A Deep Dive Into Understanding The Random Walk-Based Temporal Graph Learning Article Swipe
Nishil Talati
,
Di Jin
,
Haojie Ye
,
Ajay Brahmakshatriya
,
Ganesh Dasika
,
Saman Amarasinghe
,
Trevor Mudge
,
Danai Koutra
,
Ronald Dreslinski
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.5281/zenodo.5522917
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.5281/zenodo.5522917
Machine learning on graph data has gained sig-nificant interest because of its applicability to various domainsranging from product recommendations to drug discovery. Whilethere is a rapid growth in the algorithmic community, the com-puter architecture community has so far focused on a subset ofgraph learning algorithms including Graph Convolution Network(GCN), and a few others. In this paper, we study another, morescalable, graph learning algorithm based onrandom walks, whichoperates on dynamic input graphs and has attracted less attentionin the architecture community compared to GCN. We proposehigh-performance CPU and GPU implementations of two keygraph learning tasks, that cover a broad class of applications,using random walks on continuous-time dynamic graphs: linkprediction and node classification. We show that the resultingworkload exhibits distinct characteristics, measured in terms ofirregularity, core and memory utilization, and cache hit rates,compared to graph traversals, deep learning, and GCN. Wefurther conduct an in-depth performance analysis focused onboth algorithm and hardware to guide future software optimiza-tion and architecture exploration. The algorithm-focused studypresents a rich trade-off space between algorithmic performanceand runtime complexity to identify optimization opportunities.We find an optimal hyperparameter setting that strikes balancein this trade-off space. Using this setting, we also perform adetailed microarchitectural characterization to analyze hardwarebehavior of these applications and uncover execution bottlenecks,which include high cache misses and dependency-related stalls.The outcome of our study includes recommendations for furtherperformance optimization, and open-source implementations forfuture investigation.
Related Topics
Concepts
Metadata
- Type
- paratext
- Language
- en
- Landing Page
- https://zenodo.org/record/5522917
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4226052808
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4226052808Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.5281/zenodo.5522917Digital Object Identifier
- Title
-
A Deep Dive Into Understanding The Random Walk-Based Temporal Graph LearningWork title
- Type
-
paratextOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-11-07Full publication date if available
- Authors
-
Nishil Talati, Di Jin, Haojie Ye, Ajay Brahmakshatriya, Ganesh Dasika, Saman Amarasinghe, Trevor Mudge, Danai Koutra, Ronald DreslinskiList of authors in order
- Landing page
-
https://zenodo.org/record/5522917Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://zenodo.org/record/5522917Direct OA link when available
- Concepts
-
Computer science, Random walk, Deep learning, Artificial intelligence, Graph, Data science, Theoretical computer science, Mathematics, StatisticsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4226052808 |
|---|---|
| doi | https://doi.org/10.5281/zenodo.5522917 |
| ids.doi | https://doi.org/10.5281/zenodo.5522917 |
| ids.openalex | https://openalex.org/W4226052808 |
| fwci | 0.0 |
| type | paratext |
| title | A Deep Dive Into Understanding The Random Walk-Based Temporal Graph Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11106 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9142000079154968 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1711 |
| topics[0].subfield.display_name | Signal Processing |
| topics[0].display_name | Data Management and Algorithms |
| topics[1].id | https://openalex.org/T11550 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9067000150680542 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Text and Document Classification Technologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6924393177032471 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C121194460 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6678478717803955 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q856741 |
| concepts[1].display_name | Random walk |
| concepts[2].id | https://openalex.org/C108583219 |
| concepts[2].level | 2 |
| concepts[2].score | 0.46654319763183594 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[2].display_name | Deep learning |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.46044787764549255 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C132525143 |
| concepts[4].level | 2 |
| concepts[4].score | 0.43620288372039795 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[4].display_name | Graph |
| concepts[5].id | https://openalex.org/C2522767166 |
| concepts[5].level | 1 |
| concepts[5].score | 0.36168110370635986 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2374463 |
| concepts[5].display_name | Data science |
| concepts[6].id | https://openalex.org/C80444323 |
| concepts[6].level | 1 |
| concepts[6].score | 0.30919766426086426 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[6].display_name | Theoretical computer science |
| concepts[7].id | https://openalex.org/C33923547 |
| concepts[7].level | 0 |
| concepts[7].score | 0.1086040735244751 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[7].display_name | Mathematics |
| concepts[8].id | https://openalex.org/C105795698 |
| concepts[8].level | 1 |
| concepts[8].score | 0.08972421288490295 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[8].display_name | Statistics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6924393177032471 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/random-walk |
| keywords[1].score | 0.6678478717803955 |
| keywords[1].display_name | Random walk |
| keywords[2].id | https://openalex.org/keywords/deep-learning |
| keywords[2].score | 0.46654319763183594 |
| keywords[2].display_name | Deep learning |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.46044787764549255 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/graph |
| keywords[4].score | 0.43620288372039795 |
| keywords[4].display_name | Graph |
| keywords[5].id | https://openalex.org/keywords/data-science |
| keywords[5].score | 0.36168110370635986 |
| keywords[5].display_name | Data science |
| keywords[6].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[6].score | 0.30919766426086426 |
| keywords[6].display_name | Theoretical computer science |
| keywords[7].id | https://openalex.org/keywords/mathematics |
| keywords[7].score | 0.1086040735244751 |
| keywords[7].display_name | Mathematics |
| keywords[8].id | https://openalex.org/keywords/statistics |
| keywords[8].score | 0.08972421288490295 |
| keywords[8].display_name | Statistics |
| language | en |
| locations[0].id | pmh:oai:zenodo.org:5522917 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400562 |
| 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 | Zenodo (CERN European Organization for Nuclear Research) |
| locations[0].source.host_organization | https://openalex.org/I67311998 |
| locations[0].source.host_organization_name | European Organization for Nuclear Research |
| locations[0].source.host_organization_lineage | https://openalex.org/I67311998 |
| locations[0].license | other-oa |
| locations[0].pdf_url | |
| locations[0].version | submittedVersion |
| locations[0].raw_type | info:eu-repo/semantics/conferencePaper |
| locations[0].license_id | https://openalex.org/licenses/other-oa |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://zenodo.org/record/5522917 |
| locations[1].id | doi:10.5281/zenodo.5522917 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400562 |
| 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 | Zenodo (CERN European Organization for Nuclear Research) |
| locations[1].source.host_organization | https://openalex.org/I67311998 |
| locations[1].source.host_organization_name | European Organization for Nuclear Research |
| locations[1].source.host_organization_lineage | https://openalex.org/I67311998 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.5281/zenodo.5522917 |
| indexed_in | datacite |
| authorships[0].author.id | https://openalex.org/A5063661349 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2457-4119 |
| authorships[0].author.display_name | Nishil Talati |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I27837315 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Michigan |
| authorships[0].institutions[0].id | https://openalex.org/I27837315 |
| authorships[0].institutions[0].ror | https://ror.org/00jmfr291 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I27837315 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | University of Michigan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Nishil Talati |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of Michigan |
| authorships[1].author.id | https://openalex.org/A5012455357 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-7445-9936 |
| authorships[1].author.display_name | Di Jin |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I27837315 |
| authorships[1].affiliations[0].raw_affiliation_string | University of Michigan |
| authorships[1].institutions[0].id | https://openalex.org/I27837315 |
| authorships[1].institutions[0].ror | https://ror.org/00jmfr291 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I27837315 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | University of Michigan |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Di Jin |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of Michigan |
| authorships[2].author.id | https://openalex.org/A5028799837 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5360-5159 |
| authorships[2].author.display_name | Haojie Ye |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I27837315 |
| authorships[2].affiliations[0].raw_affiliation_string | University of Michigan |
| authorships[2].institutions[0].id | https://openalex.org/I27837315 |
| authorships[2].institutions[0].ror | https://ror.org/00jmfr291 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I27837315 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | University of Michigan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Haojie Ye |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | University of Michigan |
| authorships[3].author.id | https://openalex.org/A5046807118 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-5295-4186 |
| authorships[3].author.display_name | Ajay Brahmakshatriya |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I63966007 |
| authorships[3].affiliations[0].raw_affiliation_string | Massachusetts Institute of Technology |
| authorships[3].institutions[0].id | https://openalex.org/I63966007 |
| authorships[3].institutions[0].ror | https://ror.org/042nb2s44 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I63966007 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Massachusetts Institute of Technology |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Ajay Brahmakshatriya |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Massachusetts Institute of Technology |
| authorships[4].author.id | https://openalex.org/A5004292742 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Ganesh Dasika |
| authorships[4].affiliations[0].raw_affiliation_string | AMD Research |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ganesh Dasika |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | AMD Research |
| authorships[5].author.id | https://openalex.org/A5046791216 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-7231-7643 |
| authorships[5].author.display_name | Saman Amarasinghe |
| authorships[5].countries | US |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I63966007 |
| authorships[5].affiliations[0].raw_affiliation_string | Massachusetts Institute of Technology |
| authorships[5].institutions[0].id | https://openalex.org/I63966007 |
| authorships[5].institutions[0].ror | https://ror.org/042nb2s44 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I63966007 |
| authorships[5].institutions[0].country_code | US |
| authorships[5].institutions[0].display_name | Massachusetts Institute of Technology |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Saman Amarasinghe |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Massachusetts Institute of Technology |
| authorships[6].author.id | https://openalex.org/A5037541525 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-7845-2187 |
| authorships[6].author.display_name | Trevor Mudge |
| authorships[6].countries | US |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I27837315 |
| authorships[6].affiliations[0].raw_affiliation_string | University of Michigan |
| authorships[6].institutions[0].id | https://openalex.org/I27837315 |
| authorships[6].institutions[0].ror | https://ror.org/00jmfr291 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I27837315 |
| authorships[6].institutions[0].country_code | US |
| authorships[6].institutions[0].display_name | University of Michigan |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Trevor Mudge |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | University of Michigan |
| authorships[7].author.id | https://openalex.org/A5015996266 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-3206-8179 |
| authorships[7].author.display_name | Danai Koutra |
| authorships[7].countries | US |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I27837315 |
| authorships[7].affiliations[0].raw_affiliation_string | University of Michigan |
| authorships[7].institutions[0].id | https://openalex.org/I27837315 |
| authorships[7].institutions[0].ror | https://ror.org/00jmfr291 |
| authorships[7].institutions[0].type | education |
| authorships[7].institutions[0].lineage | https://openalex.org/I27837315 |
| authorships[7].institutions[0].country_code | US |
| authorships[7].institutions[0].display_name | University of Michigan |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Danai Koutra |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | University of Michigan |
| authorships[8].author.id | https://openalex.org/A5014250626 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Ronald Dreslinski |
| authorships[8].countries | US |
| authorships[8].affiliations[0].institution_ids | https://openalex.org/I27837315 |
| authorships[8].affiliations[0].raw_affiliation_string | University of Michigan |
| authorships[8].institutions[0].id | https://openalex.org/I27837315 |
| authorships[8].institutions[0].ror | https://ror.org/00jmfr291 |
| authorships[8].institutions[0].type | education |
| authorships[8].institutions[0].lineage | https://openalex.org/I27837315 |
| authorships[8].institutions[0].country_code | US |
