Paper Group ANR 99
ParkingSticker: A Real-World Object Detection Dataset. Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Discrete Distributions. ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation. Learning Global Transparent Models from Local Contrastive Explanations. A fast and …
ParkingSticker: A Real-World Object Detection Dataset
| Title | ParkingSticker: A Real-World Object Detection Dataset |
| Authors | Caroline Potts, Ethem F. Can, Aysu Ezen-Can, Xiangqian Hu |
| Abstract | We present a new and challenging object detection dataset, ParkingSticker, which mimics the type of data available in industry problems more closely than popular existing datasets like PASCAL VOC. ParkingSticker contains 1,871 images that come from a security camera’s video footage. The objective is to identify parking stickers on cars approaching a gate that the security camera faces. Bounding boxes are drawn around parking stickers in the images. The parking stickers are much smaller on average than the objects in other popular object detection datasets; this makes ParkingSticker a challenging test for object detection methods. This dataset also very realistically represents the data available in many industry problems where a customer presents a few video frames and asks for a solution to a very difficult problem. Performance of various object detection pipelines using a YOLOv2 architecture are presented and indicate that identifying the parking stickers in ParkingSticker is challenging yet feasible. We believe that this dataset will challenge researchers to solve a real-world problem with real-world constraints such as non-ideal camera positioning and small object-size-to-image-size ratios. |
| Tasks | Object Detection |
| Published | 2020-01-31 |
| URL | https://arxiv.org/abs/2001.11639v2 |
| https://arxiv.org/pdf/2001.11639v2.pdf | |
| PWC | https://paperswithcode.com/paper/parkingsticker-a-real-world-object-detection |
| Repo | |
| Framework | |
Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Discrete Distributions
| Title | Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Discrete Distributions |
| Authors | Yi Hao, Alon Orlitsky |
| Abstract | The profile of a sample is the multiset of its symbol frequencies. We show that for samples of discrete distributions, profile entropy is a fundamental measure unifying the concepts of estimation, inference, and compression. Specifically, profile entropy a) determines the speed of estimating the distribution relative to the best natural estimator; b) characterizes the rate of inferring all symmetric properties compared with the best estimator over any label-invariant distribution collection; c) serves as the limit of profile compression, for which we derive optimal near-linear-time block and sequential algorithms. To further our understanding of profile entropy, we investigate its attributes, provide algorithms for approximating its value, and determine its magnitude for numerous structural distribution families. |
| Tasks | |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11665v1 |
| https://arxiv.org/pdf/2002.11665v1.pdf | |
| PWC | https://paperswithcode.com/paper/profile-entropy-a-fundamental-measure-for-the |
| Repo | |
| Framework | |
ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation
| Title | ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation |
| Authors | Dongling Xiao, Han Zhang, Yukun Li, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang |
| Abstract | Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning framework named ERNIE-GEN, which bridges the discrepancy between training and inference with an infilling generation mechanism and a noise-aware generation method. To make generation closer to human writing patterns, this framework introduces a span-by-span generation flow that trains the model to predict semantically-complete spans consecutively rather than predicting word by word. Unlike existing pre-training methods, ERNIE-GEN incorporates multi-granularity target sampling to construct pre-training data, which enhances the correlation between encoder and decoder. Experimental results demonstrate that ERNIE-GEN achieves state-of-the-art results with a much smaller amount of pre-training data and parameters on a range of language generation tasks, including abstractive summarization (Gigaword and CNN/DailyMail), question generation (SQuAD), dialogue generation (Persona-Chat) and generative question answering (CoQA). |
| Tasks | Abstractive Text Summarization, Dialogue Generation, Question Answering, Question Generation, Text Generation |
