Estimating network dimension when the spectrum struggles

What is the dimension of a network? Here, we view it as the smallest dimension of Euclidean space into which nodes can be embedded so that pairwise distances accurately reflect the connectivity structure. We show that a recently proposed and extremely efficient algorithm for data clouds, based on computing first and second nearest neighbour distances, can be used as the basis of an approach for estimating the dimension of a network with weighted edges. We also show how the algorithm can be extended to unweighted networks when combined with spectral embedding. We illustrate the advantages of this technique over the widely-used approach of characterising dimension by visually searching for a suitable gap in the spectrum of the Laplacian.

[1]  P. Mucha,et al.  Escape times for subgraph detection and graph partitioning , 2022, ArXiv.

[2]  P. Mucha,et al.  Ranking Edges by their Impact on the Spectral Complexity of Information Diffusion over Networks , 2022, ArXiv.

[3]  D. Gleich,et al.  A flexible PageRank-based graph embedding framework closely related to spectral eigenvector embeddings , 2022, Journal of Applied and Computational Topology.

[4]  Philip S. Chodrow,et al.  Nonbacktracking spectral clustering of nonuniform hypergraphs , 2022, SIAM J. Math. Data Sci..

[5]  JEFF CALDER,et al.  Improved spectral convergence rates for graph Laplacians on ε-graphs and k-NN graphs , 2022, Applied and Computational Harmonic Analysis.

[6]  Aaron Lou,et al.  Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks , 2021, NeurIPS.

[7]  Micah Goldblum,et al.  The Intrinsic Dimension of Images and Its Impact on Learning , 2021, ICLR.

[8]  Alexandre d'Aspremont,et al.  Ranking and synchronization from pairwise measurements via SVD , 2019, J. Mach. Learn. Res..

[9]  Xiuyuan Cheng,et al.  Spectral Embedding Norm: Looking Deep into the Spectrum of the Graph Laplacian , 2018, SIAM J. Imaging Sci..

[10]  Alex Rodriguez,et al.  Estimating the intrinsic dimension of datasets by a minimal neighborhood information , 2017, Scientific Reports.

[11]  Konrad J. Swanepoel,et al.  Embedding graphs in Euclidean space , 2017, Electron. Notes Discret. Math..

[12]  Andrew M. Stuart,et al.  Uncertainty Quantification in Graph-Based Classification of High Dimensional Data , 2017, SIAM/ASA J. Uncertain. Quantification.

[13]  Jorge Cadima,et al.  Principal component analysis: a review and recent developments , 2016, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[14]  Dejan Slepcev,et al.  A variational approach to the consistency of spectral clustering , 2015, Applied and Computational Harmonic Analysis.

[15]  Ulrike von Luxburg,et al.  Optimal construction of k-nearest-neighbor graphs for identifying noisy clusters , 2009, Theoretical Computer Science.

[16]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[17]  Matthias Hein,et al.  Intrinsic dimensionality estimation of submanifolds in Rd , 2005, ICML.

[18]  Mikhail Belkin,et al.  Towards a theoretical foundation for Laplacian-based manifold methods , 2005, J. Comput. Syst. Sci..

[19]  Y. Koren,et al.  Drawing graphs by eigenvectors: theory and practice , 2005 .

[20]  B. Bollobás,et al.  Connectivity of random k-nearest-neighbour graphs , 2005, Advances in Applied Probability.

[21]  Panganamala Ramana Kumar,et al.  The Number of Neighbors Needed for Connectivity of Wireless Networks , 2004, Wirel. Networks.

[22]  J. Dall,et al.  Random geometric graphs. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[23]  P. Groenen,et al.  Modern Multidimensional Scaling: Theory and Applications , 1999 .

[24]  M. Penrose.  The longest edge of the random minimal spanning tree , 1997 .

[25]  Makarov Ilya,et al.  Survey on graph embeddings and their applications to machine learning problems on graphs , 2020 .

[26]  Matthias Hein.  Intrinsic Dimensionality Estimation of Submanifolds in R , 2005 .

[27]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[28]  M. Simonovits,et al.  ON THE CHROMATIC NUMBER OF GEOMETRIC GRAPHS , 1980 .