Paper Group ANR 495
A framework for streamlined statistical prediction using topic models. Multi-Scale Learned Iterative Reconstruction. Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks. AI Enabling Technologies: A Survey. Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strateg …
A framework for streamlined statistical prediction using topic models
| Title | A framework for streamlined statistical prediction using topic models |
| Authors | Vanessa Glenny, Jonathan Tuke, Nigel Bean, Lewis Mitchell |
| Abstract | In the Humanities and Social Sciences, there is increasing interest in approaches to information extraction, prediction, intelligent linkage, and dimension reduction applicable to large text corpora. With approaches in these fields being grounded in traditional statistical techniques, the need arises for frameworks whereby advanced NLP techniques such as topic modelling may be incorporated within classical methodologies. This paper provides a classical, supervised, statistical learning framework for prediction from text, using topic models as a data reduction method and the topics themselves as predictors, alongside typical statistical tools for predictive modelling. We apply this framework in a Social Sciences context (applied animal behaviour) as well as a Humanities context (narrative analysis) as examples of this framework. The results show that topic regression models perform comparably to their much less efficient equivalents that use individual words as predictors. |
| Tasks | Dimensionality Reduction, Topic Models |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.06941v1 |
| http://arxiv.org/pdf/1904.06941v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-framework-for-streamlined-statistical |
| Repo | |
| Framework | |
Multi-Scale Learned Iterative Reconstruction
| Title | Multi-Scale Learned Iterative Reconstruction |
| Authors | Andreas Hauptmann, Jonas Adler, Simon Arridge, Ozan Öktem |
| Abstract | Model-based learned iterative reconstruction methods have recently been shown to outperform classical reconstruction algorithms. Applicability of these methods to large scale inverse problems is however limited by the available memory for training and extensive training times due to computationally expensive forward models. As a possible solution to these restrictions we propose a multi-scale learned iterative reconstruction scheme that computes iterates on discretisations of increasing resolution. This procedure does not only reduce memory requirements, it also considerably speeds up reconstruction and training times, but most importantly is scalable to large scale inverse problems with non-trivial forward operators, such as those that arise in many 3D tomographic applications. In particular, we propose a hybrid network that combines the multi-scale iterative approach with a particularly expressive network architecture which in combination exhibits excellent scalability in 3D. Applicability of the algorithm is demonstrated for 3D cone beam computed tomography from real measurement data of an organic phantom. Additionally, we examine scalability and reconstruction quality in comparison to established learned reconstruction methods in two dimensions for low dose computed tomography on human phantoms. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.00936v2 |
| https://arxiv.org/pdf/1908.00936v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-learned-iterative-reconstruction |
| Repo | |
| Framework | |
Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks
| Title | Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks |
| Authors | Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang, Huajun Chen |
| Abstract | We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings. Here, the challenge is to learn accurate “few-shot” models for classes existing at the tail of the class distribution, for which little data is available. Inspired by the rich semantic correlations between classes at the long tail and those at the head, we take advantage of the knowledge from data-rich classes at the head of the distribution to boost the performance of the data-poor classes at the tail. First, we propose to leverage implicit relational knowledge among class labels from knowledge graph embeddings and learn explicit relational knowledge using graph convolution networks. Second, we integrate that relational knowledge into relation extraction model by coarse-to-fine knowledge-aware attention mechanism. We demonstrate our results for a large-scale benchmark dataset which show that our approach significantly outperforms other baselines, especially for long-tail relations. |
| Tasks | Knowledge Graph Embeddings, Relation Extraction |
| Published | 2019-03-04 |
| URL | http://arxiv.org/abs/1903.01306v1 |
| http://arxiv.org/pdf/1903.01306v1.pdf | |
| PWC | https://paperswithcode.com/paper/long-tail-relation-extraction-via-knowledge |
| Repo | |
| Framework | |
AI Enabling Technologies: A Survey
| Title | AI Enabling Technologies: A Survey |
| Authors | Vijay Gadepally, Justin Goodwin, Jeremy Kepner, Albert Reuther, Hayley Reynolds, Siddharth Samsi, Jonathan Su, David Martinez |
| Abstract | Artificial Intelligence (AI) has the opportunity to revolutionize the way the United States Department of Defense (DoD) and Intelligence Community (IC) address the challenges of evolving threats, data deluge, and rapid courses of action. Developing an end-to-end artificial intelligence system involves parallel development of different pieces that must work together in order to provide capabilities that can be used by decision makers, warfighters and analysts. These pieces include data collection, data conditioning, algorithms, computing, robust artificial intelligence, and human-machine teaming. While much of the popular press today surrounds advances in algorithms and computing, most modern AI systems leverage advances across numerous different fields. Further, while certain components may not be as visible to end-users as others, our experience has shown that each of these interrelated components play a major role in the success or failure of an AI system. This article is meant to highlight many of these technologies that are involved in an end-to-end AI system. The goal of this article is to provide readers with an overview of terminology, technical details and recent highlights from academia, industry and government. Where possible, we indicate relevant resources that can be used for further reading and understanding. |
| Tasks | |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.03592v1 |
| https://arxiv.org/pdf/1905.03592v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503592 |
| Repo | |
| Framework | |
Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy
| Title | Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy |
| Authors | Philippe Schwaller, Riccardo Petraglia, Valerio Zullo, Vishnu H Nair, Rico Andreas Haeuselmann, Riccardo Pisoni, Costas Bekas, Anna Iuliano, Teodoro Laino |
| Abstract | We present an extension of our Molecular Transformer architecture combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention. The single-step retrosynthetic model sets a new state of the art for predicting reactants as well as reagents, solvents and catalysts for each retrosynthetic step. We introduce new metrics (coverage, class diversity, round-trip accuracy and Jensen-Shannon divergence) to evaluate the single-step retrosynthetic models, using the forward prediction and a reaction classification model always based on the transformer architecture. The hypergraph is constructed on the fly, and the nodes are filtered and further expanded based on a Bayesian-like probability. We critically assessed the end-to-end framework with several retrosynthesis examples from literature and academic exams. Overall, the frameworks has a very good performance with few weaknesses due to the bias induced during the training process. The use of the newly introduced metrics opens up the possibility to optimize entire retrosynthetic frameworks through focusing on the performance of the single-step model only. |
| Tasks | |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.08036v1 |
| https://arxiv.org/pdf/1910.08036v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-retrosynthetic-pathways-using-a |
| Repo | |
| Framework | |
Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors
| Title | Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors |
| Authors | Shaofu Xu, Rui Wang, Jianping Chen, Lei Yu, Weiwen Zou |
| Abstract | In regular microwave photonic (MWP) receiving systems, broadband signals are processed in the analog domain before they are transformed to the digital domain for further processing and storage. However, the quality of the signals may be degraded by defective photonic analog links, especially in a complicated MWP system. Here, we show a unified deep learning scheme that recovers the distorted broadband signals as they are transformed to the digital domain. The neural network could automatically learn the end-to-end inverse responses of the distortion effects of actual photonic analog links from data without expert knowledge and system priors. Hence, by shifting or augmenting the datasets, the neural network is potential to be generalized to various MWP receiving systems. We conduct experiments by nontrivial MWP systems with complicated waveforms. Results validate the effectiveness, general applicability and the noise-robustness of the proposed scheme, showing its superior performance in practical MWP systems. Therefore, the proposed deep learning scheme facilitates the low-cost performance improvement of MWP receiving systems, as well as the next-generation broadband transceivers, including radars, communications, and microwave imaging. |
| Tasks | |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07312v2 |
| https://arxiv.org/pdf/1907.07312v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-scheme-for-microwave-photonic |
| Repo | |
| Framework | |
Gaussian Process Regression and Classification under Mathematical Constraints with Learning Guarantees
| Title | Gaussian Process Regression and Classification under Mathematical Constraints with Learning Guarantees |
| Authors | Jeremiah Zhe Liu |
| Abstract | We introduce constrained Gaussian process (CGP), a Gaussian process model for random functions that allows easy placement of mathematical constrains (e.g., non-negativity, monotonicity, etc) on its sample functions. CGP comes with closed-form probability density function (PDF), and has the attractive feature that its posterior distributions for regression and classification are again CGPs with closed-form expressions. Furthermore, we show that CGP inherents the optimal theoretical properties of the Gaussian process, e.g. rates of posterior contraction, due to the fact that CGP is an Gaussian process with a more efficient model space. |
| Tasks | |
| Published | 2019-04-21 |
| URL | http://arxiv.org/abs/1904.09632v1 |
| http://arxiv.org/pdf/1904.09632v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-process-regression-and |
| Repo | |
| Framework | |
Dr.Quad at MEDIQA 2019: Towards Textual Inference and Question Entailment using contextualized representations
| Title | Dr.Quad at MEDIQA 2019: Towards Textual Inference and Question Entailment using contextualized representations |
| Authors | Vinayshekhar Bannihatti Kumar, Ashwin Srinivasan, Aditi Chaudhary, James Route, Teruko Mitamura, Eric Nyberg |
| Abstract | This paper presents the submissions by Team Dr.Quad to the ACL-BioNLP 2019 shared task on Textual Inference and Question Entailment in the Medical Domain. Our system is based on the prior work Liu et al. (2019) which uses a multi-task objective function for textual entailment. In this work, we explore different strategies for generalizing state-of-the-art language understanding models to the specialized medical domain. Our results on the shared task demonstrate that incorporating domain knowledge through data augmentation is a powerful strategy for addressing challenges posed by specialized domains such as medicine. |
| Tasks | Data Augmentation, Natural Language Inference |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.10136v1 |
| https://arxiv.org/pdf/1907.10136v1.pdf | |
| PWC | https://paperswithcode.com/paper/drquad-at-mediqa-2019-towards-textual |
| Repo | |
| Framework | |
CMSN: Continuous Multi-stage Network and Variable Margin Cosine Loss for Temporal Action Proposal Generation
| Title | CMSN: Continuous Multi-stage Network and Variable Margin Cosine Loss for Temporal Action Proposal Generation |
| Authors | Yushuai Hu, Yaochu Jin, Runhua Li, Xiangxiang Zhang |
| Abstract | Accurately locating the start and end time of an action in untrimmed videos is a challenging task. One of the important reasons is the boundary of action is not highly distinguishable, and the features around the boundary are difficult to discriminate. To address this problem, we propose a novel framework for temporal action proposal generation, namely Continuous Multi-stage Network (CMSN), which divides a video that contains a complete action instance into six stages, namely Backgroud, Ready, Start, Confirm, End, Follow. To distinguish between Ready and Start, End and Follow more accurately, we propose a novel loss function, Variable Margin Cosine Loss (VMCL), which allows for different margins between different categories. Our experiments on THUMOS14 show that the proposed method for temporal proposal generation performs better than the state-of-the-art methods using the same network architecture and training dataset. |
| Tasks | Temporal Action Proposal Generation |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06080v3 |
| https://arxiv.org/pdf/1911.06080v3.pdf | |
| PWC | https://paperswithcode.com/paper/cmsn-continuous-multi-stage-network-and |
| Repo | |
| Framework | |
Online Learning to Estimate Warfarin Dose with Contextual Linear Bandits
| Title | Online Learning to Estimate Warfarin Dose with Contextual Linear Bandits |
| Authors | Hai Xiao |
| Abstract | Warfarin is one of the most commonly used oral blood anticoagulant agent in the world, the proper dose of Warfarin is difficult to establish not only because it is substantially variant among patients, but also adverse even severe consequences of taking an incorrect dose. Typical practice is to prescribe an initial dose, then doctor closely monitor patient response and adjust accordingly to the correct dosage. The three commonly used strategies for an initial dosage are the fixed-dose approach, the Warfarin Clinical algorithm, and the Pharmacogenetic algorithm developed by the IWPC (International Warfarin Pharmacogenetics Consortium). It is always best to prescribe correct initial dosage, motivated by this challenge, this work explores the performance of multi-armed bandit algorithms to best predict the correct dosage of Warfarin instead of trial-and-error procedure. Real data from the Pharmacogenetics and Pharmacogenomics Knowledge Base (PharmGKB) is used, with it a series of linear bandit algorithms and variants are developed and evaluated on Warfarin dataset. All proposed algorithms outperformed the fixed-dose baseline algorithm, and some even matched up the Warfarin Clinical Dosing Algorithm. In addition, a few promising future directions are given for further exploration and development. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05496v1 |
| https://arxiv.org/pdf/1907.05496v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-to-estimate-warfarin-dose |
| Repo | |
| Framework | |
Sex and Coevolution
| Title | Sex and Coevolution |
| Authors | Larry Bull |
| Abstract | It has been suggested that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect. This paper uses the well-known NKCS model to explore the effects of coevolution upon the behaviour of eukaryotes. It is shown how varying fitness landscape size, ruggedness and connectedness can vary the conditions under which eukaryotic sex proves beneficial over asexual reproduction in haploids in a coevolutionary context. Moreover, eukaryotic sex is shown to be more sensitive to the relative rate of evolution exhibited by its partnering species than asexual haploids. |
| Tasks | |
| Published | 2019-03-15 |
| URL | http://arxiv.org/abs/1903.07429v1 |
| http://arxiv.org/pdf/1903.07429v1.pdf | |
| PWC | https://paperswithcode.com/paper/sex-and-coevolution |
| Repo | |
| Framework | |
Towards Automatic Lesion Classification in the Upper Aerodigestive Tract Using OCT and Deep Transfer Learning Methods
| Title | Towards Automatic Lesion Classification in the Upper Aerodigestive Tract Using OCT and Deep Transfer Learning Methods |
| Authors | Nils Gessert, Matthias Schlüter, Sarah Latus, Veronika Volgger, Christian Betz, Alexander Schlaefer |
