Submodularity on Hypergraphs: From Sets to Sequences

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.

[1]  Hui Lin,et al.  A Class of Submodular Functions for Document Summarization , 2011, ACL.

[2]  Andreas Krause,et al.  Near-Optimally Teaching the Crowd to Classify , 2014, ICML.

[3]  Andreas Krause,et al.  Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization , 2010, J. Artif. Intell. Res..

[4]  M. L. Fisher,et al.  An analysis of approximations for maximizing submodular set functions—I , 1978, Math. Program..

[5]  Jeff A. Bilmes,et al.  Submodularity for Data Selection in Statistical Machine Translation , 2014 .

[6]  Francis Bach,et al.  Submodular functions: from discrete to continuous domains , 2015, Mathematical Programming.

[7]  Alexandros G. Dimakis,et al.  Streaming Weak Submodularity: Interpreting Neural Networks on the Fly , 2017, NIPS.

[8]  G. Nemhauser,et al.  Maximizing Submodular Set Functions: Formulations and Analysis of Algorithms* , 1981 .

[9]  Éva Tardos,et al.  Maximizing the Spread of Influence through a Social Network , 2015, Theory Comput..

[10]  Edwin K. P. Chong,et al.  String Submodular Functions With Curvature Constraints , 2013, IEEE Transactions on Automatic Control.

[11]  Andreas Krause,et al.  Distributed Submodular Maximization , 2014, J. Mach. Learn. Res..

[12]  V. Nagarajan,et al.  MAXIMIZING NON-MONOTONE SUBMODULAR FUNCTIONS UNDER MATROID AND KNAPSACK CONSTRAINTS , 2007 .

[13]  M. Kendall A NEW MEASURE OF RANK CORRELATION , 1938 .

[14]  Andreas Krause,et al.  Near-optimal Nonmyopic Value of Information in Graphical Models , 2005, UAI.

[15]  Pushmeet Kohli,et al.  Tractability: Practical Approaches to Hard Problems , 2013 .

[16]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[17]  Laurence A. Wolsey,et al.  An analysis of the greedy algorithm for the submodular set covering problem , 1982, Comb..

[18]  Justin Reich,et al.  HarvardX and MITx: The First Year of Open Online Courses, Fall 2012-Summer 2013 , 2014 .

[19]  Joseph Naor,et al.  Submodular Maximization with Cardinality Constraints , 2014, SODA.

[20]  Vahab Mirrokni,et al.  Maximizing Non-Monotone Submodular Functions , 2007, FOCS 2007.

[21]  Azarakhsh Malekian,et al.  Maximizing Sequence-Submodular Functions and its Application to Online Advertising , 2010, Manag. Sci..

[22]  Andreas Krause,et al.  Selecting Sequences of Items via Submodular Maximization , 2017, AAAI.

[23]  Abhimanyu Das,et al.  Submodular meets Spectral: Greedy Algorithms for Subset Selection, Sparse Approximation and Dictionary Selection , 2011, ICML.

[24]  Zheng Wen,et al.  Adaptive Submodular Maximization in Bandit Setting , 2013, NIPS.

[25]  藤重 悟 Submodular functions and optimization , 1991 .

[26]  Olgica Milenkovic,et al.  Inhomogeneous Hypergraph Clustering with Applications , 2017, NIPS.

[27]  Jure Leskovec,et al.  Inferring networks of diffusion and influence , 2010, KDD.