Web graph similarity for anomaly detection (poster)

ABSTRACT

Web graphs are approximate snapshots of the web, created by search engines. Their creation is an error-prone procedure that relies on the availability of Internet nodes and the faultless operation of multiple software and hardware units. Checking the validity of a web graph requires a notion of graph similarity. Web graph similarity helps measure the amount and significance of changes in consecutive web graphs. These measurements validate how well search engines acquire content from the web. In this paper we study five similarity schemes: three of them adapted from existing graph similarity measures and two adapted from well-known document and vector similarity methods. We compare and evaluate all five schemes using a sequence of web graphs for Yahoo! and study if the schemes can identify anomalies that may occur due to hardware or other problems.

REFERENCES

• 1: Andrei Z. Broder , Steven C. Glassman , Mark S. Manasse , Geoffrey Zweig, Syntactic clustering of the Web, Selected papers from the sixth international conference on World Wide Web, p.1157-1166, September 1997, Santa Clara, California, United States
• 2: Moses S. Charikar, Similarity estimation techniques from rounding algorithms, Proceedings of the thiry-fourth annual ACM symposium on Theory of computing, May 19-21, 2002, Montreal, Quebec, Canada [doi>10.1145/509907.509965]
• 3: P. Papadimitriou, A. Dasdan, and H. Garcia-Molina. Web graph similarity for anomaly detection. Technical Report 2008--1, Stanford University, 2008. URL: http://dbpubs.stanford.edu/pub/2008--1.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Search process

General Terms:
Algorithms, Design, Experimentation

Keywords:
anomaly detection, graph similarity, web graph lsh