Kernel-Based Models for Influence Maximization on Graphs based on Gaussian Process Variance Minimization

The inference of novel knowledge, the discovery of hidden patterns, and the uncovering of insights from large amounts of data from a multitude of sources make Data Science (DS) to an art rather than just a mere scientific discipline. The study and design of mathematical models able to analyze information represents a central research topic in DS. In this work, we introduce and investigate a novel model for influence maximization (IM) on graphs using ideas from kernel-based approximation, Gaussian process regression, and the minimization of a corresponding variance term. Datadriven approaches can be applied to determine proper kernels for this IM model and machine learning methodologies are adopted to tune the model parameters. Compared to stochastic models in this field that rely on costly Monte-Carlo simulations, our model allows for a simple and cost-efficient update strategy to compute optimal influencing nodes on a graph. In several numerical experiments, we show the properties and benefits of this new model.

[1]  Pierre Vandergheynst,et al.  Stationary Signal Processing on Graphs , 2016, IEEE Transactions on Signal Processing.

[2]  Gordon F. Royle,et al.  Algebraic Graph Theory , 2001, Graduate texts in mathematics.

[3]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[4]  Holger Wendland,et al.  Near-optimal data-independent point locations for radial basis function interpolation , 2005, Adv. Comput. Math..

[5]  I. Rodríguez‐Iturbe,et al.  Random Functions and Hydrology , 1984 .

[6]  Yilong Yin,et al.  Learning to Learn Kernels with Variational Random Features , 2020, ICML.

[7]  B. Haasdonk,et al.  Greedy Algorithms for Matrix-Valued Kernels , 2017, Lecture Notes in Computational Science and Engineering.

[8]  Donald E. Scheck,et al.  Optimum locations for exploratory drill holes , 1983 .

[9]  G. Wahba.  Spline models for observational data , 1990 .

[10]  Bernard Haasdonk,et al.  A novel class of stabilized greedy kernel approximation algorithms: Convergence, stability & uniform point distribution , 2021, J. Approx. Theory.

[11]  G. Santin,et al.  Kernel Methods for Surrogate Modeling , 2019, System- and Data-Driven Methods and Algorithms.

[12]  Gianlorenzo D'Angelo,et al.  Influence Maximization in the Independent Cascade Model , 2016, ICTCS.

[13]  Robert Schaback,et al.  Error estimates and condition numbers for radial basis function interpolation , 1995, Adv. Comput. Math..

[14]  Wolfgang Erb,et al.  Graph signal interpolation with Positive Definite Graph Basis Functions , 2019, Applied and Computational Harmonic Analysis.

[15]  Roberto Cavoretto,et al.  Partition of Unity Methods for Signal Processing on Graphs , 2020, Journal of Fourier Analysis and Applications.

[16]  Marc Levoy,et al.  A volumetric method for building complex models from range images , 1996, SIGGRAPH.

[17]  Gregory E. Fasshauer,et al.  Kernel-based Approximation Methods using MATLAB , 2015, Interdisciplinary Mathematical Sciences.

[18]  Aric Hagberg,et al.  Exploring Network Structure, Dynamics, and Function using NetworkX , 2008, Proceedings of the Python in Science Conference.

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

[20]  Pierre Vandergheynst,et al.  Vertex-Frequency Analysis on Graphs , 2013, ArXiv.

[21]  Isaac Z. Pesenson,et al.  Variational Splines and Paley–Wiener Spaces on Combinatorial Graphs , 2009, ArXiv.

[22]  Robert Schaback,et al.  Bases for kernel-based spaces , 2011, J. Comput. Appl. Math..

[23]  Joseph D. Ward,et al.  Interpolating splines on graphs for data science applications , 2018, Applied and Computational Harmonic Analysis.

[24]  Yiming Yang,et al.  Implicit Kernel Learning , 2019, AISTATS.

[25]  Matthew Richardson,et al.  Mining the network value of customers , 2001, KDD '01.

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

[27]  Bernard Haasdonk,et al.  Convergence rate of the data-independent P-greedy algorithm in kernel-based approximation , 2016, 1612.02672.

[28]  Pierre Vandergheynst,et al.  Graph Signal Processing: Overview, Challenges, and Applications , 2017, Proceedings of the IEEE.

[29]  Leonhard Held,et al.  Gaussian Markov Random Fields: Theory and Applications , 2005 .

[30]  U. Feige,et al.  Spectral Graph Theory , 2015 .

[31]  Wolfgang Erb,et al.  Semi-Supervised Learning on Graphs with Feature-Augmented Graph Basis Functions , 2020, ArXiv.

[32]  Holger Wendland,et al.  Approximation by positive definite kernels , 2002 .

[33]  M. Urner.  Scattered Data Approximation , 2016 .

[34]  Ljubisa Stankovic,et al.  Introduction to Graph Signal Processing , 2018, Signals and Communication Technology.

[35]  Wolfgang Erb,et al.  Shapes of Uncertainty in Spectral Graph Theory , 2019, IEEE Transactions on Information Theory.

[36]  John D. Lafferty,et al.  Diffusion Kernels on Graphs and Other Discrete Input Spaces , 2002, ICML.