BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Structure and Dynamics of Diffusion Networks
DTSTART:20140317T161500
DTEND:20140317T173000
DTSTAMP:20260407T042121Z
UID:4d7537810fd85a908323df7b4bc6141a73b511b0e0e13f1f53aada4e
CATEGORIES:Conferences - Seminars
DESCRIPTION:By : Manuel Gomez Rodriguez\, MPI for Intelligent Systems\nIC 
 Faculty candidateAbstract\nNetworks represent a fundamental medium for spr
 eading and diffusion of various types of information\, behavior and rumors
 . However\, observing a diffusion process often reduces to noting when nod
 es (people\, blogs\, etc.) reproduce a piece of information\, adopt a beha
 vior\, buy a product\, or\, more generally\, adopt a contagion. We often o
 bserve where and when but not how or why contagions propagate through a ne
 twork. The mechanism underlying the process is hidden. However\, the mecha
 nism is of outstanding interest in all cases\, since understanding diffusi
 on is necessary for predicting meme propagation\, stopping rumors\, or max
 imizing sales of a product.\nIn this talk\, I will present a flexible prob
 abilistic model of diffusion over networks that makes minimal assumptions 
 about the physical\, biological or cognitive mechanisms responsible for di
 ffusion. This is possible since the model is data-driven and relies primar
 ily on the visible temporal traces that diffusion processes generate. I ap
 ply the model to information diffusion among 3.3 million blogs and mainstr
 eam media sites during a one year period. The model allows us to predict f
 uture events\, it sheds light on the hidden underlying structure and tempo
 ral dynamics of diffusion\, and provides insights into the positions and r
 oles various nodes play in the diffusion process.Biography\nManuel Gomez R
 odriguez is a Research Scientist at Max Planck Institute for Intelligent S
 ystems. Manuel develops machine learning and large-scale data mining metho
 ds for the analysis and modeling of large real-world networks and processe
 s that take place over them. He is particularly interested in problems mot
 ivated by the Web and social media and has received several recognitions f
 or his research\, including an Outstanding Paper Award at NIPS'13 and a Be
 st Research Paper Honorable Mention at KDD'10. Manuel holds a PhD in Elect
 rical Engineering from Stanford University and a BS in Electrical Engineer
 ing from Carlos III University in Madrid (Spain).More information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR