Sparse Relational Reasoning with Object-Centric Representations
| Title: | Sparse Relational Reasoning with Object-Centric Representations |
|---|---|
| Authors: | Spies, Alex F., Russo, Alessandra, Shanahan, Murray |
| Publication Year: | 2022 |
| Subject Terms: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, I.2.10, I.2.6 |
| More Details: | We investigate the composability of soft-rules learned by relational neural architectures when operating over object-centric (slot-based) representations, under a variety of sparsity-inducing constraints. We find that increasing sparsity, especially on features, improves the performance of some models and leads to simpler relations. Additionally, we observe that object-centric representations can be detrimental when not all objects are fully captured; a failure mode to which CNNs are less prone. These findings demonstrate the trade-offs between interpretability and performance, even for models designed to tackle relational tasks. Comment: ICML 2022, DyNN Workshop |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2207.07512 |
| Accession Number: | edsarx.2207.07512 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2207.07512 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20220715&spage=&pages=&title=Sparse Relational Reasoning with Object-Centric Representations&atitle=Sparse%20Relational%20Reasoning%20with%20Object-Centric%20Representations&aulast=Spies%2C%20Alex%20F.&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2207.07512 RelevancyScore: 1032 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1032.4052734375 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Sparse Relational Reasoning with Object-Centric Representations – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Spies%2C+Alex+F%2E%22">Spies, Alex F.</searchLink><br /><searchLink fieldCode="AR" term="%22Russo%2C+Alessandra%22">Russo, Alessandra</searchLink><br /><searchLink fieldCode="AR" term="%22Shanahan%2C+Murray%22">Shanahan, Murray</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2022 – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Machine+Learning%22">Computer Science - Machine Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22I%2E2%2E10%22">I.2.10</searchLink><br /><searchLink fieldCode="DE" term="%22I%2E2%2E6%22">I.2.6</searchLink> – Name: Abstract Label: Description Group: Ab Data: We investigate the composability of soft-rules learned by relational neural architectures when operating over object-centric (slot-based) representations, under a variety of sparsity-inducing constraints. We find that increasing sparsity, especially on features, improves the performance of some models and leads to simpler relations. Additionally, we observe that object-centric representations can be detrimental when not all objects are fully captured; a failure mode to which CNNs are less prone. These findings demonstrate the trade-offs between interpretability and performance, even for models designed to tackle relational tasks.<br />Comment: ICML 2022, DyNN Workshop – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2207.07512" linkWindow="_blank">http://arxiv.org/abs/2207.07512</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2207.07512 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2207.07512 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Machine Learning Type: general – SubjectFull: Computer Science - Artificial Intelligence Type: general – SubjectFull: I.2.10 Type: general – SubjectFull: I.2.6 Type: general Titles: – TitleFull: Sparse Relational Reasoning with Object-Centric Representations Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Spies, Alex F. – PersonEntity: Name: NameFull: Russo, Alessandra – PersonEntity: Name: NameFull: Shanahan, Murray IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 07 Type: published Y: 2022 |
| ResultId | 1 |