October 18, 2019

2726 words 13 mins read

Paper Group ANR 529

Model-Driven Deep Learning for Physical Layer Communications. Putting Question-Answering Systems into Practice: Transfer Learning for Efficient Domain Customization. Trajectory Representation and Landmark Projection for Continuous-Time Structure from Motion. Visual-Inertial Object Detection and Mapping. Tsallis-INF: An Optimal Algorithm for Stochas …

Model-Driven Deep Learning for Physical Layer Communications


Title	Model-Driven Deep Learning for Physical Layer Communications
Authors	Hengtao He, Shi Jin, Chao-Kai Wen, Feifei Gao, Geoffrey Ye Li, Zongben Xu
Abstract	Intelligent communication is gradually considered as the mainstream direction in future wireless communications. As a major branch of machine learning, deep learning (DL) has been applied in physical layer communications and has demonstrated an impressive performance improvement in recent years. However, most of the existing works related to DL focus on data-driven approaches, which consider the communication system as a black box and train it by using a huge volume of data. Training a network requires sufficient computing resources and extensive time, both of which are rarely found in communication devices. By contrast, model-driven DL approaches combine communication domain knowledge with DL to reduce the demand for computing resources and training time. This article reviews the recent advancements in the application of model-driven DL approaches in physical layer communications, including transmission scheme, receiver design, and channel information recovery. Several open issues for further research are also highlighted after presenting the comprehensive survey.
Tasks
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06059v2
PDF	http://arxiv.org/pdf/1809.06059v2.pdf
PWC	https://paperswithcode.com/paper/model-driven-deep-learning-for-physical-layer
Repo
Framework

Putting Question-Answering Systems into Practice: Transfer Learning for Efficient Domain Customization


Title	Putting Question-Answering Systems into Practice: Transfer Learning for Efficient Domain Customization
Authors	Bernhard Kratzwald, Stefan Feuerriegel
Abstract	Traditional information retrieval (such as that offered by web search engines) impedes users with information overload from extensive result pages and the need to manually locate the desired information therein. Conversely, question-answering systems change how humans interact with information systems: users can now ask specific questions and obtain a tailored answer - both conveniently in natural language. Despite obvious benefits, their use is often limited to an academic context, largely because of expensive domain customizations, which means that the performance in domain-specific applications often fails to meet expectations. This paper proposes cost-efficient remedies: (i) we leverage metadata through a filtering mechanism, which increases the precision of document retrieval, and (ii) we develop a novel fuse-and-oversample approach for transfer learning in order to improve the performance of answer extraction. Here knowledge is inductively transferred from a related, yet different, tasks to the domain-specific application, while accounting for potential differences in the sample sizes across both tasks. The resulting performance is demonstrated with actual use cases from a finance company and the film industry, where fewer than 400 question-answer pairs had to be annotated in order to yield significant performance gains. As a direct implication to management, this presents a promising path to better leveraging of knowledge stored in information systems.
Tasks	Information Retrieval, Question Answering, Transfer Learning
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07097v2
PDF	http://arxiv.org/pdf/1804.07097v2.pdf
PWC	https://paperswithcode.com/paper/putting-question-answering-systems-into
Repo
Framework

Trajectory Representation and Landmark Projection for Continuous-Time Structure from Motion


Title	Trajectory Representation and Landmark Projection for Continuous-Time Structure from Motion
Authors	Hannes Ovrén, Per-Erik Forssén
Abstract	This paper revisits the problem of continuous-time structure from motion, and introduces a number of extensions that improve convergence and efficiency. The formulation with a $\mathcal{C}^2$-continuous spline for the trajectory naturally incorporates inertial measurements, as derivatives of the sought trajectory. We analyse the behaviour of split interpolation on $\mathbb{SO}(3)$ and on $\mathbb{R}^3$, and a joint interpolation on $\mathbb{SE}(3)$, and show that the latter implicitly couples the direction of translation and rotation. Such an assumption can make good sense for a camera mounted on a robot arm, but not for hand-held or body-mounted cameras. Our experiments show that split interpolation on $\mathbb{SO}(3)$ and on $\mathbb{R}^3$ is preferable over $\mathbb{SE}(3)$ interpolation in all tested cases. Finally, we investigate the problem of landmark reprojection on rolling shutter cameras, and show that the tested reprojection methods give similar quality, while their computational load varies by a factor of 2.
Tasks
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02543v1
PDF	http://arxiv.org/pdf/1805.02543v1.pdf
PWC	https://paperswithcode.com/paper/trajectory-representation-and-landmark
Repo
Framework

Visual-Inertial Object Detection and Mapping


Title	Visual-Inertial Object Detection and Mapping
Authors	Xiaohan Fei, Stefano Soatto
Abstract	We present a method to populate an unknown environment with models of previously seen objects, placed in a Euclidean reference frame that is inferred causally and on-line using monocular video along with inertial sensors. The system we implement returns a sparse point cloud for the regions of the scene that are visible but not recognized as a previously seen object, and a detailed object model and its pose in the Euclidean frame otherwise. The system includes bottom-up and top-down components, whereby deep networks trained for detection provide likelihood scores for object hypotheses provided by a nonlinear filter, whose state serves as memory. Additional networks provide likelihood scores for edges, which complements detection networks trained to be invariant to small deformations. We test our algorithm on existing datasets, and also introduce the VISMA dataset, that provides ground truth pose, point-cloud map, and object models, along with time-stamped inertial measurements.
Tasks	Object Detection
Published	2018-06-22
URL	http://arxiv.org/abs/1806.08498v2
PDF	http://arxiv.org/pdf/1806.08498v2.pdf
PWC	https://paperswithcode.com/paper/visual-inertial-object-detection-and-mapping
Repo
Framework

Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits


Title	Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits
Authors	Julian Zimmert, Yevgeny Seldin
Abstract	We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both adversarial and stochastic multi-armed bandits without prior knowledge of the regime and time horizon. The algorithm is based on online mirror descent (OMD) with Tsallis entropy regularization with power $\alpha=1/2$ and reduced-variance loss estimators. More generally, we define an adversarial regime with a self-bounding constraint, which includes stochastic regime, stochastically constrained adversarial regime (Wei and Luo), and stochastic regime with adversarial corruptions (Lykouris et al.) as special cases, and show that the algorithm achieves logarithmic regret guarantee in this regime and all of its special cases simultaneously with the adversarial regret guarantee.} The algorithm also achieves adversarial and stochastic optimality in the utility-based dueling bandit setting. We provide empirical evaluation of the algorithm demonstrating that it significantly outperforms UCB1 and EXP3 in stochastic environments. We also provide examples of adversarial environments, where UCB1 and Thompson Sampling exhibit almost linear regret, whereas our algorithm suffers only logarithmic regret. To the best of our knowledge, this is the first example demonstrating vulnerability of Thompson Sampling in adversarial environments. Last, but not least, we present a general stochastic analysis and a general adversarial analysis of OMD algorithms with Tsallis entropy regularization for $\alpha\in[0,1]$ and explain the reason why $\alpha=1/2$ works best.
Tasks	Multi-Armed Bandits
Published	2018-07-19
URL	https://arxiv.org/abs/1807.07623v4
PDF	https://arxiv.org/pdf/1807.07623v4.pdf
PWC	https://paperswithcode.com/paper/an-optimal-algorithm-for-stochastic-and
Repo
Framework

Image as Data: Automated Visual Content Analysis for Political Science


Title	Image as Data: Automated Visual Content Analysis for Political Science
Authors	Jungseock Joo, Zachary C. Steinert-Threlkeld
Abstract	Image data provide unique information about political events, actors, and their interactions which are difficult to measure from or not available in text data. This article introduces a new class of automated methods based on computer vision and deep learning which can automatically analyze visual content data. Scholars have already recognized the importance of visual data and a variety of large visual datasets have become available. The lack of scalable analytic methods, however, has prevented from incorporating large scale image data in political analysis. This article aims to offer an in-depth overview of automated methods for visual content analysis and explains their usages and implementations. We further elaborate on how these methods and results can be validated and interpreted. We then discuss how these methods can contribute to the study of political communication, identity and politics, development, and conflict, by enabling a new set of research questions at scale.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01544v1
PDF	http://arxiv.org/pdf/1810.01544v1.pdf
PWC	https://paperswithcode.com/paper/image-as-data-automated-visual-content
Repo
Framework

Generative adversarial networks and adversarial methods in biomedical image analysis


Title	Generative adversarial networks and adversarial methods in biomedical image analysis
Authors	Jelmer M. Wolterink, Konstantinos Kamnitsas, Christian Ledig, Ivana Išgum
Abstract	Generative adversarial networks (GANs) and other adversarial methods are based on a game-theoretical perspective on joint optimization of two neural networks as players in a game. Adversarial techniques have been extensively used to synthesize and analyze biomedical images. We provide an introduction to GANs and adversarial methods, with an overview of biomedical image analysis tasks that have benefited from such methods. We conclude with a discussion of strengths and limitations of adversarial methods in biomedical image analysis, and propose potential future research directions.
Tasks
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10352v1
PDF	http://arxiv.org/pdf/1810.10352v1.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-networks-and-2
Repo
Framework