| Abstract | Early detection of cancer is crucial for treatment and overall patient survival. In the upper aerodigestive tract (UADT) the gold standard for identification of malignant tissue is an invasive biopsy. Recently, non-invasive imaging techniques such as confocal laser microscopy and optical coherence tomography (OCT) have been used for tissue assessment. In particular, in a recent study experts classified lesions in the UADT with respect to their invasiveness using OCT images only. As the results were promising, automatic classification of lesions might be feasible which could assist experts in their decision making. Therefore, we address the problem of automatic lesion classification from OCT images. This task is very challenging as the available dataset is extremely small and the data quality is limited. However, as similar issues are typical in many clinical scenarios we study to what extent deep learning approaches can still be trained and used for decision support. |
| Tasks | Decision Making, Transfer Learning |
| Published | 2019-02-10 |
| URL | http://arxiv.org/abs/1902.03618v1 |
| http://arxiv.org/pdf/1902.03618v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-automatic-lesion-classification-in |
| Repo | |
| Framework | |
Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes
| Title | Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes |
| Authors | James P. Bailey, Georgios Piliouras |
| Abstract | We show for the first time, to our knowledge, that it is possible to reconcile in online learning in zero-sum games two seemingly contradictory objectives: vanishing time-average regret and non-vanishing step sizes. This phenomenon, that we coin ``fast and furious” learning in games, sets a new benchmark about what is possible both in max-min optimization as well as in multi-agent systems. Our analysis does not depend on introducing a carefully tailored dynamic. Instead we focus on the most well studied online dynamic, gradient descent. Similarly, we focus on the simplest textbook class of games, two-agent two-strategy zero-sum games, such as Matching Pennies. Even for this simplest of benchmarks the best known bound for total regret, prior to our work, was the trivial one of $O(T)$, which is immediately applicable even to a non-learning agent. Based on a tight understanding of the geometry of the non-equilibrating trajectories in the dual space we prove a regret bound of $\Theta(\sqrt{T})$ matching the well known optimal bound for adaptive step sizes in the online setting. This guarantee holds for all fixed step-sizes without having to know the time horizon in advance and adapt the fixed step-size accordingly. As a corollary, we establish that even with fixed learning rates the time-average of mixed strategies, utilities converge to their exact Nash equilibrium values. | |
| Tasks | |
| Published | 2019-05-11 |
| URL | https://arxiv.org/abs/1905.04532v1 |
| https://arxiv.org/pdf/1905.04532v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-furious-learning-in-zero-sum-games |
| Repo | |
| Framework | |
Towards Explainability for a Civilian UAV Fleet Management using an Agent-based Approach
| Title | Towards Explainability for a Civilian UAV Fleet Management using an Agent-based Approach |
| Authors | Yazan Mualla, Amro Najjar, Timotheus Kampik, Igor Tchappi, Stéphane Galland, Christophe Nicolle |
| Abstract | This paper presents an initial design concept and specification of a civilian Unmanned Aerial Vehicle (UAV) management simulation system that focuses on explainability for the human-in-the-loop control of semi-autonomous UAVs. The goal of the system is to facilitate the operator intervention in critical scenarios (e.g. avoid safety issues or financial risks). Explainability is supported via user-friendly abstractions on Belief-Desire-Intention agents. To evaluate the effectiveness of the system, a human-computer interaction study is proposed. |
| Tasks | |
| Published | 2019-09-22 |
| URL | https://arxiv.org/abs/1909.10090v1 |
| https://arxiv.org/pdf/1909.10090v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910090 |
| Repo | |
| Framework | |
Text segmentation on multilabel documents: A distant-supervised approach
| Title | Text segmentation on multilabel documents: A distant-supervised approach |
| Authors | Saurav Manchanda, George Karypis |
| Abstract | Segmenting text into semantically coherent segments is an important task with applications in information retrieval and text summarization. Developing accurate topical segmentation requires the availability of training data with ground truth information at the segment level. However, generating such labeled datasets, especially for applications in which the meaning of the labels is user-defined, is expensive and time-consuming. In this paper, we develop an approach that instead of using segment-level ground truth information, it instead uses the set of labels that are associated with a document and are easier to obtain as the training data essentially corresponds to a multilabel dataset. Our method, which can be thought of as an instance of distant supervision, improves upon the previous approaches by exploiting the fact that consecutive sentences in a document tend to talk about the same topic, and hence, probably belong to the same class. Experiments on the text segmentation task on a variety of datasets show that the segmentation produced by our method beats the competing approaches on four out of five datasets and performs at par on the fifth dataset. On the multilabel text classification task, our method performs at par with the competing approaches, while requiring significantly less time to estimate than the competing approaches. |
| Tasks | Information Retrieval, Text Classification, Text Summarization |
| Published | 2019-04-14 |
| URL | http://arxiv.org/abs/1904.06730v1 |
| http://arxiv.org/pdf/1904.06730v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-segmentation-on-multilabel-documents-a |
| Repo | |
| Framework | |
