Advanced search
1 file | 620.44 KB Add to list

Explainable subgraphs with surprising densities : a subgroup discovery approach

Junning Deng (UGent) , Bo Kang (UGent) , Jefrey Lijffijt (UGent) and Tijl De Bie (UGent)
Author
Organization
Project
Abstract
The connectivity structure of graphs is typically related to the attributes of the nodes. In social networks for example, the probability of a friendship between two people depends on their attributes, such as their age, address, and hobbies. The connectivity of a graph can thus possibly be understood in terms of patterns of the form 'the subgroup of individuals with properties X are often (or rarely) friends with individuals in another subgroup with properties Y'. Such rules present potentially actionable and generalizable insights into the graph. We present a method that finds pairs of node subgroups between which the edge density is interestingly high or low, using an information-theoretic definition of interestingness. This interestingness is quantified subjectively, to contrast with prior information an analyst may have about the graph. This view immediately enables iterative mining of such patterns. Our work generalizes prior work on dense subgraph mining (i.e. subgraphs induced by a single subgroup). Moreover, not only is the proposed method more general, we also demonstrate considerable practical advantages for the single subgroup special case.
Keywords
Graph mining, Subgroup Discovery, Subjective interestingness, Community detection, COMMUNITY DETECTION

Downloads

  • published paper.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 620.44 KB

Citation

Please use this url to cite or link to this publication:

MLA
Deng, Junning, et al. “Explainable Subgraphs with Surprising Densities : A Subgroup Discovery Approach.” PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM), edited by C. Demeniconi and N. Chawla, SIAM, 2020, pp. 586–94, doi:10.1137/1.9781611976236.66.
APA
Deng, J., Kang, B., Lijffijt, J., & De Bie, T. (2020). Explainable subgraphs with surprising densities : a subgroup discovery approach. In C. Demeniconi & N. Chawla (Eds.), PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM) (pp. 586–594). https://doi.org/10.1137/1.9781611976236.66
Chicago author-date
Deng, Junning, Bo Kang, Jefrey Lijffijt, and Tijl De Bie. 2020. “Explainable Subgraphs with Surprising Densities : A Subgroup Discovery Approach.” In PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM), edited by C. Demeniconi and N. Chawla, 586–94. SIAM. https://doi.org/10.1137/1.9781611976236.66.
Chicago author-date (all authors)
Deng, Junning, Bo Kang, Jefrey Lijffijt, and Tijl De Bie. 2020. “Explainable Subgraphs with Surprising Densities : A Subgroup Discovery Approach.” In PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM), ed by. C. Demeniconi and N. Chawla, 586–594. SIAM. doi:10.1137/1.9781611976236.66.
Vancouver
1.
Deng J, Kang B, Lijffijt J, De Bie T. Explainable subgraphs with surprising densities : a subgroup discovery approach. In: Demeniconi C, Chawla N, editors. PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM). SIAM; 2020. p. 586–94.
IEEE
[1]
J. Deng, B. Kang, J. Lijffijt, and T. De Bie, “Explainable subgraphs with surprising densities : a subgroup discovery approach,” in PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM), Cincinnati, OH, 2020, pp. 586–594.
@inproceedings{8640290,
  abstract     = {{The connectivity structure of graphs is typically related to the attributes of the nodes. In social networks for example, the probability of a friendship between two people depends on their attributes, such as their age, address, and hobbies. The connectivity of a graph can thus possibly be understood in terms of patterns of the form 'the subgroup of individuals with properties X are often (or rarely) friends with individuals in another subgroup with properties Y'. Such rules present potentially actionable and generalizable insights into the graph. We present a method that finds pairs of node subgroups between which the edge density is interestingly high or low, using an information-theoretic definition of interestingness. This interestingness is quantified subjectively, to contrast with prior information an analyst may have about the graph. This view immediately enables iterative mining of such patterns. Our work generalizes prior work on dense subgraph mining (i.e. subgraphs induced by a single subgroup). Moreover, not only is the proposed method more general, we also demonstrate considerable practical advantages for the single subgroup special case.}},
  author       = {{Deng, Junning and Kang, Bo and Lijffijt, Jefrey and De Bie, Tijl}},
  booktitle    = {{PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM)}},
  editor       = {{Demeniconi, C. and Chawla, N.}},
  isbn         = {{9781611976236}},
  keywords     = {{Graph mining,Subgroup Discovery,Subjective interestingness,Community detection,COMMUNITY DETECTION}},
  language     = {{eng}},
  location     = {{Cincinnati, OH}},
  pages        = {{586--594}},
  publisher    = {{SIAM}},
  title        = {{Explainable subgraphs with surprising densities : a subgroup discovery approach}},
  url          = {{http://dx.doi.org/10.1137/1.9781611976236.66}},
  year         = {{2020}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: