Paper Group ANR 103
A Signaling Game Approach to Databases Querying and Interaction. 25 years of CNNs: Can we compare to human abstraction capabilities?. Veracity Computing from Lexical Cues and Perceived Certainty Trends. A Transportation $L^p$ Distance for Signal Analysis. Learning Infinite-Layer Networks: Without the Kernel Trick. Beyond Local Search: Tracking Obje …
A Signaling Game Approach to Databases Querying and Interaction
| Title | A Signaling Game Approach to Databases Querying and Interaction |
| Authors | Ben McCamish, Vahid Ghadakchi, Arash Termehchy, Behrouz Touri |
| Abstract | As most users do not precisely know the structure and/or the content of databases, their queries do not exactly reflect their information needs. The database management systems (DBMS) may interact with users and use their feedback on the returned results to learn the information needs behind their queries. Current query interfaces assume that users do not learn and modify the way way they express their information needs in form of queries during their interaction with the DBMS. Using a real-world interaction workload, we show that users learn and modify how to express their information needs during their interactions with the DBMS and their learning is accurately modeled by a well-known reinforcement learning mechanism. As current data interaction systems assume that users do not modify their strategies, they cannot discover the information needs behind users’ queries effectively. We model the interaction between users and DBMS as a game with identical interest between two rational agents whose goal is to establish a common language for representing information needs in form of queries. We propose a reinforcement learning method that learns and answers the information needs behind queries and adapts to the changes in users’ strategies and prove that it improves the effectiveness of answering queries stochastically speaking. We propose two efficient implementation of this method over large relational databases. Our extensive empirical studies over real-world query workloads indicate that our algorithms are efficient and effective. |
| Tasks | |
| Published | 2016-03-13 |
| URL | http://arxiv.org/abs/1603.04068v5 |
| http://arxiv.org/pdf/1603.04068v5.pdf | |
| PWC | https://paperswithcode.com/paper/a-signaling-game-approach-to-databases |
| Repo | |
| Framework | |
25 years of CNNs: Can we compare to human abstraction capabilities?
| Title | 25 years of CNNs: Can we compare to human abstraction capabilities? |
| Authors | Sebastian Stabinger, Antonio Rodríguez-Sánchez, Justus Piater |
| Abstract | We try to determine the progress made by convolutional neural networks over the past 25 years in classifying images into abstractc lasses. For this purpose we compare the performance of LeNet to that of GoogLeNet at classifying randomly generated images which are differentiated by an abstract property (e.g., one class contains two objects of the same size, the other class two objects of different sizes). Our results show that there is still work to do in order to solve vision problems humans are able to solve without much difficulty. |
| Tasks | |
| Published | 2016-07-28 |
| URL | http://arxiv.org/abs/1607.08366v1 |
| http://arxiv.org/pdf/1607.08366v1.pdf | |
| PWC | https://paperswithcode.com/paper/25-years-of-cnns-can-we-compare-to-human |
| Repo | |
| Framework | |
Veracity Computing from Lexical Cues and Perceived Certainty Trends
| Title | Veracity Computing from Lexical Cues and Perceived Certainty Trends |
| Authors | Uwe D. Reichel, Piroska Lendvai |
| Abstract | We present a data-driven method for determining the veracity of a set of rumorous claims on social media data. Tweets from different sources pertaining to a rumor are processed on three levels: first, factuality values are assigned to each tweet based on four textual cue categories relevant for our journalism use case; these amalgamate speaker support in terms of polarity and commitment in terms of certainty and speculation. Next, the proportions of these lexical cues are utilized as predictors for tweet certainty in a generalized linear regression model. Subsequently, lexical cue proportions, predicted certainty, as well as their time course characteristics are used to compute veracity for each rumor in terms of the identity of the rumor-resolving tweet and its binary resolution value judgment. The system operates without access to extralinguistic resources. Evaluated on the data portion for which hand-labeled examples were available, it achieves .74 F1-score on identifying rumor resolving tweets and .76 F1-score on predicting if a rumor is resolved as true or false. |
| Tasks | |
| Published | 2016-11-08 |
| URL | http://arxiv.org/abs/1611.02590v2 |
| http://arxiv.org/pdf/1611.02590v2.pdf | |
| PWC | https://paperswithcode.com/paper/veracity-computing-from-lexical-cues-and |
| Repo | |
| Framework | |
A Transportation $L^p$ Distance for Signal Analysis
| Title | A Transportation $L^p$ Distance for Signal Analysis |
| Authors | Matthew Thorpe, Serim Park, Soheil Kolouri, Gustavo K. Rohde, Dejan Slepčev |
| Abstract | Transport based distances, such as the Wasserstein distance and earth mover’s distance, have been shown to be an effective tool in signal and image analysis. The success of transport based distances is in part due to their Lagrangian nature which allows it to capture the important variations in many signal classes. However these distances require the signal to be nonnegative and normalized. Furthermore, the signals are considered as measures and compared by redistributing (transporting) them, which does not directly take into account the signal intensity. Here we study a transport-based distance, called the $TL^p$ distance, that combines Lagrangian and intensity modelling and is directly applicable to general, non-positive and multi-channelled signals. The framework allows the application of existing numerical methods. We give an overview of the basic properties of this distance and applications to classification, with multi-channelled, non-positive one and two-dimensional signals, and color transfer. |
| Tasks | |
| Published | 2016-09-27 |
| URL | http://arxiv.org/abs/1609.08669v1 |
| http://arxiv.org/pdf/1609.08669v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-transportation-lp-distance-for-signal |
| Repo | |
| Framework | |
Learning Infinite-Layer Networks: Without the Kernel Trick
| Title | Learning Infinite-Layer Networks: Without the Kernel Trick |
| Authors | Roi Livni, Daniel Carmon, Amir Globerson |
| Abstract | Infinite–Layer Networks (ILN) have recently been proposed as an architecture that mimics neural networks while enjoying some of the advantages of kernel methods. ILN are networks that integrate over infinitely many nodes within a single hidden layer. It has been demonstrated by several authors that the problem of learning ILN can be reduced to the kernel trick, implying that whenever a certain integral can be computed analytically they are efficiently learnable. In this work we give an online algorithm for ILN, which avoids the kernel trick assumption. More generally and of independent interest, we show that kernel methods in general can be exploited even when the kernel cannot be efficiently computed but can only be estimated via sampling. We provide a regret analysis for our algorithm, showing that it matches the sample complexity of methods which have access to kernel values. Thus, our method is the first to demonstrate that the kernel trick is not necessary as such, and random features suffice to obtain comparable performance. |
| Tasks | |
| Published | 2016-06-16 |
| URL | http://arxiv.org/abs/1606.05316v2 |
| http://arxiv.org/pdf/1606.05316v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-infinite-layer-networks-without-the-1 |
| Repo | |
| Framework | |
Beyond Local Search: Tracking Objects Everywhere with Instance-Specific Proposals
| Title | Beyond Local Search: Tracking Objects Everywhere with Instance-Specific Proposals |
| Authors | Gao Zhu, Fatih Porikli, Hongdong Li |
| Abstract | Most tracking-by-detection methods employ a local search window around the predicted object location in the current frame assuming the previous location is accurate, the trajectory is smooth, and the computational capacity permits a search radius that can accommodate the maximum speed yet small enough to reduce mismatches. These, however, may not be valid always, in particular for fast and irregularly moving objects. Here, we present an object tracker that is not limited to a local search window and has ability to probe efficiently the entire frame. Our method generates a small number of “high-quality” proposals by a novel instance-specific objectness measure and evaluates them against the object model that can be adopted from an existing tracking-by-detection approach as a core tracker. During the tracking process, we update the object model concentrating on hard false-positives supplied by the proposals, which help suppressing distractors caused by difficult background clutters, and learn how to re-rank proposals according to the object model. Since we reduce significantly the number of hypotheses the core tracker evaluates, we can use richer object descriptors and stronger detector. Our method outperforms most recent state-of-the-art trackers on popular tracking benchmarks, and provides improved robustness for fast moving objects as well as for ultra low-frame-rate videos. |
| Tasks | |
| Published | 2016-05-06 |
| URL | http://arxiv.org/abs/1605.01839v1 |
| http://arxiv.org/pdf/1605.01839v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-local-search-tracking-objects |
| Repo | |
| Framework | |
Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets
| Title | Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets |
| Authors | Jaekoo Lee, Hyunjae Kim, Jongsun Lee, Sungroh Yoon |
| Abstract | Graphs provide a powerful means for representing complex interactions between entities. Recently, deep learning approaches are emerging for representing and modeling graph-structured data, although the conventional deep learning methods (such as convolutional neural networks and recurrent neural networks) have mainly focused on grid-structured inputs (image and audio). Leveraged by the capability of representation learning, deep learning based techniques are reporting promising results for graph applications by detecting structural characteristics of graphs in an automated fashion. In this paper, we attempt to advance deep learning for graph-structured data by incorporating another component, transfer learning. By transferring the intrinsic geometric information learned in the source domain, our approach can help us to construct a model for a new but related task in the target domain without collecting new data and without training a new model from scratch. We thoroughly test our approach with large-scale real corpora and confirm the effectiveness of the proposed transfer learning framework for deep learning on graphs. According to our experiments, transfer learning is most effective when the source and target domains bear a high level of structural similarity in their graph representations. |
| Tasks | Representation Learning, Transfer Learning |
| Published | 2016-11-15 |
| URL | http://arxiv.org/abs/1611.04687v2 |
| http://arxiv.org/pdf/1611.04687v2.pdf | |
| PWC | https://paperswithcode.com/paper/intrinsic-geometric-information-transfer |
| Repo | |
| Framework | |
A Review of Intelligent Practices for Irrigation Prediction
| Title | A Review of Intelligent Practices for Irrigation Prediction |
| Authors | Hans Krupakar, Akshay Jayakumar, Dhivya G |
| Abstract | Population growth and increasing droughts are creating unprecedented strain on the continued availability of water resources. Since irrigation is a major consumer of fresh water, wastage of resources in this sector could have strong consequences. To address this issue, irrigation water management and prediction techniques need to be employed effectively and should be able to account for the variabilities present in the environment. The different techniques surveyed in this paper can be classified into two categories: computational and statistical. Computational methods deal with scientific correlations between physical parameters whereas statistical methods involve specific prediction algorithms that can be used to automate the process of irrigation water prediction. These algorithms interpret semantic relationships between the various parameters of temperature, pressure, evapotranspiration etc. and store them as numerical precomputed entities specific to the conditions and the area used as the data for the training corpus used to train it. We focus on reviewing the computational methods used to determine Evapotranspiration and its implications. We compare the efficiencies of different data mining and machine learning methods implemented in this area, such as Logistic Regression, Decision Tress Classifier, SysFor, Support Vector Machine(SVM), Fuzzy Logic techniques, Artifical Neural Networks(ANNs) and various hybrids of Genetic Algorithms (GA) applied to irrigation prediction. We also recommend a possible technique for the same based on its superior results in other such time series analysis tasks. |
