Skip to main content

25. Apr 2022

Generalized page rank applications: From local community detection to graph neural networks

Datum: 25. April 2022 | 16:00 – 17:00
Sprecher: Olgica Milenkovic, University of Illinois at Urbana-Champaign
Veranstaltungsort: Online
Sprache: Englisch

image here

 

PageRank (PR) is an algorithm developed by Google for the purpose of generating website rankings used as part of their search engine systems. Roughly speaking, PageRank represent a method for aggregating scores of variable-length random walks. Aggregation is performed using weighted combinations of walk parameters, with the weights representing a predetermined function of a single “diffusion parameter”. Given that many other learning and optimization methods rely on random walk aggregation, various generalizations of PageRank have been proposed in the literature. These generalizations rely on optimizing or adapting the weights used in the aggregation process to various tasks at hand. Examples include Personalized PageRank and Heat-Kernel PageRank.

In the talk, we discuss two new forms of generalized PageRank methods, Inverse PageRank (IPR) and Adaptive PageRank (APR). IPR offers provable state-of-the-art performance guarantees for local (seed-set) community detection, while APR can be applied to different graph neural network learning tasks as it adaptively learns the aggregation weights of random walks. We describe the underlying mathematical principles supporting the parameter selection process and provide numerous experiments on synthetic and real datasets that illustrate the performance of the generalized PageRank methods. 

This is a joint work with Eli Chien, Pan Li and Jianhao Peng.

Weitere Informationen:

Datum:
25. April 2022
16:00 – 17:00

Sprecher:
Olgica Milenkovic, University of Illinois at Urbana-Champaign

Veranstaltungsort:
Online

Sprache:
Englisch

Ansprechpartner:

Arinya Eller

Email:
arinya.eller@ist.ac.at

Teilen

facebook share icon
twitter share icon



sidebar arrow up
Nach Oben