BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
BEGIN:VEVENT
UID:547@lincs.fr
DTSTART;TZID=Europe/Paris:20200617T140000
DTEND;TZID=Europe/Paris:20200617T150000
DTSTAMP:20200617T155744Z
URL:https://www.lincs.fr/events/characterizing-the-expressive-power-of-inv
 ariant-and-equivariant-graph-neural-networks/
SUMMARY:Characterizing the Expressive Power of Invariant and Equivariant
 Graph Neural Networks
DESCRIPTION:Various classes of Graph Neural Networks (GNN) have been
 proposed and shown to be successful in a wide range of applications with
 graph structured data. In this work\, we propose a theoretical framework
 able to compare the expressive power of these GNN architectures. The
 current universality theorems only apply to intractable classes of GNNs.
 Here\, we prove the first approximation guarantees for practical GNNs\,
 paving the way for a better understanding of their generalization. Our
 theoretical results are proved for invariant GNNs computing a graph
 embedding (permutation of the nodes of the input graph does not affect the
 output) and equivariant GNNs computing node embeddings (permutation of the
 input permutes the output). We show that Folklore Graph Neural Networks
 (FGNN)\, which are tensor based GNNs augmented with matrix multiplication
 are the most expressive architectures proposed so far for a given tensor
 order. We illustrate our results on the Quadratic Assignment Problem (a
 NP-Hard combinatorial problem) by showing that FGNNs are able to learn how
 to solve the problem\, leading to much better average performances than
 existing algorithms (based on spectral\, SDP or other GNNs architectures).
 On a practical side\, we also implement masked tensors to handle batches of
 graphs of varying sizes.\n\nThis is a joint work with Waiss Azizian
 (ENS).\n\nUse of Teams meetings for this seminar: contact
 ludovic.noirie{AT}nokia-bell-labs{DOT}com to get the Teams link
CATEGORIES:Seminars,Youtube
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20200329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR