GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings Article Swipe
Matthias Fey
,
Jan Eric Lenssen
,
Frank Weichert
,
Jure Leskovec
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2106.05609
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2106.05609
We present GNNAutoScale (GAS), a framework for scaling arbitrary message-passing GNNs to large graphs. GAS prunes entire sub-trees of the computation graph by utilizing historical embeddings from prior training iterations, leading to constant GPU memory consumption in respect to input node size without dropping any data. While existing solutions weaken the expressive power of message passing due to sub-sampling of edges or non-trainable propagations, our approach is provably able to maintain the expressive power of the original GNN. We achieve this by providing approximation error bounds of historical embeddings and show how to tighten them in practice. Empirically, we show that the practical realization of our framework, PyGAS, an easy-to-use extension for PyTorch Geometric, is both fast and memory-efficient, learns expressive node representations, closely resembles the performance of their non-scaling counterparts, and reaches state-of-the-art performance on large-scale graphs.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- http://arxiv.org/abs/2106.05609
- https://arxiv.org/pdf/2106.05609
- OA Status
- green
- Cited By
- 11
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3166813066
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3166813066Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2106.05609Digital Object Identifier
- Title
-
GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical EmbeddingsWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-06-10Full publication date if available
- Authors
-
Matthias Fey, Jan Eric Lenssen, Frank Weichert, Jure LeskovecList of authors in order
- Landing page
-
https://arxiv.org/abs/2106.05609Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2106.05609Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2106.05609Direct OA link when available
- Concepts
-
Computer science, Scalability, Expressive power, Theoretical computer science, Scaling, Graph, Computation, Node (physics), Algorithm, Mathematics, Database, Engineering, Structural engineering, GeometryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
11Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 3, 2023: 4, 2022: 2, 2021: 2Per-year citation counts (last 5 years)
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3166813066 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2106.05609 |
| ids.doi | https://doi.org/10.48550/arxiv.2106.05609 |
| ids.mag | 3166813066 |
| ids.openalex | https://openalex.org/W3166813066 |
| fwci | |
| type | article |
| title | GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11273 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9987999796867371 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Advanced Graph Neural Networks |
| topics[1].id | https://openalex.org/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.978600025177002 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Neural Network Applications |
| topics[2].id | https://openalex.org/T12292 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9732000231742859 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Graph Theory and Algorithms |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8294292688369751 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C48044578 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7969895601272583 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q727490 |
| concepts[1].display_name | Scalability |
| concepts[2].id | https://openalex.org/C195818886 |
| concepts[2].level | 2 |
| concepts[2].score | 0.705217719078064 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q5421724 |
| concepts[2].display_name | Expressive power |
| concepts[3].id | https://openalex.org/C80444323 |
| concepts[3].level | 1 |
| concepts[3].score | 0.583909273147583 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[3].display_name | Theoretical computer science |
| concepts[4].id | https://openalex.org/C99844830 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5316579341888428 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q102441924 |
| concepts[4].display_name | Scaling |
| concepts[5].id | https://openalex.org/C132525143 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5308120250701904 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[5].display_name | Graph |
| concepts[6].id | https://openalex.org/C45374587 |
| concepts[6].level | 2 |
| concepts[6].score | 0.516941249370575 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q12525525 |
| concepts[6].display_name | Computation |
| concepts[7].id | https://openalex.org/C62611344 |
| concepts[7].level | 2 |
| concepts[7].score | 0.500680685043335 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1062658 |
| concepts[7].display_name | Node (physics) |
| concepts[8].id | https://openalex.org/C11413529 |
| concepts[8].level | 1 |
| concepts[8].score | 0.21228399872779846 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[8].display_name | Algorithm |
| concepts[9].id | https://openalex.org/C33923547 |
| concepts[9].level | 0 |
| concepts[9].score | 0.10383358597755432 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[9].display_name | Mathematics |
| concepts[10].id | https://openalex.org/C77088390 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8513 |
| concepts[10].display_name | Database |
| concepts[11].id | https://openalex.org/C127413603 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[11].display_name | Engineering |
| concepts[12].id | https://openalex.org/C66938386 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q633538 |
| concepts[12].display_name | Structural engineering |
| concepts[13].id | https://openalex.org/C2524010 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[13].display_name | Geometry |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8294292688369751 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/scalability |
| keywords[1].score | 0.7969895601272583 |
| keywords[1].display_name | Scalability |
| keywords[2].id | https://openalex.org/keywords/expressive-power |
| keywords[2].score | 0.705217719078064 |
| keywords[2].display_name | Expressive power |
| keywords[3].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[3].score | 0.583909273147583 |
| keywords[3].display_name | Theoretical computer science |
| keywords[4].id | https://openalex.org/keywords/scaling |
| keywords[4].score | 0.5316579341888428 |
| keywords[4].display_name | Scaling |
| keywords[5].id | https://openalex.org/keywords/graph |
| keywords[5].score | 0.5308120250701904 |
| keywords[5].display_name | Graph |
| keywords[6].id | https://openalex.org/keywords/computation |
| keywords[6].score | 0.516941249370575 |
| keywords[6].display_name | Computation |
| keywords[7].id | https://openalex.org/keywords/node |
| keywords[7].score | 0.500680685043335 |
| keywords[7].display_name | Node (physics) |
| keywords[8].id | https://openalex.org/keywords/algorithm |
| keywords[8].score | 0.21228399872779846 |
| keywords[8].display_name | Algorithm |
| keywords[9].id | https://openalex.org/keywords/mathematics |
| keywords[9].score | 0.10383358597755432 |
| keywords[9].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2106.05609 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2106.05609 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2106.05609 |
| locations[1].id | doi:10.48550/arxiv.2106.05609 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2106.05609 |
| locations[2].id | mag:3171339628 |
| locations[2].is_oa | False |
| locations[2].source | |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5002742256 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5727-0701 |
| authorships[0].author.display_name | Matthias Fey |
| authorships[0].countries | DE |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I200332995 |
| authorships[0].affiliations[0].raw_affiliation_string | Tu Dortmund University |
| authorships[0].institutions[0].id | https://openalex.org/I200332995 |
| authorships[0].institutions[0].ror | https://ror.org/01k97gp34 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I200332995 |
| authorships[0].institutions[0].country_code | DE |
| authorships[0].institutions[0].display_name | TU Dortmund University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Matthias Fey |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Tu Dortmund University |
| authorships[1].author.id | https://openalex.org/A5073462022 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-4093-9840 |
| authorships[1].author.display_name | Jan Eric Lenssen |
| authorships[1].countries | DE |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I200332995 |
| authorships[1].affiliations[0].raw_affiliation_string | TU Dortmund |
| authorships[1].institutions[0].id | https://openalex.org/I200332995 |
| authorships[1].institutions[0].ror | https://ror.org/01k97gp34 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I200332995 |
| authorships[1].institutions[0].country_code | DE |
| authorships[1].institutions[0].display_name | TU Dortmund University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jan Eric Lenssen |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | TU Dortmund |
| authorships[2].author.id | https://openalex.org/A5004108638 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2530-8197 |
| authorships[2].author.display_name | Frank Weichert |
| authorships[2].countries | DE |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I200332995 |
| authorships[2].affiliations[0].raw_affiliation_string | Technical University of Dortmund, |
| authorships[2].institutions[0].id | https://openalex.org/I200332995 |
| authorships[2].institutions[0].ror | https://ror.org/01k97gp34 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I200332995 |
| authorships[2].institutions[0].country_code | DE |
| authorships[2].institutions[0].display_name | TU Dortmund University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Frank Weichert |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Technical University of Dortmund, |
| authorships[3].author.id | https://openalex.org/A5091272738 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5411-923X |
| authorships[3].author.display_name | Jure Leskovec |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I97018004 |
| authorships[3].affiliations[0].raw_affiliation_string | Stanford University () |
| authorships[3].institutions[0].id | https://openalex.org/I97018004 |
| authorships[3].institutions[0].ror | https://ror.org/00f54p054 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I97018004 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Stanford University |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Jure Leskovec |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Stanford University () |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2106.05609 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11273 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9987999796867371 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Advanced Graph Neural Networks |
