Abstract
We investigate the community detection problem on graphs in the existence of multiple edge types. Our main motivation is that similarity between objects can be defined by many different metrics and aggregation of these metrics into a single one poses several important challenges, such as recovering this aggregation function from ground-truth, investigating the space of different clusterings, etc. In this paper, we address how to find an aggregation function to generate a composite metric that best resonates with the ground-truth. We describe two approaches: solving an inverse problem where we try to find parameters that generate a graph whose clustering gives the ground-truth clustering, and choosing parameters to maximize the quality of the ground-truth clustering. We present experimental results on real and synthetic benchmarks.
This work is supported by the Laboratory Directed Research and Development program of Sandia National Laboratories.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dhillon, I., Guan, Y., Kulis, B.: Weighted graph cuts without eigenvectors a multilevel approach. IEEE T. Pattern Analysis and Machine Intelligence 29(11), 1944–1957 (2007)
Lancichinetti, A., Fortunato, S., Radicchi, F.: Benchmark graphs for testing community detection algorithms. Physical Review E 78(4), 1–5 (2008)
Lange, T., Roth, V., Braun, M.L., Buhmann, J.M.: Stability-based validation of clustering solutions, neural computation. Neural Computation 16, 1299–1323 (2004)
Leskovec, J., Lang, K., Dasgupta, A., Mahoney, M.: Community structure in large networks: Natural cluster sizes and the absence of large well-defined clusters. Internet Mathematics 6, 29–123 (2009)
Luo, X.: On coreference resolution performance metrics. In: Proc. Human Language Technology Conf. and Conf. Empirical Methods in Natural Language Processing, Vancouver, British Columbia, Canada, pp. 25–32. Association for Computational Linguistics (2005)
Meila, M.: Comparing clusterings: an axiomatic view. In: Proceedings of the 22nd International Conference on Machine Learning, 2005, pp. 577–584 (2005)
Mirkin, B.: Mathematical Classification and Clustering. Kluwer Academic Press, Dordrecht (1996)
Newman, M.: Analysis of weighted networks. Phys. Rev. EÂ 70(5), 056131 (2004)
Newman, M.: Modularity and community structure in networks. PNAS 103, 8577–8582 (2006)
Plantenga, T.: Hopspack 2.0 user manual. Technical Report SAND2009-6265, Sandia National Laboratories (2009)
Stichting, C., Centrum, M., Dongen, S.V.: Performance criteria for graph clustering and markov cluster experiments. Technical Report INS-R0012, Centre for Mathematics and Computer Science (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rocklin, M., Pinar, A. (2010). Computing an Aggregate Edge-Weight Function for Clustering Graphs with Multiple Edge Types. In: Kumar, R., Sivakumar, D. (eds) Algorithms and Models for the Web-Graph. WAW 2010. Lecture Notes in Computer Science, vol 6516. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18009-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-18009-5_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-18008-8
Online ISBN: 978-3-642-18009-5
eBook Packages: Computer ScienceComputer Science (R0)