Paper Group ANR 297
A Framework for Evaluating Agricultural Ontologies. Equations Derivation of VINS-Mono. Hyperlink Regression via Bregman Divergence. Identifying Adversarial Sentences by Analyzing Text Complexity. Pólygamma Data Augmentation to address Non-conjugacy in the Bayesian Estimation of Mixed Multinomial Logit Models. Predicting Louisiana Public High School …
A Framework for Evaluating Agricultural Ontologies
| Title | A Framework for Evaluating Agricultural Ontologies |
| Authors | Anat Goldstein, Lior Fink, Gilad Ravid |
| Abstract | An ontology is a formal representation of domain knowledge, which can be interpreted by machines. In recent years, ontologies have become a major tool for domain knowledge representation and a core component of many knowledge management systems, decision support systems and other intelligent systems, inter alia, in the context of agriculture. A review of the existing literature on agricultural ontologies, however, reveals that most of the studies, which propose agricultural ontologies, are lacking an explicit evaluation procedure. This is undesired because without well-structured evaluation processes, it is difficult to consider the value of ontologies to research and practice. Moreover, it is difficult to rely on such ontologies and share them on the Semantic Web or between semantic aware applications. With the growing number of ontology-based agricultural systems and the increasing popularity of the Semantic Web, it becomes essential that such development and evaluation methods are put forward to guide future efforts of ontology development. Our work contributes to the literature on agricultural ontologies, by presenting a method for evaluating agricultural ontologies, which seems to be missing from most existing studies on agricultural ontologies. The framework supports the matching of appropriate evaluation methods for a given ontology based on the ontology’s purpose. |
| Tasks | |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10450v2 |
| https://arxiv.org/pdf/1906.10450v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-framework-for-evaluating-agricultural |
| Repo | |
| Framework | |
Equations Derivation of VINS-Mono
| Title | Equations Derivation of VINS-Mono |
| Authors | Yibin Wu |
| Abstract | The VINS-Mono is a monocular visual-inertial 6 DOF state estimator proposed by Aerial Robotics Group at HKUST in 2017, which can be performed on MAVs, smartphones and many other intelligent platforms. It is a state-of-the-art visual-inertial odometry algorithms which has gained extensive attention worldwide. The main equations including IMU preintegration, visual/inertial co-initialization and tightly-coupled nonlinear optimization are derived and analyzed in this manuscript. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.11986v1 |
| https://arxiv.org/pdf/1912.11986v1.pdf | |
| PWC | https://paperswithcode.com/paper/equations-derivation-of-vins-mono |
| Repo | |
| Framework | |
Hyperlink Regression via Bregman Divergence
| Title | Hyperlink Regression via Bregman Divergence |
| Authors | Akifumi Okuno, Hidetoshi Shimodaira |
| Abstract | A collection of $U : (\in \mathbb{N})$ data vectors is called a $U$-tuple, and the association strength among the vectors of a tuple is termed as the \emph{hyperlink weight}, that is assumed to be symmetric with respect to permutation of the entries in the index. We herein propose Bregman hyperlink regression (BHLR), which learns a user-specified symmetric similarity function such that it predicts the tuple’s hyperlink weight from data vectors stored in the $U$-tuple. BHLR is a simple and general framework for hyper-relational learning, that minimizes Bregman-divergence (BD) between the hyperlink weights and estimated similarities defined for the corresponding tuples; BHLR encompasses various existing methods, such as logistic regression ($U=1$), Poisson regression ($U=1$), link prediction ($U=2$), and those for representation learning, such as graph embedding ($U=2$), matrix factorization ($U=2$), tensor factorization ($U \geq 2$), and their variants equipped with arbitrary BD. Nonlinear functions (e.g., neural networks), can be employed for the similarity functions. However, there are theoretical challenges such that some of different tuples of BHLR may share data vectors therein, unlike the i.i.d. setting of classical regression. We address these theoretical issues, and proved that BHLR equipped with arbitrary BD and $U \in \mathbb{N}$ is (P-1) statistically consistent, that is, it asymptotically recovers the underlying true conditional expectation of hyperlink weights given data vectors, and (P-2) computationally tractable, that is, it is efficiently computed by stochastic optimization algorithms using a novel generalized minibatch sampling procedure for hyper-relational data. Consequently, theoretical guarantees for BHLR including several existing methods, that have been examined experimentally, are provided in a unified manner. |
| Tasks | Graph Embedding, Link Prediction, Relational Reasoning, Representation Learning, Stochastic Optimization |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1908.02573v2 |
| https://arxiv.org/pdf/1908.02573v2.pdf | |
| PWC | https://paperswithcode.com/paper/hyperlink-regression-via-bregman-divergence |
| Repo | |
| Framework | |
Identifying Adversarial Sentences by Analyzing Text Complexity
| Title | Identifying Adversarial Sentences by Analyzing Text Complexity |
| Authors | Hoang-Quoc Nguyen-Son, Tran Phuong Thao, Seira Hidano, Shinsaku Kiyomoto |
| Abstract | Attackers create adversarial text to deceive both human perception and the current AI systems to perform malicious purposes such as spam product reviews and fake political posts. We investigate the difference between the adversarial and the original text to prevent the risk. We prove that the text written by a human is more coherent and fluent. Moreover, the human can express the idea through the flexible text with modern words while a machine focuses on optimizing the generated text by the simple and common words. We also suggest a method to identify the adversarial text by extracting the features related to our findings. The proposed method achieves high performance with 82.0% of accuracy and 18.4% of equal error rate, which is better than the existing methods whose the best accuracy is 77.0% corresponding to the error rate 22.8%. |
| Tasks | Adversarial Text |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.08981v1 |
| https://arxiv.org/pdf/1912.08981v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-adversarial-sentences-by |
| Repo | |
| Framework | |
Pólygamma Data Augmentation to address Non-conjugacy in the Bayesian Estimation of Mixed Multinomial Logit Models
| Title | Pólygamma Data Augmentation to address Non-conjugacy in the Bayesian Estimation of Mixed Multinomial Logit Models |
| Authors | Prateek Bansal, Rico Krueger, Michel Bierlaire, Ricardo A. Daziano, Taha H. Rashidi |
| Abstract | The standard Gibbs sampler of Mixed Multinomial Logit (MMNL) models involves sampling from conditional densities of utility parameters using Metropolis-Hastings (MH) algorithm due to unavailability of conjugate prior for logit kernel. To address this non-conjugacy concern, we propose the application of P'olygamma data augmentation (PG-DA) technique for the MMNL estimation. The posterior estimates of the augmented and the default Gibbs sampler are similar for two-alternative scenario (binary choice), but we encounter empirical identification issues in the case of more alternatives ($J \geq 3$). |
| Tasks | Data Augmentation |
| Published | 2019-04-13 |
| URL | http://arxiv.org/abs/1904.07688v1 |
| http://arxiv.org/pdf/1904.07688v1.pdf | |
| PWC | https://paperswithcode.com/paper/polygamma-data-augmentation-to-address-non |
| Repo | |
| Framework | |
Predicting Louisiana Public High School Dropout through Imbalanced Learning Techniques
| Title | Predicting Louisiana Public High School Dropout through Imbalanced Learning Techniques |
| Authors | Marmar Orooji, Jianhua Chen |
| Abstract | This study is motivated by the magnitude of the problem of Louisiana high school dropout and its negative impacts on individual and public well-being. Our goal is to predict students who are at risk of high school dropout, by examining Louisiana administrative dataset. Due to the imbalanced nature of the dataset, imbalanced learning techniques including resampling, case weighting, and cost-sensitive learning have been applied to enhance the prediction performance on the rare class. Performance metrics used in this study are F-measure, recall and precision of the rare class. We compare the performance of several machine learning algorithms such as neural networks, decision trees and bagging trees in combination with the imbalanced learning approaches using an administrative dataset of size of 366k+ from Louisiana Department of Education. Experiments show that application of imbalanced learning methods produces good results on recall but decreases precision, whereas base classifiers without regard of imbalanced data handling gives better precision but poor recall. Overall application of imbalanced learning techniques is beneficial, yet more studies are desired to improve precision. |
| Tasks | |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13018v1 |
| https://arxiv.org/pdf/1910.13018v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-louisiana-public-high-school |
| Repo | |
| Framework | |
Snomed2Vec: Random Walk and Poincaré Embeddings of a Clinical Knowledge Base for Healthcare Analytics
| Title | Snomed2Vec: Random Walk and Poincaré Embeddings of a Clinical Knowledge Base for Healthcare Analytics |
| Authors | Khushbu Agarwal, Tome Eftimov, Raghavendra Addanki, Sutanay Choudhury, Suzanne Tamang, Robert Rallo |
| Abstract | Representation learning methods that transform encoded data (e.g., diagnosis and drug codes) into continuous vector spaces (i.e., vector embeddings) are critical for the application of deep learning in healthcare. Initial work in this area explored the use of variants of the word2vec algorithm to learn embeddings for medical concepts from electronic health records or medical claims datasets. We propose learning embeddings for medical concepts by using graph-based representation learning methods on SNOMED-CT, a widely popular knowledge graph in the healthcare domain with numerous operational and research applications. Current work presents an empirical analysis of various embedding methods, including the evaluation of their performance on multiple tasks of biomedical relevance (node classification, link prediction, and patient state prediction). Our results show that concept embeddings derived from the SNOMED-CT knowledge graph significantly outperform state-of-the-art embeddings, showing 5-6x improvement in ``concept similarity” and 6-20% improvement in patient diagnosis. | |
