Arrow Research search

Author name cluster

Dmitry Pavlov

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers
2 author rows

Possible papers

5

KER Journal 2018 Journal Article

Ontology visualization methods and tools: a survey of the state of the art

  • Marek Dudáš
  • Steffen Lohmann
  • Vojtěch Svátek
  • Dmitry Pavlov

Abstract Various ontology visualization tools using different visualization methods exist and new ones are being developed every year. The goal of this paper is to follow up on previous surveys with an updated classification of ontology visualization methods and a comprehensive survey of available tools. The tools are analyzed for the used visualization methods, interaction techniques and supported ontology constructs. It shows that most of the tools apply two-dimensional node-link visualizations with a focus on class hierarchies. Color and shape are used with little variation, support for constructs introduced with version 2 of the OWL Web Ontology Language is limited, and it often remains vague what tasks and use cases are supported by the visualizations. Major challenges are the limited maturity and usability of many of the tools as well as providing an overview of large ontologies while also showing details on demand. We see a high demand for a universal ontology visualization framework implementing a core set of visual and interactive features that can be extended and customized to respective use cases.

Details DOI

NeurIPS Conference 2009 Conference Paper

Factor Modeling for Advertisement Targeting

  • Ye Chen
  • Michael Kapralov
  • John Canny
  • Dmitry Pavlov

We adapt a probabilistic latent variable model, namely GaP (Gamma-Poisson), to ad targeting in the contexts of sponsored search (SS) and behaviorally targeted (BT) display advertising. We also approach the important problem of ad positional bias by formulating a one-latent-dimension GaP factorization. Learning from click-through data is intrinsically large scale, even more so for ads. We scale up the algorithm to terabytes of real-world SS and BT data that contains hundreds of millions of users and hundreds of thousands of features, by leveraging the scalability characteristics of the algorithm and the inherent structure of the problem including data sparsity and locality. Specifically, we demonstrate two somewhat orthogonal philosophies of scaling algorithms to large-scale problems, through the SS and BT implementations, respectively. Finally, we report the experimental results using Yahoos vast datasets, and show that our approach substantially outperform the state-of-the-art methods in prediction accuracy. For BT in particular, the ROC area achieved by GaP is exceeding 0. 95, while one prior approach using Poisson regression yielded 0. 83. For computational performance, we compare a single-node sparse implementation with a parallel implementation using Hadoop MapReduce, the results are counterintuitive yet quite interesting. We therefore provide insights into the underlying principles of large-scale learning.

PDF Details

NeurIPS Conference 2002 Conference Paper

A Maximum Entropy Approach to Collaborative Filtering in Dynamic, Sparse, High-Dimensional Domains

  • Dmitry Pavlov
  • David Pennock

We develop a maximum entropy (maxent) approach to generating recom- mendations in the context of a user’s current navigation stream, suitable for environments where data is sparse, high-dimensional, and dynamic— conditions typical of many recommendation applications. We address sparsity and dimensionality reduction by first clustering items based on user access patterns so as to attempt to minimize the apriori probabil- ity that recommendations will cross cluster boundaries and then recom- mending only within clusters. We address the inherent dynamic nature of the problem by explicitly modeling the data as a time series; we show how this representational expressivity fits naturally into a maxent frame- work. We conduct experiments on data from ResearchIndex, a popu- lar online repository of over 470, 000 computer science documents. We show that our maxent formulation outperforms several competing algo- rithms in offline tests simulating the recommendation of documents to ResearchIndex users.

PDF Details