| Published | 2020-01-26 |
| URL | https://arxiv.org/abs/2001.11314v2 |
| https://arxiv.org/pdf/2001.11314v2.pdf | |
| PWC | https://paperswithcode.com/paper/ernie-gen-an-enhanced-multi-flow-pre-training |
| Repo | |
| Framework | |
Learning Global Transparent Models from Local Contrastive Explanations
| Title | Learning Global Transparent Models from Local Contrastive Explanations |
| Authors | Tejaswini Pedapati, Avinash Balakrishnan, Karthikeyan Shanmugam, Amit Dhurandhar |
| Abstract | There is a rich and growing literature on producing local point wise contrastive/counterfactual explanations for complex models. These methods highlight what is important to justify the classification and/or produce a contrast point that alters the final classification. Other works try to build globally interpretable models like decision trees and rule lists directly by efficient model search using the data or by transferring information from a complex model using distillation-like methods. Although these interpretable global models can be useful, they may not be consistent with local explanations from a specific complex model of choice. In this work, we explore the question: Can we produce a transparent global model that is consistent with/derivable from local explanations? Based on a key insight we provide a novel method where every local contrastive/counterfactual explanation can be turned into a Boolean feature. These Boolean features are sparse conjunctions of binarized features. The dataset thus constructed is consistent with local explanations by design and one can train an interpretable model like a decision tree on it. We note that this approach strictly loses information due to reliance only on sparse local explanations, nonetheless, we demonstrate empirically that in many cases it can still be competitive with respect to the complex model’s performance and also other methods that learn directly from the original dataset. Our approach also provides an avenue to benchmark local explanation methods in a quantitative manner. |
| Tasks | |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08247v1 |
| https://arxiv.org/pdf/2002.08247v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-global-transparent-models-from-local |
| Repo | |
| Framework | |
A fast and efficient Modal EM algorithm for Gaussian mixtures
| Title | A fast and efficient Modal EM algorithm for Gaussian mixtures |
| Authors | Luca Scrucca |
| Abstract | In the modal approach to clustering, clusters are defined as the local maxima of the underlying probability density function, where the latter can be estimated either non-parametrically or using finite mixture models. Thus, clusters are closely related to certain regions around the density modes, and every cluster corresponds to a bump of the density. The Modal EM algorithm is an iterative procedure that can identify the local maxima of any density function. In this contribution, we propose a fast and efficient Modal EM algorithm to be used when the density function is estimated through a finite mixture of Gaussian distributions with parsimonious component-covariance structures. After describing the procedure, we apply the proposed Modal EM algorithm on both simulated and real data examples, showing its high flexibility in several contexts. |
| Tasks | |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.03600v1 |
| https://arxiv.org/pdf/2002.03600v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fast-and-efficient-modal-em-algorithm-for |
| Repo | |
| Framework | |
Model Selection in Contextual Stochastic Bandit Problems
| Title | Model Selection in Contextual Stochastic Bandit Problems |
| Authors | Aldo Pacchiano, My Phan, Yasin Abbasi-Yadkori, Anup Rao, Julian Zimmert, Tor Lattimore, Csaba Szepesvari |
| Abstract | We study model selection in stochastic bandit problems. Our approach relies on a master algorithm that selects its actions among candidate base algorithms. While this problem is studied for specific classes of stochastic base algorithms, our objective is to provide a method that can work with more general classes of stochastic base algorithms. We propose a master algorithm inspired by CORRAL \cite{DBLP:conf/colt/AgarwalLNS17} and introduce a novel and generic smoothing transformation for stochastic bandit algorithms that permits us to obtain $O(\sqrt{T})$ regret guarantees for a wide class of base algorithms when working along with our master. We exhibit a lower bound showing that even when one of the base algorithms has $O(\log T)$ regret, in general it is impossible to get better than $\Omega(\sqrt{T})$ regret in model selection, even asymptotically. We apply our algorithm to choose among different values of $\epsilon$ for the $\epsilon$-greedy algorithm, and to choose between the $k$-armed UCB and linear UCB algorithms. Our empirical studies further confirm the effectiveness of our model-selection method. |
