Difference between revisions of "M. Kim and J. Leskovec. ICML'12"
Line 11: | Line 11: | ||
[[File:KimLeskovec.png]] | [[File:KimLeskovec.png]] | ||
− | On the figure above, <math>N</math>, <math>L</math>, <math>K</math> is the number of users, number of user feature categories, and number of blocks respectively. The block membership of node <math>i</math> at bloc <math>k</math> is <math>\phi_{ik}\in [0, 1]</math>. Note that this model does not require <math>\sum_k\phi_{ik}= 1</math> | + | On the figure above, <math>N</math>, <math>L</math>, <math>K</math> is the number of users, number of user feature categories, and number of blocks respectively. The block membership probability of node <math>i</math> at bloc <math>k</math> is <math>\phi_{ik}\in [0, 1]</math>. Note that this model does not require <math>\sum_k\phi_{ik}= 1</math>. For each user <math>i</math>, and each block <math>k</math>, <math>\phi_{ik}</math> is generated from [http://en.wikipedia.org/wiki/Beta_distribution Beta distribution]: <math> \phi_{ik}\sim Beta(\alpha_{k1},\alpha_{k2})</math>. Then, the truly block membership of user <math>i</math> at block <math>k</math> is a binary indicator which is generated from [http://en.wikipedia.org/wiki/Bernoulli_distribution Bernoulli distribution] <math>z_{ik}\sim Bernoulli(\phi_{ik})</math> |
== Dicussion == | == Dicussion == |
Revision as of 13:31, 2 October 2012
This is a scientific paper authored by M. Kim and J. Leskovec, and appeared in ICML'12. Below is the paper summary written by Tuan Anh.
Citation
Online Version
Latent Multi-group Membership Graph Model.
Summary
This is a paper on block based network analysis and prediction. This work furthers the work by Airoldi. et. al (see Related papers) to the extent that each node/ user can actually belong to more than one block and node features are modeled in addition to link existence. The generative process is given as below (see the figure)
On the figure above, , , is the number of users, number of user feature categories, and number of blocks respectively. The block membership probability of node at bloc is . Note that this model does not require . For each user , and each block , is generated from Beta distribution: . Then, the truly block membership of user at block is a binary indicator which is generated from Bernoulli distribution
Dicussion
Related papers
- Probabilistic graph clustering: Airoldi. et. al. Mixed Membership Stochastic Blockmodels. Journal of Machine Learning Research 9 (2008) 1981-2014
- The paper by Hoff on Multiplicative latent factor models for description and prediction of social networks