Clustering Applications at Yahoo!. Deepayan Chakrabarti (email@example.com). Outline. Clustering, in itself, is often not the primary problem Exploratory analysis is rarely needed Methods are often tied to the “final” goal. Data Problem Method Issues. Data Problem Method Issues.
Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.
Deepayan Chakrabarti (firstname.lastname@example.org)
Who-messages-whom IM graph
Better balance worse cuts
Large-sized low-quotient cuts are actually just unions of whiskers
Perfect balance on hypersphere: SDP formulation [Lang/05]Graph Partitioning (Methods)
= row effect + column effect + block effect
Refinement = cluster of terms
lyrics “song title” album …
~100M users, ~10M groups