|
ReSi: A comprehensive benchmark for representational similarity measures
Klabunde, Max
;
Wald, Tassilo
;
Schumacher, Tobias
;
Maier-Hein, Klaus
;
Strohmaier, Markus
;
Lemmerich, Florian
![[img]](https://madoc.bib.uni-mannheim.de/71342/1.hassmallThumbnailVersion/7022_ReSi_A_Comprehensive_Benc.pdf)  Vorschau |
|
PDF
7022_ReSi_A_Comprehensive_Benc.pdf
- Veröffentlichte Version
Download (5MB)
|
|
URL:
|
https://openreview.net/forum?id=PRvdO3nfFi
|
|
URN:
|
urn:nbn:de:bsz:180-madoc-713429
|
|
Dokumenttyp:
|
Konferenzveröffentlichung
|
|
Erscheinungsjahr:
|
2025
|
|
Buchtitel:
|
13th International Conference on Learning Representations (ICLR 2025)
|
|
Seitenbereich:
|
1-40
|
|
Veranstaltungstitel:
|
ICLR 2025, The Thirteenth International Conference on Learning Representations
|
|
Veranstaltungsort:
|
Singapur, Singapore
|
|
Veranstaltungsdatum:
|
24.-28.04.2025
|
|
Ort der Veröffentlichung:
|
Red Hook, NY
|
|
Verlag:
|
Curran Associates, Inc.
|
|
ISBN:
|
979-8-3313-2193-2 , 979-8-3313-2085-0
|
|
Verwandte URLs:
|
|
|
Sprache der Veröffentlichung:
|
Englisch
|
|
Einrichtung:
|
Fakultät für Betriebswirtschaftslehre > Data Science in the Economic and Social Sciences (Strohmaier, 2022-)
|
|
Bereits vorhandene Lizenz:
|
 Creative Commons Namensnennung 4.0 International (CC BY 4.0)
|
|
Fachgebiet:
|
004 Informatik
|
|
Freie Schlagwörter (Englisch):
|
representational similarity , benchmark , grounding , representations
|
|
Abstract:
|
Measuring the similarity of different representations of neural architectures is a fundamental task and an open research challenge for the machine learning community. This paper presents the first comprehensive benchmark for evaluating representational similarity measures based on well-defined groundings of similarity. The representational similarity (ReSi) benchmark consists of (i) six carefully designed tests for similarity measures, (ii) 24 similarity measures, (iii) 14 neural network architectures, and (iv) seven datasets, spanning over the graph, language, and vision domains. The benchmark opens up several important avenues of research on representational similarity that enable novel explorations and applications of neural architectures. We demonstrate the utility of the ReSi benchmark by conducting experiments on various neural network architectures, real world datasets and similarity measures. All components of the benchmark are publicly available and thereby facilitate systematic reproduction and production of research results. The benchmark is extensible, future research can build on and further expand it. We believe that the ReSi benchmark can serve as a sound platform catalyzing future research that aims to systematically evaluate existing and explore novel ways of comparing representations of neural architectures.
|
 | Dieser Eintrag ist Teil der Universitätsbibliographie. |
 | Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt. |
 Suche Autoren in
BASE:
Klabunde, Max
;
Wald, Tassilo
;
Schumacher, Tobias
;
Maier-Hein, Klaus
;
Strohmaier, Markus
;
Lemmerich, Florian
Google Scholar:
Klabunde, Max
;
Wald, Tassilo
;
Schumacher, Tobias
;
Maier-Hein, Klaus
;
Strohmaier, Markus
;
Lemmerich, Florian
ORCID:
Klabunde, Max ; Wald, Tassilo ; Schumacher, Tobias  ORCID: 0000-0003-3091-5095 ; Maier-Hein, Klaus ; Strohmaier, Markus ORCID: 0000-0002-5485-5720 ; Lemmerich, Florian
Sie haben einen Fehler gefunden? Teilen Sie uns Ihren Korrekturwunsch bitte hier mit: E-Mail
Actions (login required)
 |
Eintrag anzeigen |
|