| authorships[8].institutions[0].display_name | University of Michigan |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Ronald Dreslinski |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | University of Michigan |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://zenodo.org/record/5522917 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | A Deep Dive Into Understanding The Random Walk-Based Temporal Graph Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11106 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9142000079154968 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1711 |
| primary_topic.subfield.display_name | Signal Processing |
| primary_topic.display_name | Data Management and Algorithms |
| related_works | https://openalex.org/W4210836535, https://openalex.org/W2151399529, https://openalex.org/W2952419077, https://openalex.org/W4286857724, https://openalex.org/W4372260176, https://openalex.org/W2891771806, https://openalex.org/W4281693073, https://openalex.org/W2890855364, https://openalex.org/W2008857988, https://openalex.org/W2892310698 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:zenodo.org:5522917 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400562 |
| 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 | Zenodo (CERN European Organization for Nuclear Research) |
| best_oa_location.source.host_organization | https://openalex.org/I67311998 |
| best_oa_location.source.host_organization_name | European Organization for Nuclear Research |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I67311998 |
| best_oa_location.license | other-oa |
| best_oa_location.pdf_url | |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | info:eu-repo/semantics/conferencePaper |
| best_oa_location.license_id | https://openalex.org/licenses/other-oa |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://zenodo.org/record/5522917 |
| primary_location.id | pmh:oai:zenodo.org:5522917 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400562 |
| 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 | Zenodo (CERN European Organization for Nuclear Research) |
| primary_location.source.host_organization | https://openalex.org/I67311998 |
| primary_location.source.host_organization_name | European Organization for Nuclear Research |
| primary_location.source.host_organization_lineage | https://openalex.org/I67311998 |
| primary_location.license | other-oa |
| primary_location.pdf_url | |
| primary_location.version | submittedVersion |
| primary_location.raw_type | info:eu-repo/semantics/conferencePaper |
| primary_location.license_id | https://openalex.org/licenses/other-oa |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://zenodo.org/record/5522917 |
| publication_date | 2021-11-07 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 24, 40, 50, 95, 159 |
| abstract_inverted_index.In | 53 |
| abstract_inverted_index.We | 82, 110 |
| abstract_inverted_index.an | 139, 173 |
| abstract_inverted_index.in | 27, 119 |
| abstract_inverted_index.is | 23 |
| abstract_inverted_index.of | 10, 88, 98, 195, 210 |
| abstract_inverted_index.on | 2, 39, 67, 102 |
| abstract_inverted_index.so | 36 |
| abstract_inverted_index.to | 13, 19, 80, 130, 148, 168, 192 |
| abstract_inverted_index.we | 56, 186 |
| abstract_inverted_index.CPU | 84 |
| abstract_inverted_index.GPU | 86 |
| abstract_inverted_index.The | 156 |
| abstract_inverted_index.and | 49, 71, 85, 107, 123, 126, 135, 146, 153, 198, 206, 218 |
| abstract_inverted_index.far | 37 |
| abstract_inverted_index.few | 51 |
| abstract_inverted_index.for | 215 |
| abstract_inverted_index.has | 5, 35, 72 |
| abstract_inverted_index.hit | 128 |
| abstract_inverted_index.its | 11 |
| abstract_inverted_index.our | 211 |
| abstract_inverted_index.the | 28, 31, 76, 113 |
| abstract_inverted_index.two | 89 |
| abstract_inverted_index.GCN. | 81, 136 |
| abstract_inverted_index.also | 187 |
| abstract_inverted_index.core | 122 |
| abstract_inverted_index.data | 4 |
| abstract_inverted_index.deep | 133 |
| abstract_inverted_index.drug | 20 |
| abstract_inverted_index.find | 172 |
| abstract_inverted_index.from | 16 |
| abstract_inverted_index.high | 203 |
| abstract_inverted_index.less | 74 |
| abstract_inverted_index.node | 108 |
| abstract_inverted_index.rich | 160 |
| abstract_inverted_index.show | 111 |
| abstract_inverted_index.that | 93, 112, 177 |
| abstract_inverted_index.this | 54, 180, 184 |
| abstract_inverted_index.Graph | 46 |
| abstract_inverted_index.Using | 183 |
| abstract_inverted_index.based | 63 |
| abstract_inverted_index.broad | 96 |
| abstract_inverted_index.cache | 127, 204 |
| abstract_inverted_index.class | 97 |
| abstract_inverted_index.cover | 94 |
| abstract_inverted_index.graph | 3, 60, 131 |
| abstract_inverted_index.guide | 149 |
| abstract_inverted_index.input | 69 |
| abstract_inverted_index.rapid | 25 |
| abstract_inverted_index.space | 162 |
| abstract_inverted_index.study | 57, 212 |
| abstract_inverted_index.terms | 120 |
| abstract_inverted_index.these | 196 |
| abstract_inverted_index.walks | 101 |
| abstract_inverted_index.future | 150 |
| abstract_inverted_index.gained | 6 |
| abstract_inverted_index.graphs | 70 |
| abstract_inverted_index.growth | 26 |
| abstract_inverted_index.memory | 124 |
| abstract_inverted_index.misses | 205 |
| abstract_inverted_index.onboth | 144 |
| abstract_inverted_index.paper, | 55 |
| abstract_inverted_index.random | 100 |
| abstract_inverted_index.space. | 182 |
| abstract_inverted_index.subset | 41 |
| abstract_inverted_index.tasks, | 92 |
| abstract_inverted_index.walks, | 65 |
| abstract_inverted_index.Machine | 0 |
| abstract_inverted_index.analyze | 193 |
| abstract_inverted_index.because | 9 |
| abstract_inverted_index.between | 163 |
| abstract_inverted_index.conduct | 138 |
| abstract_inverted_index.dynamic | 68, 104 |
| abstract_inverted_index.focused | 38, 143 |
| abstract_inverted_index.graphs: | 105 |
| abstract_inverted_index.include | 202 |
| abstract_inverted_index.ofgraph | 42 |
| abstract_inverted_index.optimal | 174 |
| abstract_inverted_index.others. | 52 |
| abstract_inverted_index.outcome | 209 |
| abstract_inverted_index.perform | 188 |
| abstract_inverted_index.product | 17 |
| abstract_inverted_index.runtime | 166 |
| abstract_inverted_index.setting | 176 |
| abstract_inverted_index.strikes | 178 |
| abstract_inverted_index.uncover | 199 |
| abstract_inverted_index.various | 14 |
| abstract_inverted_index.analysis | 142 |
| abstract_inverted_index.another, | 58 |
| abstract_inverted_index.compared | 79 |
| abstract_inverted_index.distinct | 116 |
| abstract_inverted_index.exhibits | 115 |
| abstract_inverted_index.hardware | 147 |
| abstract_inverted_index.identify | 169 |
| abstract_inverted_index.in-depth | 140 |
| abstract_inverted_index.includes | 213 |
| abstract_inverted_index.interest | 8 |
| abstract_inverted_index.keygraph | 90 |
| abstract_inverted_index.learning | 1, 43, 61, 91 |
| abstract_inverted_index.measured | 118 |
| abstract_inverted_index.onrandom | 64 |
| abstract_inverted_index.setting, | 185 |
| abstract_inverted_index.software | 151 |
| abstract_inverted_index.Wefurther | 137 |
| abstract_inverted_index.adetailed | 189 |
| abstract_inverted_index.algorithm | 62, 145 |
| abstract_inverted_index.attracted | 73 |
| abstract_inverted_index.balancein | 179 |
| abstract_inverted_index.com-puter | 32 |
| abstract_inverted_index.community | 34, 78 |
| abstract_inverted_index.execution | 200 |
| abstract_inverted_index.forfuture | 221 |
| abstract_inverted_index.including | 45 |
| abstract_inverted_index.learning, | 134 |
| abstract_inverted_index.trade-off | 161, 181 |
| abstract_inverted_index.Whilethere | 22 |
| abstract_inverted_index.algorithms | 44 |
| abstract_inverted_index.community, | 30 |
| abstract_inverted_index.complexity | 167 |
| abstract_inverted_index.discovery. | 21 |
| abstract_inverted_index.stalls.The | 208 |
| abstract_inverted_index.Convolution | 47 |
| abstract_inverted_index.algorithmic | 29, 164 |
| abstract_inverted_index.attentionin | 75 |
| abstract_inverted_index.open-source | 219 |
| abstract_inverted_index.performance | 141 |
| abstract_inverted_index.traversals, | 132 |
| abstract_inverted_index.applications | 197 |
| abstract_inverted_index.architecture | 33, 77, 154 |
| abstract_inverted_index.exploration. | 155 |
| abstract_inverted_index.optimization | 170 |
| abstract_inverted_index.sig-nificant | 7 |
| abstract_inverted_index.utilization, | 125 |
| abstract_inverted_index.Network(GCN), | 48 |
| abstract_inverted_index.applicability | 12 |
| abstract_inverted_index.morescalable, | 59 |
| abstract_inverted_index.optimiza-tion | 152 |
| abstract_inverted_index.optimization, | 217 |
| abstract_inverted_index.studypresents | 158 |
| abstract_inverted_index.whichoperates | 66 |
| abstract_inverted_index.domainsranging | 15 |
| abstract_inverted_index.hyperparameter | 175 |
| abstract_inverted_index.investigation. | 222 |
| abstract_inverted_index.linkprediction | 106 |
| abstract_inverted_index.performanceand | 165 |
| abstract_inverted_index.rates,compared | 129 |
| abstract_inverted_index.classification. | 109 |
| abstract_inverted_index.continuous-time | 103 |
| abstract_inverted_index.implementations | 87, 220 |
| abstract_inverted_index.ofirregularity, | 121 |
| abstract_inverted_index.recommendations | 18, 214 |
| abstract_inverted_index.characteristics, | 117 |
| abstract_inverted_index.characterization | 191 |
| abstract_inverted_index.hardwarebehavior | 194 |
| abstract_inverted_index.opportunities.We | 171 |
| abstract_inverted_index.algorithm-focused | 157 |
| abstract_inverted_index.bottlenecks,which | 201 |
| abstract_inverted_index.resultingworkload | 114 |
| abstract_inverted_index.applications,using | 99 |
| abstract_inverted_index.dependency-related | 207 |
| abstract_inverted_index.furtherperformance | 216 |
| abstract_inverted_index.microarchitectural | 190 |
| abstract_inverted_index.proposehigh-performance | 83 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile.value | 0.19626407 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |