Learning Laplacian Matrix in Smooth Graph Signal Representations

被引:412
|
作者
Dong, Xiaowen [1 ]
Thanou, Dorina [2 ]
Frossard, Pascal [2 ]
Vandergheynst, Pierre [2 ]
机构
[1] MIT, Media Lab, Cambridge, MA 02139 USA
[2] Ecole Polytech Fed Lausanne, Signal Proc Labs, LTS4, LTS2, CH-1015 Lausanne, Switzerland
基金
瑞士国家科学基金会;
关键词
Laplacian matrix learning; graph signal processing; representation theory; factor analysis; Gaussian prior; VARIABLE SELECTION; BRAIN CONNECTIVITY; MODEL; WAVELET;
D O I
10.1109/TSP.2016.2602809
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The construction of a meaningful graph plays a crucial role in the success of many graph-based representations and algorithms for handling structured data, especially in the emerging field of graph signal processing. However, a meaningful graph is not always readily available from the data, nor easy to define depending on the application domain. In particular, it is often desirable in graph signal processing applications that a graph is chosen such that the data admit certain regularity or smoothness on the graph. In this paper, we address the problem of learning graph Laplacians, which is equivalent to learning graph topologies, such that the input data form graph signals with smooth variations on the resulting topology. To this end, we adopt a factor analysis model for the graph signals and impose a Gaussian probabilistic prior on the latent variables that control these signals. We show that the Gaussian prior leads to an efficient representation that favors the smoothness property of the graph signals. We then propose an algorithm for learning graphs that enforces such property and is based on minimizing the variations of the signals on the learned graph. Experiments on both synthetic and real world data demonstrate that the proposed graph learning framework can efficiently infer meaningful graph topologies from signal observations under the smoothness prior.
引用
收藏
页码:6160 / 6173
页数:14
相关论文
共 50 条
  • [41] The tau constant and the discrete Laplacian matrix of a metrized graph
    Cinkir, Zubeyir
    EUROPEAN JOURNAL OF COMBINATORICS, 2011, 32 (04) : 639 - 655
  • [42] On the Ky Fan norm of the signless Laplacian matrix of a graph
    S. Pirzada
    Rezwan Ul Shaban
    Hilal A. Ganie
    L. de Lima
    Computational and Applied Mathematics, 2024, 43
  • [43] Estimating a smooth function on a large graph by Bayesian Laplacian regularisation
    Kirichenko, Alisa
    van Zanten, Harry
    ELECTRONIC JOURNAL OF STATISTICS, 2017, 11 (01): : 891 - 915
  • [44] The Spectral Radius of the Reciprocal Distance Laplacian Matrix of a Graph
    Ravindra Bapat
    Swarup Kumar Panda
    Bulletin of the Iranian Mathematical Society, 2018, 44 : 1211 - 1216
  • [45] Advancing Graph Convolution Network with Revised Laplacian Matrix
    Wang, Jiahui
    Guo, Yi
    Wang, Zhihong
    Tang, Qifeng
    Wen, Xinxiu
    CHINESE JOURNAL OF ELECTRONICS, 2020, 29 (06) : 1134 - 1140
  • [46] The Spectral Radius of the Reciprocal Distance Laplacian Matrix of a Graph
    Bapat, Ravindra
    Panda, Swarup Kumar
    BULLETIN OF THE IRANIAN MATHEMATICAL SOCIETY, 2018, 44 (05) : 1211 - 1216
  • [47] On the determinant of the Laplacian matrix of a complex unit gain graph
    Wang, Yi
    Gong, Shi-Cai
    Fan, Yi-Zheng
    DISCRETE MATHEMATICS, 2018, 341 (01) : 81 - 86
  • [48] The determinant of the Laplacian matrix of a quaternion unit gain graph
    Kyrchei, Ivan I.
    Treister, Eran
    Pelykh, Volodymyr O.
    DISCRETE MATHEMATICS, 2024, 347 (06)
  • [49] A new upper bound for eigenvalues of the Laplacian matrix of a graph
    Li, JS
    Zhang, XD
    LINEAR ALGEBRA AND ITS APPLICATIONS, 1997, 265 : 93 - 100
  • [50] A note on the second largest eigenvalue of the Laplacian matrix of a graph
    Li, JS
    Pan, YL
    LINEAR & MULTILINEAR ALGEBRA, 2000, 48 (02): : 117 - 121