Adversarially Learned Mixture Model


Title	Adversarially Learned Mixture Model
Authors	Andrew Jesson, Cécile Low-Kam, Florian Soudan, Nicolas Chapados
Abstract	The Adversarially Learned Mixture Model (AMM) is a generative model for unsupervised or semi-supervised data clustering. The AMM is the first adversarially optimized method to model the conditional dependence between inferred continuous and categorical latent variables. Experiments on the MNIST and SVHN datasets show that the AMM allows for semantic separation of complex data when little or no labeled data is available. The AMM achieves a state-of-the-art unsupervised clustering error rate of 2.86% on the MNIST dataset. A semi-supervised extension of the AMM yields competitive results on the SVHN dataset.
Tasks
Published	2018-07-14
URL	http://arxiv.org/abs/1807.05344v1
PDF	http://arxiv.org/pdf/1807.05344v1.pdf
PWC	https://paperswithcode.com/paper/adversarially-learned-mixture-model
Repo
Framework

WordNet-Based Information Retrieval Using Common Hypernyms and Combined Features


Title	WordNet-Based Information Retrieval Using Common Hypernyms and Combined Features
Authors	Vuong M. Ngo, Tru H. Cao, Tuan M. V. Le
Abstract	Text search based on lexical matching of keywords is not satisfactory due to polysemous and synonymous words. Semantic search that exploits word meanings, in general, improves search performance. In this paper, we survey WordNet-based information retrieval systems, which employ a word sense disambiguation method to process queries and documents. The problem is that in many cases a word has more than one possible direct sense, and picking only one of them may give a wrong sense for the word. Moreover, the previous systems use only word forms to represent word senses and their hypernyms. We propose a novel approach that uses the most specific common hypernym of the remaining undisambiguated multi-senses of a word, as well as combined WordNet features to represent word meanings. Experiments on a benchmark dataset show that, in terms of the MAP measure, our search engine is 17.7% better than the lexical search, and at least 9.4% better than all surveyed search systems using WordNet. Keywords Ontology, word sense disambiguation, semantic annotation, semantic search.
Tasks	Information Retrieval, Word Sense Disambiguation
Published	2018-07-15
URL	http://arxiv.org/abs/1807.05574v1
PDF	http://arxiv.org/pdf/1807.05574v1.pdf
PWC	https://paperswithcode.com/paper/wordnet-based-information-retrieval-using
Repo
Framework

Improving confidence while predicting trends in temporal disease networks


Title	Improving confidence while predicting trends in temporal disease networks
Authors	Djordje Gligorijevic, Jelena Stojanovic, Zoran Obradovic
Abstract	For highly sensitive real-world predictive analytic applications such as healthcare and medicine, having good prediction accuracy alone is often not enough. These kinds of applications require a decision making process which uses uncertainty estimation as input whenever possible. Quality of uncertainty estimation is a subject of over or under confident prediction, which is often not addressed in many models. In this paper we show several extensions to the Gaussian Conditional Random Fields model, which aim to provide higher quality uncertainty estimation. These extensions are applied to the temporal disease graph built from the State Inpatient Database (SID) of California, acquired from the HCUP. Our experiments demonstrate benefits of using graph information in modeling temporal disease properties as well as improvements in uncertainty estimation provided by given extensions of the Gaussian Conditional Random Fields method.
Tasks	Decision Making
Published	2018-03-28
URL	http://arxiv.org/abs/1803.11462v1
PDF	http://arxiv.org/pdf/1803.11462v1.pdf
PWC	https://paperswithcode.com/paper/improving-confidence-while-predicting-trends
Repo
Framework

String Transduction with Target Language Models and Insertion Handling


Title	String Transduction with Target Language Models and Insertion Handling
Authors	Garrett Nicolai, Saeed Najafi, Grzegorz Kondrak
Abstract	Many character-level tasks can be framed as sequence-to-sequence transduction, where the target is a word from a natural language. We show that leveraging target language models derived from unannotated target corpora, combined with a precise alignment of the training data, yields state-of-the art results on cognate projection, inflection generation, and phoneme-to-grapheme conversion.
Tasks
Published	2018-09-19
URL	http://arxiv.org/abs/1809.07182v1
PDF	http://arxiv.org/pdf/1809.07182v1.pdf
PWC	https://paperswithcode.com/paper/string-transduction-with-target-language
Repo
Framework

Modeling Friends and Foes


Title	Modeling Friends and Foes
Authors	Pedro A. Ortega, Shane Legg
Abstract	How can one detect friendly and adversarial behavior from raw data? Detecting whether an environment is a friend, a foe, or anything in between, remains a poorly understood yet desirable ability for safe and robust agents. This paper proposes a definition of these environmental “attitudes” based on an characterization of the environment’s ability to react to the agent’s private strategy. We define an objective function for a one-shot game that allows deriving the environment’s probability distribution under friendly and adversarial assumptions alongside the agent’s optimal strategy. Furthermore, we present an algorithm to compute these equilibrium strategies, and show experimentally that both friendly and adversarial environments possess non-trivial optimal strategies.
Tasks
Published	2018-06-30
URL	http://arxiv.org/abs/1807.00196v1
PDF	http://arxiv.org/pdf/1807.00196v1.pdf
PWC	https://paperswithcode.com/paper/modeling-friends-and-foes
Repo
Framework

Sentence Encoding with Tree-constrained Relation Networks


Title	Sentence Encoding with Tree-constrained Relation Networks
Authors	Lei Yu, Cyprien de Masson d’Autume, Chris Dyer, Phil Blunsom, Lingpeng Kong, Wang Ling
Abstract	The meaning of a sentence is a function of the relations that hold between its words. We instantiate this relational view of semantics in a series of neural models based on variants of relation networks (RNs) which represent a set of objects (for us, words forming a sentence) in terms of representations of pairs of objects. We propose two extensions to the basic RN model for natural language. First, building on the intuition that not all word pairs are equally informative about the meaning of a sentence, we use constraints based on both supervised and unsupervised dependency syntax to control which relations influence the representation. Second, since higher-order relations are poorly captured by a sum of pairwise relations, we use a recurrent extension of RNs to propagate information so as to form representations of higher order relations. Experiments on sentence classification, sentence pair classification, and machine translation reveal that, while basic RNs are only modestly effective for sentence representation, recurrent RNs with latent syntax are a reliably powerful representational device.
Tasks	Machine Translation, Sentence Classification
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10475v1
PDF	http://arxiv.org/pdf/1811.10475v1.pdf
PWC	https://paperswithcode.com/paper/sentence-encoding-with-tree-constrained
Repo
Framework

Interpretable Credit Application Predictions With Counterfactual Explanations


Title	Interpretable Credit Application Predictions With Counterfactual Explanations
Authors	Rory Mc Grath, Luca Costabello, Chan Le Van, Paul Sweeney, Farbod Kamiab, Zhao Shen, Freddy Lecue
Abstract	We predict credit applications with off-the-shelf, interchangeable black-box classifiers and we explain single predictions with counterfactual explanations. Counterfactual explanations expose the minimal changes required on the input data to obtain a different result e.g., approved vs rejected application. Despite their effectiveness, counterfactuals are mainly designed for changing an undesired outcome of a prediction i.e. loan rejected. Counterfactuals, however, can be difficult to interpret, especially when a high number of features are involved in the explanation. Our contribution is two-fold: i) we propose positive counterfactuals, i.e. we adapt counterfactual explanations to also explain accepted loan applications, and ii) we propose two weighting strategies to generate more interpretable counterfactuals. Experiments on the HELOC loan applications dataset show that our contribution outperforms the baseline counterfactual generation strategy, by leading to smaller and hence more interpretable counterfactuals.
Tasks
Published	2018-11-13
URL	http://arxiv.org/abs/1811.05245v2
PDF	http://arxiv.org/pdf/1811.05245v2.pdf
PWC	https://paperswithcode.com/paper/interpretable-credit-application-predictions
Repo
Framework

ML-Schema: Exposing the Semantics of Machine Learning with Schemas and Ontologies


Title	ML-Schema: Exposing the Semantics of Machine Learning with Schemas and Ontologies
Authors	Gustavo Correa Publio, Diego Esteves, Agnieszka Ławrynowicz, Panče Panov, Larisa Soldatova, Tommaso Soru, Joaquin Vanschoren, Hamid Zafar
Abstract	The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments. It can be easily extended and specialized and it is also mapped to other more domain-specific ontologies developed in the area of machine learning and data mining. In this paper we overview existing state-of-the-art machine learning interchange formats and present the first release of ML-Schema, a canonical format resulted of more than seven years of experience among different research institutions. We argue that exposing semantics of machine learning algorithms, models, and experiments through a canonical format may pave the way to better interpretability and to realistically achieve the full interoperability of experiments regardless of platform or adopted workflow solution.
Tasks
Published	2018-07-14
URL	http://arxiv.org/abs/1807.05351v1
PDF	http://arxiv.org/pdf/1807.05351v1.pdf
PWC	https://paperswithcode.com/paper/ml-schema-exposing-the-semantics-of-machine
Repo
Framework