Timezone: »

 
Spotlight
Overlapping Clustering Models, and One (class) SVM to Bind Them All
Xueyu Mao · Purnamrita Sarkar · Deepayan Chakrabarti

Thu Dec 06 07:20 AM -- 07:25 AM (PST) @ Room 517 CD
in Thu Track 3 -- Session 1 »

People belong to multiple communities, words belong to multiple topics, and books cover multiple genres; overlapping clusters are commonplace. Many existing overlapping clustering methods model each person (or word, or book) as a non-negative weighted combination of "exemplars" who belong solely to one community, with some small noise. Geometrically, each person is a point on a cone whose corners are these exemplars. This basic form encompasses the widely used Mixed Membership Stochastic Blockmodel of networks and its degree-corrected variants, as well as topic models such as LDA. We show that a simple one-class SVM yields provably consistent parameter inference for all such models, and scales to large datasets. Experimental results on several simulated and real datasets show our algorithm (called SVM-cone) is both accurate and scalable.

Author Information

Xueyu Mao (University of Texas at Austin)
Purnamrita Sarkar (UT Austin)
Deepayan Chakrabarti (UT Austin)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors