Skip to main content

Advertisement

SpringerLink
Log in

Resling: a scalable and generic framework to mine top-k representative subgraph patterns

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

Mining subgraph patterns is an active area of research due to its wide-ranging applications. Examples include frequent subgraph mining, discriminative subgraph mining, statistically significant subgraphs. Existing research has primarily focused on mining all subgraph patterns in the database. However, due to the exponential subgraph search space, the number of patterns mined, typically, is too large for any human-mediated analysis. Consequently, deriving insights from the mined patterns is hard for domain scientists. In addition, subgraph pattern mining is posed in multiple forms: the function that models if a subgraph is a pattern varies based on the application and the database could be over multiple graphs or a single, large graph. In this paper, we ask the following question: Given a subgraph importance function and a budget k, which are the k subgraph patterns that best represent all other patterns of interest? We show that the problem is NP-hard, and propose a generic framework called Resling that adapts to arbitrary subgraph importance functions and generalizable to both transactional graph databases as well as single, large graphs. Resling derives its power by structuring the search space in the form of an edit map, where each subgraph is a node, and two subgraphs are connected if they have an edit distance of one. We rank nodes in the edit map through two random walk based algorithms: vertex-reinforced random walks ( Resling -VR) and negative-reinforced random walks( Resling -NR). Experiments show that Resling-VR is up to 20 times more representative of the pattern space and two orders of magnitude faster than the state-of-the-art techniques. Resling-NR further improves the running time while maintaining comparable or better performance in representative power.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. We slightly abuse the term “undirected graph” here. Although the edges are undirected, the sign of the edge weight depends on the direction.

References

  1. Ranu S, Singh AK (2012) Indexing and mining topological patterns for drug discovery. In: EDBT, pp 562–565

  2. Ranu S, Hoang M, Singh A (2013) Mining discriminative subgraphs from global-state networks. In: KDD, pp 509–517

  3. Chaoji V, Ranu S, Rastogi R, Bhatt R (2012) Recommendations to boost content spread in social networks. In: WWW, pp 529–538

  4. Banerjee P, Ranu S, Raghavan S (2014) Inferring uncertain trajectories from partial observations. In: ICDM, pp 30–39

  5. Banerjee P, Yawalkar P, Ranu S (2016) Mantra: a scalable approach to mining temporally anomalous sub-trajectories. In: KDD, pp 1415–1424

  6. Yan X, Han J (2002) Gspan: graph-based substructure pattern mining. In: ICDM, p 721. ISBN: 0-7695-1754-4

  7. Kuramochi M, Karypis G (2005) Finding frequent patterns in a large sparse graph*. Data Min Knowl Discov 11(3):243–271

    Article  MathSciNet  Google Scholar 

  8. Elseidy M, Abdelhamid E, Skiadopoulos S, Kalnis P (2014) Grami: frequent subgraph and pattern mining in a single large graph. PVLDB 7(7):517–528

    Google Scholar 

  9. Gurukar S, Ranu S, Ravindran B (2015) Commit: A scalable approach to mining communication motifs from dynamic networks. In: SIGMOD, pp 475–489

  10. Thoma M, Cheng H, Gretton A, Han J, Kriegel H-P, Smola A, Song L, Yu PS, Yan X, Borgwardt K (2009) Near-optimal supervised feature selection among frequent subgraphs. In: SDM 2009, pp 1076–1087

  11. Hasan MA, Zaki MJ (2009) Output space sampling for graph patterns. PVLDB 2(1):730–741

    Google Scholar 

  12. Ranu S, Singh AK (2009) Graphsig: a scalable approach to mining significant subgraphs in large graph databases. In: ICDE

  13. Ranu S, Calhoun BT, Singh AK, Swamidass SJ (2011) Probabilistic substructure mining from small-molecule screens. Mol Inf 30(9):809–815

    Article  Google Scholar 

  14. Ranu S, Singh AK (2009) Mining statistically significant molecular substructures for efficient molecular classification. J Chem Inf Model 49:2537–2550

    Article  Google Scholar 

  15. Kuramochi M, Karypis G (2001) Frequent subgraph discovery. In: ICDM

  16. Nijssen S, Kok JN (2004) The Gaston tool for frequent subgraph mining. In: Proceedings of the international workshop on graph-based tools

  17. Yan X, Cheng H, Han J, Yu PS (2008) Mining significant graph patterns by scalable leap search. In: SIGMOD

  18. Jin N, Young C, Wang W (2010) Gaia: graph classification using evolutionary computation. In: SIGMOD

  19. Cheng H, Lo D, Zhou Y, Wang X, Yan X (2009) Identifying bug signatures using discriminative graph mining, In: Proceedings of the eighteenth international symposium on software testing and analysis, pp 141–152

  20. Dutkowski J, Ideker T (2011) Protein networks as logic functions in development and cancer. PLoS Comput Biol 7:e1002180

    Article  Google Scholar 

  21. Hasan MA, Chaoji V, Salem S, Besson J, Zaki MJ (2007) Origami: mining representative orthogonal graph patterns. In: ICDM, pp 153–162

  22. Yan X, Han J (2003) Closegraph: mining closed frequent graph patterns. In: KDD, pp 286–295

  23. Zeng Z, Tung AKH, Wang J, Feng J, Zhou L (2009) Comparing stars: on approximating graph edit distance. PVLDB 2(1):25–36

    Google Scholar 

  24. Zhang S, Yang J, Li S (2009) Ring: an integrated method for frequent representative subgraph mining, In: ICDM, pp 1082–1087

  25. Natarajan D, Ranu S (2016) A scalable and generic framework to mine top-k representative subgraph patterns. In: 2016 IEEE 16th international conference on data mining (ICDM). IEEE, pp 370–379

  26. Metwally A, Agrawal D, El Abbadi A (2005) Efficient computation of frequent and top-k elements in data streams. In: ICDT, pp 398–412

  27. Ranu S, Hoang M, Singh A (2014) Answering top-k representative queries on graph databases. In: SIGMOD, pp 1163–1174

  28. Drosou M, Pitoura E (2012) Disc diversity: result diversification based on dissimilarity and coverage. PVLDB 6(1):13–24

    Google Scholar 

  29. Cornuejols G, Fisher ML, Nemhauser GL (1977) Location of bank accounts to optimize float: an analytic study of exact and approximate algorithms. Manag Sci 23(8):789–810

    Article  MathSciNet  MATH  Google Scholar 

  30. He H, Singh AK (2006) Closure-tree: an index structure for graph queries. In: ICDE

  31. Page L, Brin S, Motwani R, Winograd T (1998) The pagerank citation ranking: bringing order to the web. In: WWW, pp 161–172

  32. Pemantle R (1992) Vertex-reinforced random walk. Probab Theory Relat Fields 92(1):117–136

    Article  MathSciNet  MATH  Google Scholar 

  33. Badrinath R, Madhavan CEV (2012) Diversity in ranking using negative reinforcement. In: Proceedings of the ACM SIGKDD workshop on mining data semantics, vol 11, no 1–11, p 6

  34. Mei Q, Guo J, Radev D (2010) Divrank: the interplay of prestige and diversity in information networks. In: KDD

  35. Huan J, Wang W, Prins J, Yang J (2004) Spin: mining maximal frequent subgraphs from graph databases. In: KDD, pp 581–586

  36. Thomas L, Valluri S, Karlapalem K (2006) Margin: maximal frequent subgraph mining. In: ICDM, pp 1097–1101

  37. Krishnan A, Padmanabhan D, Ranu S, Mehta S (2016) Select, link and rank: diversified query expansion and entity ranking using wikipedia. In: International conference on web information systems engineering, pp 157–173

Download references

Author information

Authors and Affiliations

  1. Machine Learning Team, Amazon, Seattle, USA

    Dheepikaa Natarajan

  2. Department of CSE, IIT Delhi, New Delhi, India

    Sayan Ranu

Authors
  1. Dheepikaa Natarajan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sayan Ranu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sayan Ranu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Natarajan, D., Ranu, S. Resling: a scalable and generic framework to mine top-k representative subgraph patterns. Knowl Inf Syst 54, 123–149 (2018). https://doi.org/10.1007/s10115-017-1129-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-017-1129-y

Keywords

Search

Navigation