| related_works | https://openalex.org/W3127144957, https://openalex.org/W3169904068, https://openalex.org/W2889956396, https://openalex.org/W2469438475, https://openalex.org/W3209192622, https://openalex.org/W2786554108, https://openalex.org/W11153862, https://openalex.org/W2974199725, https://openalex.org/W1573184733, https://openalex.org/W3156343063, https://openalex.org/W2981086289, https://openalex.org/W2412434091, https://openalex.org/W3087293054, https://openalex.org/W2185542187, https://openalex.org/W2965868507, https://openalex.org/W52445081, https://openalex.org/W3006898349, https://openalex.org/W3112497798, https://openalex.org/W2967526509, https://openalex.org/W3124794912 |
| cited_by_count | 11 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 3 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 4 |
| counts_by_year[2].year | 2022 |
| counts_by_year[2].cited_by_count | 2 |
| counts_by_year[3].year | 2021 |
| counts_by_year[3].cited_by_count | 2 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:arXiv.org:2106.05609 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2106.05609 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2106.05609 |
| primary_location.id | pmh:oai:arXiv.org:2106.05609 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2106.05609 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2106.05609 |
| publication_date | 2021-06-10 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 4 |
| abstract_inverted_index.We | 0, 78 |
| abstract_inverted_index.an | 108 |
| abstract_inverted_index.by | 22, 81 |
| abstract_inverted_index.in | 36, 95 |
| abstract_inverted_index.is | 66, 114 |
| abstract_inverted_index.of | 18, 53, 59, 74, 86, 104, 127 |
| abstract_inverted_index.on | 135 |
| abstract_inverted_index.or | 61 |
| abstract_inverted_index.to | 11, 31, 38, 57, 69, 92 |
| abstract_inverted_index.we | 98 |
| abstract_inverted_index.GAS | 14 |
| abstract_inverted_index.GPU | 33 |
| abstract_inverted_index.and | 89, 117, 131 |
| abstract_inverted_index.any | 44 |
| abstract_inverted_index.due | 56 |
| abstract_inverted_index.for | 6, 111 |
| abstract_inverted_index.how | 91 |
| abstract_inverted_index.our | 64, 105 |
| abstract_inverted_index.the | 19, 50, 71, 75, 101, 125 |
| abstract_inverted_index.GNN. | 77 |
| abstract_inverted_index.GNNs | 10 |
| abstract_inverted_index.able | 68 |
| abstract_inverted_index.both | 115 |
| abstract_inverted_index.fast | 116 |
| abstract_inverted_index.from | 26 |
| abstract_inverted_index.node | 40, 121 |
| abstract_inverted_index.show | 90, 99 |
| abstract_inverted_index.size | 41 |
| abstract_inverted_index.that | 100 |
| abstract_inverted_index.them | 94 |
| abstract_inverted_index.this | 80 |
| abstract_inverted_index.While | 46 |
| abstract_inverted_index.data. | 45 |
| abstract_inverted_index.edges | 60 |
| abstract_inverted_index.error | 84 |
| abstract_inverted_index.graph | 21 |
| abstract_inverted_index.input | 39 |
| abstract_inverted_index.large | 12 |
| abstract_inverted_index.power | 52, 73 |
| abstract_inverted_index.prior | 27 |
| abstract_inverted_index.their | 128 |
| abstract_inverted_index.(GAS), | 3 |
| abstract_inverted_index.PyGAS, | 107 |
| abstract_inverted_index.bounds | 85 |
| abstract_inverted_index.entire | 16 |
| abstract_inverted_index.learns | 119 |
| abstract_inverted_index.memory | 34 |
| abstract_inverted_index.prunes | 15 |
| abstract_inverted_index.weaken | 49 |
| abstract_inverted_index.PyTorch | 112 |
| abstract_inverted_index.achieve | 79 |
| abstract_inverted_index.closely | 123 |
| abstract_inverted_index.graphs. | 13, 137 |
| abstract_inverted_index.leading | 30 |
| abstract_inverted_index.message | 54 |
| abstract_inverted_index.passing | 55 |
| abstract_inverted_index.present | 1 |
| abstract_inverted_index.reaches | 132 |
| abstract_inverted_index.respect | 37 |
| abstract_inverted_index.scaling | 7 |
| abstract_inverted_index.tighten | 93 |
| abstract_inverted_index.without | 42 |
| abstract_inverted_index.approach | 65 |
| abstract_inverted_index.constant | 32 |
| abstract_inverted_index.dropping | 43 |
| abstract_inverted_index.existing | 47 |
| abstract_inverted_index.maintain | 70 |
| abstract_inverted_index.original | 76 |
| abstract_inverted_index.provably | 67 |
| abstract_inverted_index.training | 28 |
| abstract_inverted_index.arbitrary | 8 |
| abstract_inverted_index.extension | 110 |
| abstract_inverted_index.framework | 5 |
| abstract_inverted_index.practical | 102 |
| abstract_inverted_index.practice. | 96 |
| abstract_inverted_index.providing | 82 |
| abstract_inverted_index.resembles | 124 |
| abstract_inverted_index.solutions | 48 |
| abstract_inverted_index.sub-trees | 17 |
| abstract_inverted_index.utilizing | 23 |
| abstract_inverted_index.Geometric, | 113 |
| abstract_inverted_index.embeddings | 25, 88 |
| abstract_inverted_index.expressive | 51, 72, 120 |
| abstract_inverted_index.framework, | 106 |
| abstract_inverted_index.historical | 24, 87 |
| abstract_inverted_index.computation | 20 |
| abstract_inverted_index.consumption | 35 |
| abstract_inverted_index.easy-to-use | 109 |
| abstract_inverted_index.iterations, | 29 |
| abstract_inverted_index.large-scale | 136 |
| abstract_inverted_index.non-scaling | 129 |
| abstract_inverted_index.performance | 126, 134 |
| abstract_inverted_index.realization | 103 |
| abstract_inverted_index.Empirically, | 97 |
| abstract_inverted_index.GNNAutoScale | 2 |
| abstract_inverted_index.sub-sampling | 58 |
| abstract_inverted_index.approximation | 83 |
| abstract_inverted_index.counterparts, | 130 |
| abstract_inverted_index.non-trainable | 62 |
| abstract_inverted_index.propagations, | 63 |
| abstract_inverted_index.message-passing | 9 |
| abstract_inverted_index.representations, | 122 |
| abstract_inverted_index.state-of-the-art | 133 |
| abstract_inverted_index.memory-efficient, | 118 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |