@inproceedings{conf/sigmod/WangWYY02,
  author = {Wang, Haixun and 0010, Wei Wang and Yang, Jiong and Yu, Philip S.},
  booktitle = {SIGMOD Conference},
  crossref = {conf/sigmod/2002},
  date = {2009-06-28},
  editor = {Franklin, Michael J. and Moon, Bongki and Ailamaki, Anastassia},
  ee = {http://doi.acm.org/10.1145/564691.564737},
  interhash = {9da0e61a2ac3ac371edfb251fbbfc2ae},
  intrahash = {5ad941d8f0a06bb5e570e22a8cc58d92},
  isbn = {1-58113-497-5},
  pages = {394-405},
  publisher = {ACM},
  title = {Clustering by pattern similarity in large data sets.},
  url = {http://dblp.uni-trier.de/db/conf/sigmod/sigmod2002.html#WangWYY02},
  year = 2002
}

@inproceedings{zhang96birch,
  author = {Zhang, Tian and Ramakrishnan, Raghu and Livny, Miron},
  booktitle = {Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data (SIGMOD'96)},
  interhash = {bd3d8e33e8785ecf66408081db016ca4},
  intrahash = {d8ede3f66d485d95578bdc3eeda11fc3},
  pages = {103--114},
  title = {{BIRCH}: an efficient data clustering method for very large databases},
  url = {http://citeseer.ist.psu.edu/zhang96birch.html},
  year = 1996
}

@article{clauset-2004-70,
  author = {Clauset, Aaron and Newman, M. E. J. and Moore, Cristopher},
  interhash = {2c68e3c981a00380692a3b0b661d7cfd},
  intrahash = {0ea285bfc0f5a46ffec8a213e5133ba6},
  journal = {Physical Review E},
  pages = 066111,
  title = {Finding community structure in very large networks},
  url = {http://www.citebase.org/abstract?id=oai:arXiv.org:cond-mat/0408187},
  volume = 70,
  year = 2004
}

@misc{citeulike:95936,
  abstract = {The discovery and analysis of community structure in networks is a topic of
considerable recent interest within the physics community, but most methods
proposed so far are unsuitable for very large networks because of their
computational cost. Here we present a hierarchical agglomeration algorithm for
detecting community structure which is faster than many competing algorithms:
its running time on a network with n vertices and m edges is O(m d log n) where
d is the depth of the dendrogram describing the community structure. Many
real-world networks are sparse and hierarchical, with m ~ n and d ~ log n, in
which case our algorithm runs in essentially linear time, O(n log^2 n). As an
example of the application of this algorithm we use it to analyze a network of
items for sale on the web-site of a large online retailer, items in the network
being linked if they are frequently purchased by the same buyer. The network
has more than 400,000 vertices and 2 million edges. We show that our algorithm
can extract meaningful communities from this network, revealing large-scale
patterns present in the purchasing habits of customers.},
  author = {Clauset, Aaron and Newman, M. E. J. and Moore, Cristopher},
  citeulike-article-id = {95936},
  eprint = {cond-mat/0408187},
  interhash = {2c68e3c981a00380692a3b0b661d7cfd},
  intrahash = {f9a12630a6d31d576ea5222219a4cf0b},
  month = {August},
  priority = {0},
  title = {Finding community structure in very large networks},
  url = {http://arxiv.org/abs/cond-mat/0408187},
  year = 2004
}