Repo | |
| Framework | |
Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames
| Title | Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames |
| Authors | Geneviève Robin, Hoi-To Wai, Julie Josse, Olga Klopp, Éric Moulines |
| Abstract | Many applications of machine learning involve the analysis of large data frames-matrices collecting heterogeneous measurements (binary, numerical, counts, etc.) across samples-with missing values. Low-rank models, as studied by Udell et al. [30], are popular in this framework for tasks such as visualization, clustering and missing value imputation. Yet, available methods with statistical guarantees and efficient optimization do not allow explicit modeling of main additive effects such as row and column, or covariate effects. In this paper, we introduce a low-rank interaction and sparse additive effects (LORIS) model which combines matrix regression on a dictionary and low-rank design, to estimate main effects and interactions simultaneously. We provide statistical guarantees in the form of upper bounds on the estimation error of both components. Then, we introduce a mixed coordinate gradient descent (MCGD) method which provably converges sub-linearly to an optimal solution and is computationally efficient for large scale data sets. We show on simulated and survey data that the method has a clear advantage over current practices, which consist in dealing separately with additive effects in a preprocessing step. |
| Tasks | Imputation |
| Published | 2018-12-20 |
| URL | http://arxiv.org/abs/1812.08398v1 |
| http://arxiv.org/pdf/1812.08398v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-rank-interaction-with-sparse-additive |
| Repo | |
| Framework | |
Imputation of Clinical Covariates in Time Series
| Title | Imputation of Clinical Covariates in Time Series |
| Authors | Dimitris Bertsimas, Agni Orfanoudaki, Colin Pawlowski |
| Abstract | Missing data is a common problem in real-world settings and particularly relevant in healthcare applications where researchers use Electronic Health Records (EHR) and results of observational studies to apply analytics methods. This issue becomes even more prominent for longitudinal data sets, where multiple instances of the same individual correspond to different observations in time. Standard imputation methods do not take into account patient specific information incorporated in multivariate panel data. We introduce the novel imputation algorithm MedImpute that addresses this problem, extending the flexible framework of OptImpute suggested by Bertsimas et al. (2018). Our algorithm provides imputations for data sets with missing continuous and categorical features, and we present the formulation and implement scalable first-order methods for a $K$-NN model. We test the performance of our algorithm on longitudinal data from the Framingham Heart Study when data are missing completely at random (MCAR). We demonstrate that MedImpute leads to significant improvements in both imputation accuracy and downstream model AUC compared to state-of-the-art methods. |
| Tasks | Imputation, Time Series |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00418v1 |
| http://arxiv.org/pdf/1812.00418v1.pdf | |
| PWC | https://paperswithcode.com/paper/imputation-of-clinical-covariates-in-time |
| Repo | |
| Framework | |
Biomedical term normalization of EHRs with UMLS
| Title | Biomedical term normalization of EHRs with UMLS |
| Authors | Naiara Perez, Montse Cuadros, German Rigau |
| Abstract | This paper presents a novel prototype for biomedical term normalization of electronic health record excerpts with the Unified Medical Language System (UMLS) Metathesaurus. Despite being multilingual and cross-lingual by design, we first focus on processing clinical text in Spanish because there is no existing tool for this language and for this specific purpose. The tool is based on Apache Lucene to index the Metathesaurus and generate mapping candidates from input text. It uses the IXA pipeline for basic language processing and resolves ambiguities with the UKB toolkit. It has been evaluated by measuring its agreement with MetaMap in two English-Spanish parallel corpora. In addition, we present a web-based interface for the tool. |
| Tasks | |
| Published | 2018-02-08 |
| URL | http://arxiv.org/abs/1802.02870v2 |
| http://arxiv.org/pdf/1802.02870v2.pdf | |
| PWC | https://paperswithcode.com/paper/biomedical-term-normalization-of-ehrs-with |
| Repo | |
| Framework | |
Leveraging Deep Stein’s Unbiased Risk Estimator for Unsupervised X-ray Denoising
| Title | Leveraging Deep Stein’s Unbiased Risk Estimator for Unsupervised X-ray Denoising |
| Authors | Fahad Shamshad, Muhammad Awais, Muhammad Asim, Zain ul Aabidin Lodhi, Muhammad Umair, Ali Ahmed |
| Abstract | Among the plethora of techniques devised to curb the prevalence of noise in medical images, deep learning based approaches have shown the most promise. However, one critical limitation of these deep learning based denoisers is the requirement of high-quality noiseless ground truth images that are difficult to obtain in many medical imaging applications such as X-rays. To circumvent this issue, we leverage recently proposed approach of [7] that incorporates Stein’s Unbiased Risk Estimator (SURE) to train a deep convolutional neural network without requiring denoised ground truth X-ray data. Our experimental results demonstrate the effectiveness of SURE based approach for denoising X-ray images. |
| Tasks | Denoising |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.12488v1 |
| http://arxiv.org/pdf/1811.12488v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-deep-steins-unbiased-risk |
| Repo | |
| Framework | |
On a ‘Two Truths’ Phenomenon in Spectral Graph Clustering
| Title | On a ‘Two Truths’ Phenomenon in Spectral Graph Clustering |
| Authors | Carey E. Priebe, Youngser Park, Joshua T. Vogelstein, John M. Conroy, Vince Lyzinski, Minh Tang, Avanti Athreya, Joshua Cape, Eric Bridgeford |
| Abstract | Clustering is concerned with coherently grouping observations without any explicit concept of true groupings. Spectral graph clustering - clustering the vertices of a graph based on their spectral embedding - is commonly approached via K-means (or, more generally, Gaussian mixture model) clustering composed with either Laplacian or Adjacency spectral embedding (LSE or ASE). Recent theoretical results provide new understanding of the problem and solutions, and lead us to a ‘Two Truths’ LSE vs. ASE spectral graph clustering phenomenon convincingly illustrated here via a diffusion MRI connectome data set: the different embedding methods yield different clustering results, with LSE capturing left hemisphere/right hemisphere affinity structure and ASE capturing gray matter/white matter core-periphery structure. |
| Tasks | Graph Clustering, Spectral Graph Clustering |
| Published | 2018-08-23 |
| URL | http://arxiv.org/abs/1808.07801v3 |
| http://arxiv.org/pdf/1808.07801v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-a-two-truths-phenomenon-in-spectral-graph |
| Repo | |
| Framework | |
Prediction and Localization of Student Engagement in the Wild
| Title | Prediction and Localization of Student Engagement in the Wild |
| Authors | Amanjot Kaur, Aamir Mustafa, Love Mehta, Abhinav Dhall |
| Abstract | In this paper, we introduce a new dataset for student engagement detection and localization. Digital revolution has transformed the traditional teaching procedure and a result analysis of the student engagement in an e-learning environment would facilitate effective task accomplishment and learning. Well known social cues of engagement/disengagement can be inferred from facial expressions, body movements and gaze pattern. In this paper, student’s response to various stimuli videos are recorded and important cues are extracted to estimate variations in engagement level. In this paper, we study the association of a subject’s behavioral cues with his/her engagement level, as annotated by labelers. We then localize engaging/non-engaging parts in the stimuli videos using a deep multiple instance learning based framework, which can give useful insight into designing Massive Open Online Courses (MOOCs) video material. Recognizing the lack of any publicly available dataset in the domain of user engagement, a new `in the wild’ dataset is created to study the subject engagement problem. The dataset contains 195 videos captured from 78 subjects which is about 16.5 hours of recording. We present detailed baseline results using different classifiers ranging from traditional machine learning to deep learning based approaches. The subject independent analysis is performed so that it can be generalized to new users. The problem of engagement prediction is modeled as a weakly supervised learning problem. The dataset is manually annotated by different labelers for four levels of engagement independently and the correlation studies between annotated and predicted labels of videos by different classifiers is reported. This dataset creation is an effort to facilitate research in various e-learning environments such as intelligent tutoring systems, MOOCs, and others. | |
| Tasks | Multiple Instance Learning |
| Published | 2018-04-03 |
| URL | http://arxiv.org/abs/1804.00858v4 |
| http://arxiv.org/pdf/1804.00858v4.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-and-localization-of-student |
| Repo | |
| Framework | |