| Tasks | Time Series, Time Series Analysis |
| Published | 2016-12-07 |
| URL | http://arxiv.org/abs/1612.02893v1 |
| http://arxiv.org/pdf/1612.02893v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-review-of-intelligent-practices-for |
| Repo | |
| Framework | |
Convex Optimization For Non-Convex Problems via Column Generation
| Title | Convex Optimization For Non-Convex Problems via Column Generation |
| Authors | Julian Yarkony, Kamalika Chaudhuri |
| Abstract | We apply column generation to approximating complex structured objects via a set of primitive structured objects under either the cross entropy or L2 loss. We use L1 regularization to encourage the use of few structured primitive objects. We attack approximation using convex optimization over an infinite number of variables each corresponding to a primitive structured object that are generated on demand by easy inference in the Lagrangian dual. We apply our approach to producing low rank approximations to large 3-way tensors. |
| Tasks | |
| Published | 2016-02-14 |
| URL | http://arxiv.org/abs/1602.04409v1 |
| http://arxiv.org/pdf/1602.04409v1.pdf | |
| PWC | https://paperswithcode.com/paper/convex-optimization-for-non-convex-problems |
| Repo | |
| Framework | |
Retrieving and Ranking Similar Questions from Question-Answer Archives Using Topic Modelling and Topic Distribution Regression
| Title | Retrieving and Ranking Similar Questions from Question-Answer Archives Using Topic Modelling and Topic Distribution Regression |
| Authors | Pedro Chahuara, Thomas Lampert, Pierre Gancarski |
| Abstract | Presented herein is a novel model for similar question ranking within collaborative question answer platforms. The presented approach integrates a regression stage to relate topics derived from questions to those derived from question-answer pairs. This helps to avoid problems caused by the differences in vocabulary used within questions and answers, and the tendency for questions to be shorter than answers. The performance of the model is shown to outperform translation methods and topic modelling (without regression) on several real-world datasets. |
| Tasks | |
| Published | 2016-06-12 |
| URL | http://arxiv.org/abs/1606.03783v1 |
| http://arxiv.org/pdf/1606.03783v1.pdf | |
| PWC | https://paperswithcode.com/paper/retrieving-and-ranking-similar-questions-from |
| Repo | |
| Framework | |
Scalable Group Level Probabilistic Sparse Factor Analysis
| Title | Scalable Group Level Probabilistic Sparse Factor Analysis |
| Authors | Jesper L. Hinrich, Søren F. V. Nielsen, Nicolai A. B. Riis, Casper T. Eriksen, Jacob Frøsig, Marco D. F. Kristensen, Mikkel N. Schmidt, Kristoffer H. Madsen, Morten Mørup |
| Abstract | Many data-driven approaches exist to extract neural representations of functional magnetic resonance imaging (fMRI) data, but most of them lack a proper probabilistic formulation. We propose a group level scalable probabilistic sparse factor analysis (psFA) allowing spatially sparse maps, component pruning using automatic relevance determination (ARD) and subject specific heteroscedastic spatial noise modeling. For task-based and resting state fMRI, we show that the sparsity constraint gives rise to components similar to those obtained by group independent component analysis. The noise modeling shows that noise is reduced in areas typically associated with activation by the experimental design. The psFA model identifies sparse components and the probabilistic setting provides a natural way to handle parameter uncertainties. The variational Bayesian framework easily extends to more complex noise models than the presently considered. |
| Tasks | |
| Published | 2016-12-14 |
| URL | http://arxiv.org/abs/1612.04555v1 |
| http://arxiv.org/pdf/1612.04555v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-group-level-probabilistic-sparse |
| Repo | |
| Framework | |
Leveraging Visual Question Answering for Image-Caption Ranking
| Title | Leveraging Visual Question Answering for Image-Caption Ranking |
| Authors | Xiao Lin, Devi Parikh |
| Abstract | Visual Question Answering (VQA) is the task of taking as input an image and a free-form natural language question about the image, and producing an accurate answer. In this work we view VQA as a “feature extraction” module to extract image and caption representations. We employ these representations for the task of image-caption ranking. Each feature dimension captures (imagines) whether a fact (question-answer pair) could plausibly be true for the image and caption. This allows the model to interpret images and captions from a wide variety of perspectives. We propose score-level and representation-level fusion models to incorporate VQA knowledge in an existing state-of-the-art VQA-agnostic image-caption ranking model. We find that incorporating and reasoning about consistency between images and captions significantly improves performance. Concretely, our model improves state-of-the-art on caption retrieval by 7.1% and on image retrieval by 4.4% on the MSCOCO dataset. |
| Tasks | Image Retrieval, Question Answering, Visual Question Answering |
| Published | 2016-05-04 |
| URL | http://arxiv.org/abs/1605.01379v2 |
| http://arxiv.org/pdf/1605.01379v2.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-visual-question-answering-for |
| Repo | |
| Framework | |
Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems
| Title | Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems |
| Authors | Zi Wang, Stefanie Jegelka, Leslie Pack Kaelbling, Tomás Lozano-Pérez |
| Abstract | We introduce a framework for model learning and planning in stochastic domains with continuous state and action spaces and non-Gaussian transition models. It is efficient because (1) local models are estimated only when the planner requires them; (2) the planner focuses on the most relevant states to the current planning problem; and (3) the planner focuses on the most informative and/or high-value actions. Our theoretical analysis shows the validity and asymptotic optimality of the proposed approach. Empirically, we demonstrate the effectiveness of our algorithm on a simulated multi-modal pushing problem. |
| Tasks | |
| Published | 2016-07-26 |
| URL | http://arxiv.org/abs/1607.07762v4 |
| http://arxiv.org/pdf/1607.07762v4.pdf | |
| PWC | https://paperswithcode.com/paper/focused-model-learning-and-planning-for-non |
| Repo | |
| Framework | |
Convergence rate of stochastic k-means
| Title | Convergence rate of stochastic k-means |
| Authors | Cheng Tang, Claire Monteleoni |
| Abstract | We analyze online and mini-batch k-means variants. Both scale up the widely used Lloyd ‘s algorithm via stochastic approximation, and have become popular for large-scale clustering and unsupervised feature learning. We show, for the first time, that they have global convergence towards local optima at $O(\frac{1}{t})$ rate under general conditions. In addition, we show if the dataset is clusterable, with suitable initialization, mini-batch k-means converges to an optimal k-means solution with $O(\frac{1}{t})$ convergence rate with high probability. The k-means objective is non-convex and non-differentiable: we exploit ideas from non-convex gradient-based optimization by providing a novel characterization of the trajectory of k-means algorithm on its solution space, and circumvent its non-differentiability via geometric insights about k-means update. |
| Tasks | |
| Published | 2016-10-16 |
| URL | http://arxiv.org/abs/1610.04900v2 |
| http://arxiv.org/pdf/1610.04900v2.pdf | |
| PWC | https://paperswithcode.com/paper/convergence-rate-of-stochastic-k-means-1 |
| Repo | |
| Framework | |
Highly Accurate Prediction of Jobs Runtime Classes
| Title | Highly Accurate Prediction of Jobs Runtime Classes |
| Authors | Anat Reiner-Benaim, Anna Grabarnick, Edi Shmueli |
| Abstract | Separating the short jobs from the long is a known technique to improve scheduling performance. In this paper we describe a method we developed for accurately predicting the runtimes classes of the jobs to enable this separation. Our method uses the fact that the runtimes can be represented as a mixture of overlapping Gaussian distributions, in order to train a CART classifier to provide the prediction. The threshold that separates the short jobs from the long jobs is determined during the evaluation of the classifier to maximize prediction accuracy. Our results indicate overall accuracy of 90% for the data set used in our study, with sensitivity and specificity both above 90%. |
| Tasks | |
| Published | 2016-05-02 |
| URL | http://arxiv.org/abs/1605.00388v2 |
| http://arxiv.org/pdf/1605.00388v2.pdf | |
| PWC | https://paperswithcode.com/paper/highly-accurate-prediction-of-jobs-runtime |
| Repo | |
| Framework | |
