Skip to main navigation Skip to search Skip to main content

Submodularity on Hypergraphs: From Sets to Sequences

Research output: Contribution to journalConference articlepeer-review

Abstract

In a nutshell, submodular functions encode an intuitive notion of diminishing returns. As a result, submodularity appears in many important machine learning tasks such as feature selection and data summarization. Although there has been a large volume of work devoted to the study of submodular functions in recent years, the vast majority of this work has been focused on algorithms that output sets, not sequences. However, in many settings, the order in which we output items can be just as important as the items themselves. To extend the notion of submodularity to sequences, we use a directed graph on the items where the edges encode the additional value of selecting items in a particular order. Existing theory is limited to the case where this underlying graph is a directed acyclic graph. In this paper, we introduce two new algorithms that provably give constant factor approximations for general graphs and hypergraphs having bounded in or out degrees. Furthermore, we show the utility of our new algorithms for real-world applications in movie recommendation, online link prediction, and the design of course sequences for MOOCs.

Original languageEnglish
JournalProceedings of Machine Learning Research
Volume84
StatePublished - 2018
Externally publishedYes
Event21st International Conference on Artificial Intelligence and Statistics, AISTATS 2018 - Playa Blanca, Lanzarote, Canary Islands, Spain
Duration: 9 Apr 201811 Apr 2018

Bibliographical note

Publisher Copyright:
© 2018 by the author(s).

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Submodularity on Hypergraphs: From Sets to Sequences'. Together they form a unique fingerprint.

Cite this