| Tasks | Model Selection |
| Published | 2020-03-03 |
| URL | https://arxiv.org/abs/2003.01704v1 |
| https://arxiv.org/pdf/2003.01704v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-selection-in-contextual-stochastic |
| Repo | |
| Framework | |
Assessment of Amazon Comprehend Medical: Medication Information Extraction
| Title | Assessment of Amazon Comprehend Medical: Medication Information Extraction |
| Authors | Benedict Guzman, MS, Isabel Metzger, MS, Yindalon Aphinyanaphongs, M. D., Ph. D., Himanshu Grover, Ph. D |
| Abstract | In November 27, 2018, Amazon Web Services (AWS) released Amazon Comprehend Medical (ACM), a deep learning based system that automatically extracts clinical concepts (which include anatomy, medical conditions, protected health information (PH)I, test names, treatment names, and medical procedures, and medications) from clinical text notes. Uptake and trust in any new data product relies on independent validation across benchmark datasets and tools to establish and confirm expected quality of results. This work focuses on the medication extraction task, and particularly, ACM was evaluated using the official test sets from the 2009 i2b2 Medication Extraction Challenge and 2018 n2c2 Track 2: Adverse Drug Events and Medication Extraction in EHRs. Overall, ACM achieved F-scores of 0.768 and 0.828. These scores ranked the lowest when compared to the three best systems in the respective challenges. To further establish the generalizability of its medication extraction performance, a set of random internal clinical text notes from NYU Langone Medical Center were also included in this work. And in this corpus, ACM garnered an F-score of 0.753. |
| Tasks | |
| Published | 2020-02-02 |
| URL | https://arxiv.org/abs/2002.00481v1 |
| https://arxiv.org/pdf/2002.00481v1.pdf | |
| PWC | https://paperswithcode.com/paper/assessment-of-amazon-comprehend-medical |
| Repo | |
| Framework | |
Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets
| Title | Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets |
| Authors | Clara Fernandez-Labrador, Ajad Chhatkuli, Danda Pani Paudel, Jose J. Guerrero, Cédric Demonceaux, Luc Van Gool |
| Abstract | Automatic discovery of category-specific 3D keypoints from a collection of objects of some category is a challenging problem. One reason is that not all objects in a category necessarily have the same semantic parts. The level of difficulty adds up further when objects are represented by 3D point clouds, with variations in shape and unknown coordinate frames. We define keypoints to be category-specific, if they meaningfully represent objects’ shape and their correspondences can be simply established order-wise across all objects. This paper aims at learning category-specific 3D keypoints, in an unsupervised manner, using a collection of misaligned 3D point clouds of objects from an unknown category. In order to do so, we model shapes defined by the keypoints, within a category, using the symmetric linear basis shapes without assuming the plane of symmetry to be known. The usage of symmetry prior leads us to learn stable keypoints suitable for higher misalignments. To the best of our knowledge, this is the first work on learning such keypoints directly from 3D point clouds. Using categories from four benchmark datasets, we demonstrate the quality of our learned keypoints by quantitative and qualitative evaluations. Our experiments also show that the keypoints discovered by our method are geometrically and semantically consistent. |
| Tasks | |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.07619v1 |
| https://arxiv.org/pdf/2003.07619v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-category-specific |
| Repo | |
| Framework | |
Explainable Machine Learning Control – robust control and stability analysis
| Title | Explainable Machine Learning Control – robust control and stability analysis |
| Authors | Markus Quade, Thomas Isele, Markus Abel |
| Abstract | Recently, the term explainable AI became known as an approach to produce models from artificial intelligence which allow interpretation. Since a long time, there are models of symbolic regression in use that are perfectly explainable and mathematically tractable: in this contribution we demonstrate how to use symbolic regression methods to infer the optimal control of a dynamical system given one or several optimization criteria, or cost functions. In previous publications, network control was achieved by automatized machine learning control using genetic programming. Here, we focus on the subsequent analysis of the analytical expressions which result from the machine learning. In particular, we use AUTO to analyze the stability properties of the controlled oscillator system which served as our model. As a result, we show that there is a considerable advantage of explainable models over less accessible neural networks. |
| Tasks | |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2001.10056v1 |
| https://arxiv.org/pdf/2001.10056v1.pdf | |
| PWC | https://paperswithcode.com/paper/explainable-machine-learning-control-robust |
| Repo | |
| Framework | |
A Non-Intrusive Correction Algorithm for Classification Problems with Corrupted Data
| Title | A Non-Intrusive Correction Algorithm for Classification Problems with Corrupted Data |
| Authors | Jun Hou, Tong Qin, Kailiang Wu, Dongbin Xiu |
| Abstract | A novel correction algorithm is proposed for multi-class classification problems with corrupted training data. The algorithm is non-intrusive, in the sense that it post-processes a trained classification model by adding a correction procedure to the model prediction. The correction procedure can be coupled with any approximators, such as logistic regression, neural networks of various architectures, etc. When training dataset is sufficiently large, we prove that the corrected models deliver correct classification results as if there is no corruption in the training data. For datasets of finite size, the corrected models produce significantly better recovery results, compared to the models without the correction algorithm. All of the theoretical findings in the paper are verified by our numerical examples. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04658v1 |
| https://arxiv.org/pdf/2002.04658v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-non-intrusive-correction-algorithm-for |
| Repo | |
| Framework | |
Structural Decompositions of Epistemic Logic Programs
| Title | Structural Decompositions of Epistemic Logic Programs |
| Authors | Markus Hecher, Michael Morak, Stefan Woltran |
| Abstract | Epistemic logic programs (ELPs) are a popular generalization of standard Answer Set Programming (ASP) providing means for reasoning over answer sets within the language. This richer formalism comes at the price of higher computational complexity reaching up to the fourth level of the polynomial hierarchy. However, in contrast to standard ASP, dedicated investigations towards tractability have not been undertaken yet. In this paper, we give first results in this direction and show that central ELP problems can be solved in linear time for ELPs exhibiting structural properties in terms of bounded treewidth. We also provide a full dynamic programming algorithm that adheres to these bounds. Finally, we show that applying treewidth to a novel dependency structure—given in terms of epistemic literals—allows to bound the number of ASP solver calls in typical ELP solving procedures. |
| Tasks | |
| Published | 2020-01-13 |
| URL | https://arxiv.org/abs/2001.04219v1 |
| https://arxiv.org/pdf/2001.04219v1.pdf | |
| PWC | https://paperswithcode.com/paper/structural-decompositions-of-epistemic-logic |
| Repo | |
| Framework | |
The {0,1}-knapsack problem with qualitative levels
| Title | The {0,1}-knapsack problem with qualitative levels |
| Authors | Luca E. Schäfer, Tobias Dietz, Maria Barbati, José Rui Figueira, Salvatore Greco, Stefan Ruzika |
| Abstract | A variant of the classical knapsack problem is considered in which each item is associated with an integer weight and a qualitative level. We define a dominance relation over the feasible subsets of the given item set and show that this relation defines a preorder. We propose a dynamic programming algorithm to compute the entire set of non-dominated rank cardinality vectors and we state two greedy algorithms, which efficiently compute a single efficient solution. |
| Tasks | |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.04850v1 |
| https://arxiv.org/pdf/2002.04850v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-01-knapsack-problem-with-qualitative |
| Repo | |
| Framework | |
Regret Minimization in Partially Observable Linear Quadratic Control
| Title | Regret Minimization in Partially Observable Linear Quadratic Control |
| Authors | Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar |
| Abstract | We study the problem of regret minimization in partially observable linear quadratic control systems when the model dynamics are unknown a priori. We propose ExpCommit, an explore-then-commit algorithm that learns the model Markov parameters and then follows the principle of optimism in the face of uncertainty to design a controller. We propose a novel way to decompose the regret and provide an end-to-end sublinear regret upper bound for partially observable linear quadratic control. Finally, we provide stability guarantees and establish a regret upper bound of $\tilde{\mathcal{O}}(T^{2/3})$ for ExpCommit, where $T$ is the time horizon of the problem. |
| Tasks | |
| Published | 2020-01-31 |
| URL | https://arxiv.org/abs/2002.00082v2 |
| https://arxiv.org/pdf/2002.00082v2.pdf | |
| PWC | https://paperswithcode.com/paper/regret-minimization-in-partially-observable |
| Repo | |
| Framework | |
Eating Healthier: Exploring Nutrition Information for Healthier Recipe Recommendation
| Title | Eating Healthier: Exploring Nutrition Information for Healthier Recipe Recommendation |
| Authors | Meng Chen, Xiaoyi Jia, Elizabeth Gorbonos, Chnh T. Hong, Xiaohui Yu, Yang Liu |
| Abstract | With the booming of personalized recipe sharing networks (e.g., Yummly), a deluge of recipes from different cuisines could be obtained easily. In this paper, we aim to solve a problem which many home-cooks encounter when searching for recipes online. Namely, finding recipes which best fit a handy set of ingredients while at the same time follow healthy eating guidelines. This task is especially difficult since the lions share of online recipes have been shown to be unhealthy. In this paper we propose a novel framework named NutRec, which models the interactions between ingredients and their proportions within recipes for the purpose of offering healthy recommendation. Specifically, NutRec consists of three main components: 1) using an embedding-based ingredient predictor to predict the relevant ingredients with user-defined initial ingredients, 2) predicting the amounts of the relevant ingredients with a multi-layer perceptron-based network, 3) creating a healthy pseudo-recipe with a list of ingredients and their amounts according to the nutritional information and recommending the top similar recipes with the pseudo-recipe. We conduct the experiments on two recipe datasets, including Allrecipes with 36,429 recipes and Yummly with 89,413 recipes, respectively. The empirical results support the framework’s intuition and showcase its ability to retrieve healthier recipes. |
| Tasks | |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07027v1 |
| https://arxiv.org/pdf/2003.07027v1.pdf | |
| PWC | https://paperswithcode.com/paper/eating-healthier-exploring-nutrition |
| Repo | |
| Framework | |
AutoCogniSys: IoT Assisted Context-Aware Automatic Cognitive Health Assessment
| Title | AutoCogniSys: IoT Assisted Context-Aware Automatic Cognitive Health Assessment |
| Authors | Mohammad Arif Ul Alam, Nirmalya Roy, Sarah Holmes, Aryya Gangopadhyay, Elizabeth Galik |
| Abstract | Cognitive impairment has become epidemic in older adult population. The recent advent of tiny wearable and ambient devices, a.k.a Internet of Things (IoT) provides ample platforms for continuous functional and cognitive health assessment of older adults. In this paper, we design, implement and evaluate AutoCogniSys, a context-aware automated cognitive health assessment system, combining the sensing powers of wearable physiological (Electrodermal Activity, Photoplethysmography) and physical (Accelerometer, Object) sensors in conjunction with ambient sensors. We design appropriate signal processing and machine learning techniques, and develop an automatic cognitive health assessment system in a natural older adults living environment. We validate our approaches using two datasets: (i) a naturalistic sensor data streams related to Activities of Daily Living and mental arousal of 22 older adults recruited in a retirement community center, individually living in their own apartments using a customized inexpensive IoT system (IRB #HP-00064387) and (ii) a publicly available dataset for emotion detection. The performance of AutoCogniSys attests max. 93% of accuracy in assessing cognitive health of older adults. |
| Tasks | |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.07492v1 |
| https://arxiv.org/pdf/2003.07492v1.pdf | |
| PWC | https://paperswithcode.com/paper/autocognisys-iot-assisted-context-aware |
| Repo | |
| Framework | |
