kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
GeomCA: Geometric Evaluation of Data Representations
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0001-6920-5109
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0002-0900-1523
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for Autonomous Systems, CAS.ORCID iD: 0000-0003-2965-2953
2021 (English)In: Proceedings of Machine Learning Research: Proceedings of the 38th International Conference on Machine Learning, ML Research Press , 2021, p. 8588-8598Conference paper, Published paper (Refereed)
Abstract [en]

Evaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning. In this work, we present Geometric Component Analysis (GeomCA) algorithm that evaluates representation spaces based on their geometric and topological properties. GeomCA can be applied to representations of any dimension, independently of the model that generated them. We demonstrate its applicability by analyzing representations obtained from a variety of scenarios, such as contrastive learning models, generative models and supervised learning models.

Place, publisher, year, edition, pages
ML Research Press , 2021. p. 8588-8598
Keywords [en]
Embedding and Representation learning, Algorithms Evaluation, Generative Models, GeomCA
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-308496Scopus ID: 2-s2.0-85124639338OAI: oai:DiVA.org:kth-308496DiVA, id: diva2:1636088
Conference
38th International Conference on Machine Learning, ICML 2021, Virtual Online, 18-24 July 2021
Note

QC 20220215

Available from: 2022-02-08 Created: 2022-02-08 Last updated: 2024-07-12Bibliographically approved
In thesis
1. Learning and Evaluating the Geometric Structure of Representation Spaces
Open this publication in new window or tab >>Learning and Evaluating the Geometric Structure of Representation Spaces
2022 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Efficient representations of observed input data have been shown to significantly accelerate the performance of subsequent learning tasks in numerous domains. To obtain such representations automatically, we need to design both i) models that identify useful patterns in the input data and encode them into structured low dimensional representations, and ii) evaluation measures that accurately assess the quality of the resulting representations. In this thesis, we present work that addresses both these requirements, where we extensively focus on requirement ii) since the evaluation of representations has been largely unexplored in the machine learning research. We begin with an overview of representation learning techniques and different structures that can be imposed on representation spaces, thus first addressing i). In this regard,we present a representation learning model that identifies useful patterns from multimodal data, and describe an approach that promotes a structure on there presentation space that is favourable for performing a robotics task. We then thoroughly study the problem of assessing the quality of learned representations and overview the pitfalls of current practices. With this, we motivate the evaluation based on analyzing geometric properties of representations and present two novel evaluation algorithms constituting the core of this thesis. Finally, we present an application of the proposed evaluation algorithms to compare large input graphs.

Abstract [sv]

Effektive representationer av observerat input-data har visat sig ge ensignifikant ökning av prestandan för träningsproblem i ett flertal områden.För att på ett automatiskt sett få fram sådana representationer behövervi både i) modeller som kan identifiera användbara mönster i input-datatoch koda dessa till strukturerade lågdimensionella representationer, samtii) utvärderingsmått som på ett tillförlitligt sätt mäter kvaliteten av dessarepresentationer. I denna avhandling presenterar vi arbete som hanterar bådadessa krav, där fokus ligger på ii) eftersom utvärdering av representationerhar varit ett i stort sätt outforskat ämne i litteraturen för maskininlärning.Vi börjar med en översikt av representationsinlärningstekniker och typer avstrukturer som man kan förelägga på representationsrymden, vilket tillhöri). I detta avseende, presenterar vi modell för representationsinlärning somidentifierar användbara mönster från multimodal data, samt beskriver enmetod som framhäver struktur på representationsrymden som gör sig välpassande för robotikuppgift. Vi studerar sedan genomgående problemet medatt avgöra kvaliteten av dessa inlärda representationer och ger en översikt avvanliga fallgropar som finns med nuvarande metoder. Vi motiverar med dettautvärderingen baserat på av representationernas geometriska egenskaper ochpresenterar två nya utvärderingsalgoritmer vilka huvuddelen av avhandlingenbestår av. Slutligen så presenterar vi ett praktiskt användningsområde avalgoritmerna för att jämföra stora inputgrafer.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2022. p. 54
Series
TRITA-EECS-AVL ; 2022:33
Keywords
Representation Learning, Machine Learning, Generative Models
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-312723 (URN)978-91-8040-228-6 (ISBN)
Public defence
2022-06-13, https://kth-se.zoom.us/j/65953366981, F3, Lindstedtsvägen 26, Stockholm, 15:00 (English)
Opponent
Supervisors
Note

QC 20220523

Available from: 2022-05-23 Created: 2022-05-20 Last updated: 2022-06-25Bibliographically approved

Open Access in DiVA

GeomCA(4560 kB)130 downloads
File information
File name FULLTEXT01.pdfFile size 4560 kBChecksum SHA-512
c5d987717c4cf1e9b47e11f731c78607746223d1b373a7009b67a6049644fba8c490d33db38eac8b4d89da6361f25d7cbf52e82342b96d033347d83588f783d0
Type fulltextMimetype application/pdf

Other links

ScopusProceedings

Authority records

Poklukar, PetraVarava, AnastasiiaKragic, Danica

Search in DiVA

By author/editor
Poklukar, PetraVarava, AnastasiiaKragic, Danica
By organisation
Robotics, Perception and Learning, RPLCentre for Autonomous Systems, CAS
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 130 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 293 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf