Node Similarity Measures


There are many problems where objects lend themselves to be represented easily using graphs. For example, scientific publications are linked together by citations. In cases like this, similarity between the objects represented as nodes can be computed using the structure of the graph. The algorithms take advantage of the local neighborhood of the nodes in order to compute the similarity. Refer to the papers for a description of the various algorithms.
Here is a README which explains the algorithms implemented, instructions for usage and input data format.

Click here to download the package

References
  1. Glenn Jeh and Jennifer Widom. SimRank: a measure of structural-context similarity. In Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 538-543. 2002.
  2. David Harel and Yehuda Koren. Clustering spatial data using random walks. Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, pages 281-286. 2001.
Back to Software