Deep Chronnectome Learning via Full Bidirectional Long Short-Term Memory Networks for MCI Diagnosis
| Title | Deep Chronnectome Learning via Full Bidirectional Long Short-Term Memory Networks for MCI Diagnosis |
| Authors | Weizheng Yan, Han Zhang, Jing Sui, Dinggang Shen |
| Abstract | Brain functional connectivity (FC) extracted from resting-state fMRI (RS-fMRI) has become a popular approach for disease diagnosis, where discriminating subjects with mild cognitive impairment (MCI) from normal controls (NC) is still one of the most challenging problems. Dynamic functional connectivity (dFC), consisting of time-varying spatiotemporal dynamics, may characterize “chronnectome” diagnostic information for improving MCI classification. However, most of the current dFC studies are based on detecting discrete major brain status via spatial clustering, which ignores rich spatiotemporal dynamics contained in such chronnectome. We propose Deep Chronnectome Learning for exhaustively mining the comprehensive information, especially the hidden higher-level features, i.e., the dFC time series that may add critical diagnostic power for MCI classification. To this end, we devise a new Fully-connected Bidirectional Long Short-Term Memory Network (Full-BiLSTM) to effectively learn the periodic brain status changes using both past and future information for each brief time segment and then fuse them to form the final output. We have applied our method to a rigorously built large-scale multi-site database (i.e., with 164 data from NCs and 330 from MCIs, which can be further augmented by 25 folds). Our method outperforms other state-of-the-art approaches with an accuracy of 73.6% under solid cross-validations. We also made extensive comparisons among multiple variants of LSTM models. The results suggest high feasibility of our method with promising value also for other brain disorder diagnoses. |
| Tasks | Time Series |
| Published | 2018-08-30 |
| URL | http://arxiv.org/abs/1808.10383v1 |
| http://arxiv.org/pdf/1808.10383v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-chronnectome-learning-via-full |
| Repo | |
| Framework | |
A probabilistic incremental proximal gradient method
| Title | A probabilistic incremental proximal gradient method |
| Authors | Ömer Deniz Akyildiz, Émilie Chouzenoux, Víctor Elvira, Joaquín Míguez |
| Abstract | In this paper, we propose a probabilistic optimization method, named probabilistic incremental proximal gradient (PIPG) method, by developing a probabilistic interpretation of the incremental proximal gradient algorithm. We explicitly model the update rules of the incremental proximal gradient method and develop a systematic approach to propagate the uncertainty of the solution estimate over iterations. The PIPG algorithm takes the form of Bayesian filtering updates for a state-space model constructed by using the cost function. Our framework makes it possible to utilize well-known exact or approximate Bayesian filters, such as Kalman or extended Kalman filters, to solve large-scale regularized optimization problems. |
| Tasks | |
| Published | 2018-12-04 |
| URL | https://arxiv.org/abs/1812.01655v5 |
| https://arxiv.org/pdf/1812.01655v5.pdf | |
| PWC | https://paperswithcode.com/paper/a-probabilistic-incremental-proximal-gradient |
| Repo | |
| Framework | |
ShuffleNASNets: Efficient CNN models through modified Efficient Neural Architecture Search
| Title | ShuffleNASNets: Efficient CNN models through modified Efficient Neural Architecture Search |
| Authors | Kevin Alexander Laube, Andreas Zell |
| Abstract | Neural network architectures found by sophistic search algorithms achieve strikingly good test performance, surpassing most human-crafted network models by significant margins. Although computationally efficient, their design is often very complex, impairing execution speed. Additionally, finding models outside of the search space is not possible by design. While our space is still limited, we implement undiscoverable expert knowledge into the economic search algorithm Efficient Neural Architecture Search (ENAS), guided by the design principles and architecture of ShuffleNet V2. While maintaining baseline-like 2.85% test error on CIFAR-10, our ShuffleNASNets are significantly less complex, require fewer parameters, and are two times faster than the ENAS baseline in a classification task. These models also scale well to a low parameter space, achieving less than 5% test error with little regularization and only 236K parameters. |
| Tasks | Neural Architecture Search |
| Published | 2018-12-07 |
| URL | http://arxiv.org/abs/1812.02975v1 |
| http://arxiv.org/pdf/1812.02975v1.pdf | |
| PWC | https://paperswithcode.com/paper/shufflenasnets-efficient-cnn-models-through |
| Repo | |
| Framework | |
