A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs
SIAM Journal on Scientific Computing
SimRank: a measure of structural-context similarity
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
The link prediction problem for social networks
CIKM '03 Proceedings of the twelfth international conference on Information and knowledge management
STOC '04 Proceedings of the thirty-sixth annual ACM symposium on Theory of computing
SPIN: searching personal information networks
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
To randomize or not to randomize: space optimal summaries for hyperlink analysis
Proceedings of the 15th international conference on World Wide Web
Local Graph Partitioning using PageRank Vectors
FOCS '06 Proceedings of the 47th Annual IEEE Symposium on Foundations of Computer Science
Dynamic personalized pagerank in entity-relation graphs
Proceedings of the 16th international conference on World Wide Web
Anchor-based proximity measures
Proceedings of the 16th international conference on World Wide Web
Objectrank: authority-based keyword search in databases
VLDB '04 Proceedings of the Thirtieth international conference on Very large data bases - Volume 30
Combating web spam with trustrank
VLDB '04 Proceedings of the Thirtieth international conference on Very large data bases - Volume 30
Estimating PageRank on graph streams
Proceedings of the twenty-seventh ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Keyword search on external memory data graphs
Proceedings of the VLDB Endowment
Query suggestion using hitting time
Proceedings of the 17th ACM conference on Information and knowledge management
On compressing social networks
Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Robust multi-body motion tracking using commute time clustering
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Diversified ranking on large graphs: an optimization viewpoint
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
GBASE: a scalable and general graph management system
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Finding information nebula over large networks
Proceedings of the 20th ACM international conference on Information and knowledge management
gbase: an efficient analysis platform for large graphs
The VLDB Journal — The International Journal on Very Large Data Bases
Incremental and accuracy-aware personalized pagerank through scheduled approximation
Proceedings of the VLDB Endowment
Hi-index | 0.00 |
Link prediction, personalized graph search, fraud detection, and many such graph mining problems revolve around the computation of the most "similar" k nodes to a given query node. One widely used class of similarity measures is based on random walks on graphs, e.g., personalized pagerank, hitting and commute times, and simrank. There are two fundamental problems associated with these measures. First, existing online algorithms typically examine the local neighborhood of the query node which can become significantly slower whenever high-degree nodes are encountered (a common phenomenon in real-world graphs). We prove that turning high degree nodes into sinks results in only a small approximation error, while greatly improving running times. The second problem is that of computing similarities at query time when the graph is too large to be memory-resident. The obvious solution is to split the graph into clusters of nodes and store each cluster on a disk page; ideally random walks will rarely cross cluster boundaries and cause page-faults. Our contributions here are twofold: (a) we present an efficient deterministic algorithm to find the k closest neighbors (in terms of personalized pagerank) of any query node in such a clustered graph, and (b) we develop a clustering algorithm (RWDISK) that uses only sequential sweeps over data files. Empirical results on several large publicly available graphs like DBLP, Citeseer and Live-Journal (~ 90 M edges) demonstrate that turning high degree nodes into sinks not only improves running time of RWDISK by a factor of 3 but also boosts link prediction accuracy by a factor of 4 on average. We also show that RWDISK returns more desirable (high conductance and small size) clusters than the popular clustering algorithm METIS, while requiring much less memory. Finally our deterministic algorithm for computing nearest neighbors incurs far fewer page-faults (factor of 5) than actually simulating random walks.