Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/38990
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | GEERTS, Floris | - |
dc.contributor.author | STEEGMANS, Jasper | - |
dc.contributor.author | VAN DEN BUSSCHE, Jan | - |
dc.date.accessioned | 2022-12-05T12:48:50Z | - |
dc.date.available | 2022-12-05T12:48:50Z | - |
dc.date.issued | 2022 | - |
dc.date.submitted | 2022-11-30T14:16:12Z | - |
dc.identifier.citation | Varzinczak, Ivan (Ed.). Foundations of Information and Knowledge Systems 12th International Symposium, FoIKS 2022 Helsinki, Finland, June 20–23, 2022 Proceedings, SPRINGER INTERNATIONAL PUBLISHING AG, p. 20 -34 | - |
dc.identifier.isbn | 978-3-031-11320-8 | - |
dc.identifier.isbn | 978-3-031-11321-5 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/1942/38990 | - |
dc.description.abstract | We investigate the power of message-passing neural networks (MPNNs) in their capacity to transform the numerical features stored in the nodes of their input graphs. Our focus is on global expressive power, uniformly over all input graphs, or over graphs of bounded degree with features from a bounded domain. Accordingly, we introduce the notion of a global feature map transformer (GFMT). As a yardstick for expressiveness, we use a basic language for GFMTs, which we call MPLang. Every MPNN can be expressed in MPLang, and our results clarify to which extent the converse inclusion holds. We consider exact versus approximate expressiveness; the use of arbitrary activation functions; and the case where only the ReLU activation function is allowed. | - |
dc.language.iso | en | - |
dc.publisher | SPRINGER INTERNATIONAL PUBLISHING AG | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science | - |
dc.subject | Computer Science - Artificial Intelligence | - |
dc.subject | Computer Science - Artificial Intelligence | - |
dc.subject | Computer Science - Learning | - |
dc.subject.other | Closure under concatenation | - |
dc.subject.other | Semiring provenance semantics for modal logic | - |
dc.subject.other | Query languages for numerical data | - |
dc.title | On the Expressive Power of Message-Passing Neural Networks as Global Feature Map Transformers | - |
dc.type | Proceedings Paper | - |
local.bibliographicCitation.authors | Varzinczak, Ivan | - |
local.bibliographicCitation.conferencedate | June 20–23, 2022 | - |
local.bibliographicCitation.conferencename | Foundations of Information and Knowledge Systems 12th International Symposium, FoIKS 2022 | - |
local.bibliographicCitation.conferenceplace | Helsinki, Finland | - |
dc.identifier.epage | 34 | - |
dc.identifier.spage | 20 | - |
local.bibliographicCitation.jcat | C1 | - |
local.publisher.place | GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND | - |
local.type.refereed | Refereed | - |
local.type.specified | Proceedings Paper | - |
dc.identifier.doi | 10.1007/978-3-031-11321-5_2 | - |
dc.identifier.arxiv | 2203.09555 | - |
dc.identifier.isi | WOS:000883026400002 | - |
dc.identifier.eissn | 1611-3349 | - |
local.provider.type | Web of Science | - |
local.bibliographicCitation.btitle | Foundations of Information and Knowledge Systems 12th International Symposium, FoIKS 2022 Helsinki, Finland, June 20–23, 2022 Proceedings | - |
local.uhasselt.international | no | - |
item.validation | ecoom 2023 | - |
item.accessRights | Open Access | - |
item.fullcitation | GEERTS, Floris; STEEGMANS, Jasper & VAN DEN BUSSCHE, Jan (2022) On the Expressive Power of Message-Passing Neural Networks as Global Feature Map Transformers. In: Varzinczak, Ivan (Ed.). Foundations of Information and Knowledge Systems 12th International Symposium, FoIKS 2022 Helsinki, Finland, June 20–23, 2022 Proceedings, SPRINGER INTERNATIONAL PUBLISHING AG, p. 20 -34. | - |
item.fulltext | With Fulltext | - |
item.contributor | GEERTS, Floris | - |
item.contributor | STEEGMANS, Jasper | - |
item.contributor | VAN DEN BUSSCHE, Jan | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Pages from 978-3-031-11321-5.pdf Restricted Access | Published version | 272.06 kB | Adobe PDF | View/Open Request a copy |
helsinki.pdf | Peer-reviewed author version | 273.91 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.