| Tasks | Link Prediction, Node Classification, Representation Learning |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08650v1 |
| https://arxiv.org/pdf/1907.08650v1.pdf | |
| PWC | https://paperswithcode.com/paper/snomed2vec-random-walk-and-poincare |
| Repo | |
| Framework | |
Domain Constraint Approximation based Semi Supervision
| Title | Domain Constraint Approximation based Semi Supervision |
| Authors | Yifu Wu, Jin Wei, Rigoberto Roche |
| Abstract | Deep learning for supervised learning has achieved astonishing performance in various machine learning applications. However, annotated data is expensive and rare. In practice, only a small portion of data samples are annotated. Pseudo-ensembling-based approaches have achieved state-of-the-art results in computer vision related tasks. However, it still relies on the quality of an initial model built by labeled data. Less labeled data may degrade model performance a lot. Domain constraint is another way regularize the posterior but has some limitation. In this paper, we proposed a fuzzy domain-constraint-based framework which loses the requirement of traditional constraint learning and enhances the model quality for semi supervision. Simulations results show the effectiveness of our design. |
| Tasks | |
| Published | 2019-02-11 |
| URL | https://arxiv.org/abs/1902.04177v2 |
| https://arxiv.org/pdf/1902.04177v2.pdf | |
| PWC | https://paperswithcode.com/paper/domain-constraint-approximation-based-semi |
| Repo | |
| Framework | |
Distantly Supervised Question Parsing
| Title | Distantly Supervised Question Parsing |
| Authors | Hamid Zafar, Maryam Tavakol, Jens Lehmann |
| Abstract | The emergence of structured databases for Question Answering (QA) systems has led to developing methods, in which the problem of learning the correct answer efficiently is based on a linking task between the constituents of the question and the corresponding entries in the database. As a result, parsing the questions in order to determine their main elements, which are required for answer retrieval, becomes crucial. However, most datasets for QA systems lack gold annotations for parsing, i.e., labels are only available in the form of (question, formal-query, answer). In this paper, we propose a distantly supervised learning framework based on reinforcement learning to learn the mentions of entities and relations in questions. We leverage the provided formal queries to characterize delayed rewards for optimizing a policy gradient objective for the parsing model. An empirical evaluation of our approach shows a significant improvement in the performance of entity and relation linking compared to the state of the art. We also demonstrate that a more accurate parsing component enhances the overall performance of QA systems. |
| Tasks | Knowledge Graphs, Question Answering |
| Published | 2019-09-27 |
| URL | https://arxiv.org/abs/1909.12566v2 |
| https://arxiv.org/pdf/1909.12566v2.pdf | |
| PWC | https://paperswithcode.com/paper/mdp-based-shallow-parsing-in-distantly |
| Repo | |
| Framework | |
Action Guidance with MCTS for Deep Reinforcement Learning
| Title | Action Guidance with MCTS for Deep Reinforcement Learning |
| Authors | Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor |
| Abstract | Deep reinforcement learning has achieved great successes in recent years, however, one main challenge is the sample inefficiency. In this paper, we focus on how to use action guidance by means of a non-expert demonstrator to improve sample efficiency in a domain with sparse, delayed, and possibly deceptive rewards: the recently-proposed multi-agent benchmark of Pommerman. We propose a new framework where even a non-expert simulated demonstrator, e.g., planning algorithms such as Monte Carlo tree search with a small number rollouts, can be integrated within asynchronous distributed deep reinforcement learning methods. Compared to a vanilla deep RL algorithm, our proposed methods both learn faster and converge to better policies on a two-player mini version of the Pommerman game. |
| Tasks | |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.11703v1 |
| https://arxiv.org/pdf/1907.11703v1.pdf | |
| PWC | https://paperswithcode.com/paper/action-guidance-with-mcts-for-deep |
| Repo | |
| Framework | |
3D Organ Shape Reconstruction from Topogram Images
| Title | 3D Organ Shape Reconstruction from Topogram Images |
| Authors | Elena Balashova, Jiangping Wang, Vivek Singh, Bogdan Georgescu, Brian Teixeira, Ankur Kapoor |
| Abstract | Automatic delineation and measurement of main organs such as liver is one of the critical steps for assessment of hepatic diseases, planning and postoperative or treatment follow-up. However, addressing this problem typically requires performing computed tomography (CT) scanning and complicated postprocessing of the resulting scans using slice-by-slice techniques. In this paper, we show that 3D organ shape can be automatically predicted directly from topogram images, which are easier to acquire and have limited exposure to radiation during acquisition, compared to CT scans. We evaluate our approach on the challenging task of predicting liver shape using a generative model. We also demonstrate that our method can be combined with user annotations, such as a 2D mask, for improved prediction accuracy. We show compelling results on 3D liver shape reconstruction and volume estimation on 2129 CT scans. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1904.00073v1 |
| http://arxiv.org/pdf/1904.00073v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-organ-shape-reconstruction-from-topogram |
| Repo | |
| Framework | |
Think Again Networks and the Delta Loss
| Title | Think Again Networks and the Delta Loss |
| Authors | Alexandre Salle, Marcelo Prates |
| Abstract | This short paper introduces an abstraction called Think Again Networks (ThinkNet) which can be applied to any state-dependent function (such as a recurrent neural network). |
| Tasks | Language Modelling |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.11816v2 |
| http://arxiv.org/pdf/1904.11816v2.pdf | |
| PWC | https://paperswithcode.com/paper/think-again-networks-the-delta-loss-and-an |
| Repo | |
| Framework | |
A Robust Transferable Deep Learning Framework for Cross-sectional Investment Strategy
| Title | A Robust Transferable Deep Learning Framework for Cross-sectional Investment Strategy |
| Authors | Kei Nakagawa, Masaya Abe, Junpei Komiyama |
| Abstract | Stock return predictability is an important research theme as it reflects our economic and social organization, and significant efforts are made to explain the dynamism therein. Statistics of strong explanative power, called “factor” have been proposed to summarize the essence of predictive stock returns. Although machine learning methods are increasingly popular in stock return prediction, an inference of the stock returns is highly elusive, and still most investors, if partly, rely on their intuition to build a better decision making. The challenge here is to make an investment strategy that is consistent over a reasonably long period, with the minimum human decision on the entire process. To this end, we propose a new stock return prediction framework that we call Ranked Information Coefficient Neural Network (RIC-NN). RIC-NN is a deep learning approach and includes the following three novel ideas: (1) nonlinear multi-factor approach, (2) stopping criteria with ranked information coefficient (rank IC), and (3) deep transfer learning among multiple regions. Experimental comparison with the stocks in the Morgan Stanley Capital International (MSCI) indices shows that RIC-NN outperforms not only off-the-shelf machine learning methods but also the average return of major equity investment funds in the last fourteen years. |
| Tasks | Decision Making, Transfer Learning |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.01491v1 |
| https://arxiv.org/pdf/1910.01491v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-robust-transferable-deep-learning-framework |
| Repo | |
| Framework | |
A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
| Title | A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach |
| Authors | Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil |
| Abstract | In this paper we consider solving saddle point problems using two variants of Gradient Descent-Ascent algorithms, Extra-gradient (EG) and Optimistic Gradient Descent Ascent (OGDA) methods. We show that both of these algorithms admit a unified analysis as approximations of the classical proximal point method for solving saddle point problems. This viewpoint enables us to develop a new framework for analyzing EG and OGDA for bilinear and strongly convex-strongly concave settings. Moreover, we use the proximal point approximation interpretation to generalize the results for OGDA for a wide range of parameters. |
| Tasks | |
| Published | 2019-01-24 |
| URL | https://arxiv.org/abs/1901.08511v4 |
| https://arxiv.org/pdf/1901.08511v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-analysis-of-extra-gradient-and |
| Repo | |
| Framework | |
Fraud detection in telephone conversations for financial services using linguistic features
| Title | Fraud detection in telephone conversations for financial services using linguistic features |
| Authors | Nikesh Bajaj, Tracy Goodluck Constance, Marvin Rajwadi, Julie Wall, Mansour Moniri, Cornelius Glackin, Nigel Cannings, Chris Woodruff, James Laird |
| Abstract | Detecting the elements of deception in a conversation is one of the most challenging problems for the AI community. It becomes even more difficult to design a transparent system, which is fully explainable and satisfies the need for financial and legal services to be deployed. This paper presents an approach for fraud detection in transcribed telephone conversations using linguistic features. The proposed approach exploits the syntactic and semantic information of the transcription to extract both the linguistic markers and the sentiment of the customer’s response. We demonstrate the results on real-world financial services data using simple, robust and explainable classifiers such as Naive Bayes, Decision Tree, Nearest Neighbours, and Support Vector Machines. |
| Tasks | Fraud Detection |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04748v1 |
| https://arxiv.org/pdf/1912.04748v1.pdf | |
| PWC | https://paperswithcode.com/paper/fraud-detection-in-telephone-conversations |
| Repo | |
| Framework | |
