BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//NextToU//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:47d3c08c-e6fa-4026-ad87-28cb322ed922@nexttoyou
DTSTAMP:20261105T151913Z
DTSTART:20261106T200000Z
DTEND:20261106T210000Z
SUMMARY:Dissertation Defense: Derek Bagagem
LOCATION:Clearwater Building at City Center Plaza 259\, 777 W Main St.\, B
 oise\, ID 83725
DESCRIPTION:Title: Graph Representation Learning for Spatial and Temporal 
 Graphs: Invariance\, Spectral Structure\, and Higher-Order Temporal Roles
 \n\nProgram: Computing PhD\n\nCommittee Chair: Edoardo Serra\n\nCommittee
 : Edoardo Serra\, Francesco Gullo\, Oliviero Andreussi\n\nAbstract: Graph
 s furnish a general model for relational data across the sciences\, from 
 molecular chemistry and materials to biological interaction networks\, tr
 ansportation systems\, and social platforms. Graph representation learnin
 g (GRL) assigns vector embeddings to nodes\, edges\, or entire graphs so 
 that proximity in the embedding space reflects meaningful similarity in t
 he underlying data. Most GRL methods\, however\, treat the graph as a pur
 ely combinatorial object. In scientific applications this is rarely the c
 ase: nodes carry coordinates in physical space\, edges carry direction an
 d orientation\, interactions unfold over time\, and structure is often hi
 erarchical rather than flat. This additional structure is what makes such
  data informative\, yet it is also what standard methods handle least wel
 l. Representations must respect the symmetries of the setting\, such as i
 nvariance to rotation and translation\; they must scale to large graphs a
 nd point sets\; and they must expose geometric\, directional\, and tempor
 al information in a form that downstream models can use.\n\nThis disserta
 tion develops representation learning methods for graphs that carry such 
 structure. The unifying principle is to build the relevant structure dire
 ctly int\n\nhttp://next-to-u.app/events/47d3c08c-e6fa-4026-ad87-28cb322ed
 922
URL:http://next-to-u.app/events/47d3c08c-e6fa-4026-ad87-28cb322ed922
END:VEVENT
END:VCALENDAR