Rethinking Deep Contrastive Learning with Embedding Memory Article Swipe
Haozhi Zhang
,
Xun Wang
,
Weilin Huang
,
Matthew R. Scott
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2103.14003
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2103.14003
Pair-wise loss functions have been extensively studied and shown to continuously improve the performance of deep metric learning (DML). However, they are primarily designed with intuition based on simple toy examples, and experimentally identifying the truly effective design is difficult in complicated, real-world cases. In this paper, we provide a new methodology for systematically studying weighting strategies of various pair-wise loss functions, and rethink pair weighting with an embedding memory. We delve into the weighting mechanisms by decomposing the pair-wise functions, and study positive and negative weights separately using direct weight assignment. This allows us to study various weighting functions deeply and systematically via weight curves, and identify a number of meaningful, comprehensive and insightful facts, which come up with our key observation on memory-based DML: it is critical to mine hard negatives and discard easy negatives which are less informative and redundant, but weighting on positive pairs is not helpful. This results in an efficient but surprisingly simple rule to design the weighting scheme, making it significantly different from existing mini-batch based methods which design various sophisticated loss functions to weight pairs carefully. Finally, we conduct extensive experiments on three large-scale visual retrieval benchmarks, and demonstrate the superiority of memory-based DML over recent mini-batch based approaches, by using a simple contrastive loss with momentum-updated memory.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2103.14003
- https://arxiv.org/pdf/2103.14003
- OA Status
- green
- Cited By
- 1
- References
- 10
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3136911909
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3136911909Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2103.14003Digital Object Identifier
- Title
-
Rethinking Deep Contrastive Learning with Embedding MemoryWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-03-25Full publication date if available
- Authors
-
Haozhi Zhang, Xun Wang, Weilin Huang, Matthew R. ScottList of authors in order
- Landing page
-
https://arxiv.org/abs/2103.14003Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2103.14003Direct 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/2103.14003Direct OA link when available
- Concepts
-
Weighting, Embedding, Computer science, Intuition, Simple (philosophy), Metric (unit), Artificial intelligence, Key (lock), Theoretical computer science, Algorithm, Machine learning, Engineering, Operations management, Radiology, Computer security, Epistemology, Philosophy, MedicineTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2021: 1Per-year citation counts (last 5 years)
- References (count)
-
10Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3136911909 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2103.14003 |
| ids.doi | https://doi.org/10.48550/arxiv.2103.14003 |
| ids.mag | 3136911909 |
| ids.openalex | https://openalex.org/W3136911909 |
| fwci | |
| type | preprint |
| title | Rethinking Deep Contrastive Learning with Embedding Memory |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10627 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9994999766349792 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Advanced Image and Video Retrieval Techniques |
| topics[1].id | https://openalex.org/T11448 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9987999796867371 |
| 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 | Face recognition and analysis |
| topics[2].id | https://openalex.org/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9965000152587891 |
| 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 | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C183115368 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9093753099441528 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q856577 |
| concepts[0].display_name | Weighting |
| concepts[1].id | https://openalex.org/C41608201 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7334423065185547 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q980509 |
| concepts[1].display_name | Embedding |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6790728569030762 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C132010649 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6425726413726807 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q189222 |
| concepts[3].display_name | Intuition |
| concepts[4].id | https://openalex.org/C2780586882 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5019652843475342 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7520643 |
| concepts[4].display_name | Simple (philosophy) |
| concepts[5].id | https://openalex.org/C176217482 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4943103790283203 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q860554 |
| concepts[5].display_name | Metric (unit) |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.48431888222694397 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C26517878 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4387821555137634 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q228039 |
| concepts[7].display_name | Key (lock) |
| concepts[8].id | https://openalex.org/C80444323 |
| concepts[8].level | 1 |
| concepts[8].score | 0.4207150936126709 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[8].display_name | Theoretical computer science |
| concepts[9].id | https://openalex.org/C11413529 |
| concepts[9].level | 1 |
| concepts[9].score | 0.3914395570755005 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[9].display_name | Algorithm |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3911263346672058 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C127413603 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0901276171207428 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[11].display_name | Engineering |
| concepts[12].id | https://openalex.org/C21547014 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1423657 |
| concepts[12].display_name | Operations management |
| concepts[13].id | https://openalex.org/C126838900 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q77604 |
| concepts[13].display_name | Radiology |
| concepts[14].id | https://openalex.org/C38652104 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[14].display_name | Computer security |
| concepts[15].id | https://openalex.org/C111472728 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[15].display_name | Epistemology |
| concepts[16].id | https://openalex.org/C138885662 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[16].display_name | Philosophy |
| concepts[17].id | https://openalex.org/C71924100 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[17].display_name | Medicine |
| keywords[0].id | https://openalex.org/keywords/weighting |
| keywords[0].score | 0.9093753099441528 |
| keywords[0].display_name | Weighting |
| keywords[1].id | https://openalex.org/keywords/embedding |
| keywords[1].score | 0.7334423065185547 |
| keywords[1].display_name | Embedding |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6790728569030762 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/intuition |
| keywords[3].score | 0.6425726413726807 |
| keywords[3].display_name | Intuition |
| keywords[4].id | https://openalex.org/keywords/simple |
| keywords[4].score | 0.5019652843475342 |
| keywords[4].display_name | Simple (philosophy) |
| keywords[5].id | https://openalex.org/keywords/metric |
| keywords[5].score | 0.4943103790283203 |
| keywords[5].display_name | Metric (unit) |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.48431888222694397 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/key |
| keywords[7].score | 0.4387821555137634 |
| keywords[7].display_name | Key (lock) |
| keywords[8].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[8].score | 0.4207150936126709 |
| keywords[8].display_name | Theoretical computer science |
| keywords[9].id | https://openalex.org/keywords/algorithm |
| keywords[9].score | 0.3914395570755005 |
| keywords[9].display_name | Algorithm |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.3911263346672058 |
| keywords[10].display_name | Machine learning |
| keywords[11].id | https://openalex.org/keywords/engineering |
| keywords[11].score | 0.0901276171207428 |
| keywords[11].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2103.14003 |
| 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/2103.14003 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| 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/2103.14003 |
| locations[1].id | doi:10.48550/arxiv.2103.14003 |
| 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 | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| 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/10.48550/arxiv.2103.14003 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101480431 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Haozhi Zhang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Haozhi Zhang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100333854 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2741-433X |
| authorships[1].author.display_name | Xun Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xun Wang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101909917 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-1520-4140 |
| authorships[2].author.display_name | Weilin Huang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Weilin Huang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5019329248 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-1404-4437 |
| authorships[3].author.display_name | Matthew R. Scott |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Matthew R. Scott |
| authorships[3].is_corresponding | False |
| 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/2103.14003 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Rethinking Deep Contrastive Learning with Embedding Memory |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10627 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9994999766349792 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Advanced Image and Video Retrieval Techniques |
| related_works | https://openalex.org/W2180954594, https://openalex.org/W2052835778, https://openalex.org/W2049003611, https://openalex.org/W2108418243, https://openalex.org/W2127804977, https://openalex.org/W164103134, https://openalex.org/W2787352659, https://openalex.org/W1970611213, https://openalex.org/W4206560911, https://openalex.org/W4372260270 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2103.14003 |
| 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/2103.14003 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| 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/2103.14003 |
| primary_location.id | pmh:oai:arXiv.org:2103.14003 |
| 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/2103.14003 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| 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/2103.14003 |
| publication_date | 2021-03-25 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W3011927872, https://openalex.org/W1797268635, https://openalex.org/W2779066530, https://openalex.org/W2973134629, https://openalex.org/W2605102252, https://openalex.org/W2962723992, https://openalex.org/W2613997951, https://openalex.org/W2138011018, https://openalex.org/W2964271799, https://openalex.org/W2895347732 |
| referenced_works_count | 10 |
| abstract_inverted_index.a | 49, 108, 209 |
| abstract_inverted_index.In | 44 |
| abstract_inverted_index.We | 70 |
| abstract_inverted_index.an | 67, 154 |
| abstract_inverted_index.by | 76, 207 |
| abstract_inverted_index.in | 40, 153 |
| abstract_inverted_index.is | 38, 127, 148 |
| abstract_inverted_index.it | 126, 166 |
| abstract_inverted_index.of | 14, 57, 110, 199 |
| abstract_inverted_index.on | 27, 123, 145, 189 |
| abstract_inverted_index.to | 9, 95, 129, 160, 180 |
| abstract_inverted_index.up | 118 |
| abstract_inverted_index.us | 94 |
| abstract_inverted_index.we | 47, 185 |
| abstract_inverted_index.DML | 201 |
| abstract_inverted_index.and | 7, 31, 62, 81, 84, 101, 106, 113, 133, 141, 195 |
| abstract_inverted_index.are | 21, 138 |
| abstract_inverted_index.but | 143, 156 |
| abstract_inverted_index.for | 52 |
| abstract_inverted_index.key | 121 |
| abstract_inverted_index.new | 50 |
| abstract_inverted_index.not | 149 |
| abstract_inverted_index.our | 120 |
| abstract_inverted_index.the | 12, 34, 73, 78, 162, 197 |
| abstract_inverted_index.toy | 29 |
| abstract_inverted_index.via | 103 |
| abstract_inverted_index.DML: | 125 |
| abstract_inverted_index.This | 92, 151 |
| abstract_inverted_index.been | 4 |
| abstract_inverted_index.come | 117 |
| abstract_inverted_index.deep | 15 |
| abstract_inverted_index.easy | 135 |
| abstract_inverted_index.from | 169 |
| abstract_inverted_index.hard | 131 |
| abstract_inverted_index.have | 3 |
| abstract_inverted_index.into | 72 |
| abstract_inverted_index.less | 139 |
| abstract_inverted_index.loss | 1, 60, 178, 212 |
| abstract_inverted_index.mine | 130 |
| abstract_inverted_index.over | 202 |
| abstract_inverted_index.pair | 64 |
| abstract_inverted_index.rule | 159 |
| abstract_inverted_index.they | 20 |
| abstract_inverted_index.this | 45 |
| abstract_inverted_index.with | 24, 66, 119, 213 |
| abstract_inverted_index.based | 26, 172, 205 |
| abstract_inverted_index.delve | 71 |
| abstract_inverted_index.pairs | 147, 182 |
| abstract_inverted_index.shown | 8 |
| abstract_inverted_index.study | 82, 96 |
| abstract_inverted_index.three | 190 |
| abstract_inverted_index.truly | 35 |
| abstract_inverted_index.using | 88, 208 |
| abstract_inverted_index.which | 116, 137, 174 |
| abstract_inverted_index.(DML). | 18 |
| abstract_inverted_index.allows | 93 |
| abstract_inverted_index.cases. | 43 |
| abstract_inverted_index.deeply | 100 |
| abstract_inverted_index.design | 37, 161, 175 |
| abstract_inverted_index.direct | 89 |
| abstract_inverted_index.facts, | 115 |
| abstract_inverted_index.making | 165 |
| abstract_inverted_index.metric | 16 |
| abstract_inverted_index.number | 109 |
| abstract_inverted_index.paper, | 46 |
| abstract_inverted_index.recent | 203 |
| abstract_inverted_index.simple | 28, 158, 210 |
| abstract_inverted_index.visual | 192 |
| abstract_inverted_index.weight | 90, 104, 181 |
| abstract_inverted_index.conduct | 186 |
| abstract_inverted_index.curves, | 105 |
| abstract_inverted_index.discard | 134 |
| abstract_inverted_index.improve | 11 |
| abstract_inverted_index.memory. | 69, 215 |
| abstract_inverted_index.methods | 173 |
| abstract_inverted_index.provide | 48 |
| abstract_inverted_index.results | 152 |
| abstract_inverted_index.rethink | 63 |
| abstract_inverted_index.scheme, | 164 |
| abstract_inverted_index.studied | 6 |
| abstract_inverted_index.various | 58, 97, 176 |
| abstract_inverted_index.weights | 86 |
| abstract_inverted_index.Finally, | 184 |
| abstract_inverted_index.However, | 19 |
| abstract_inverted_index.critical | 128 |
| abstract_inverted_index.designed | 23 |
| abstract_inverted_index.existing | 170 |
| abstract_inverted_index.helpful. | 150 |
| abstract_inverted_index.identify | 107 |
| abstract_inverted_index.learning | 17 |
| abstract_inverted_index.negative | 85 |
| abstract_inverted_index.positive | 83, 146 |
| abstract_inverted_index.studying | 54 |
| abstract_inverted_index.Pair-wise | 0 |
| abstract_inverted_index.different | 168 |
| abstract_inverted_index.difficult | 39 |
| abstract_inverted_index.effective | 36 |
| abstract_inverted_index.efficient | 155 |
| abstract_inverted_index.embedding | 68 |
| abstract_inverted_index.examples, | 30 |
| abstract_inverted_index.extensive | 187 |
| abstract_inverted_index.functions | 2, 99, 179 |
| abstract_inverted_index.intuition | 25 |
| abstract_inverted_index.negatives | 132, 136 |
| abstract_inverted_index.pair-wise | 59, 79 |
| abstract_inverted_index.primarily | 22 |
| abstract_inverted_index.retrieval | 193 |
| abstract_inverted_index.weighting | 55, 65, 74, 98, 144, 163 |
| abstract_inverted_index.carefully. | 183 |
| abstract_inverted_index.functions, | 61, 80 |
| abstract_inverted_index.insightful | 114 |
| abstract_inverted_index.mechanisms | 75 |
| abstract_inverted_index.mini-batch | 171, 204 |
| abstract_inverted_index.real-world | 42 |
| abstract_inverted_index.redundant, | 142 |
| abstract_inverted_index.separately | 87 |
| abstract_inverted_index.strategies | 56 |
| abstract_inverted_index.approaches, | 206 |
| abstract_inverted_index.assignment. | 91 |
| abstract_inverted_index.benchmarks, | 194 |
| abstract_inverted_index.contrastive | 211 |
| abstract_inverted_index.decomposing | 77 |
| abstract_inverted_index.demonstrate | 196 |
| abstract_inverted_index.experiments | 188 |
| abstract_inverted_index.extensively | 5 |
| abstract_inverted_index.identifying | 33 |
| abstract_inverted_index.informative | 140 |
| abstract_inverted_index.large-scale | 191 |
| abstract_inverted_index.meaningful, | 111 |
| abstract_inverted_index.methodology | 51 |
| abstract_inverted_index.observation | 122 |
| abstract_inverted_index.performance | 13 |
| abstract_inverted_index.superiority | 198 |
| abstract_inverted_index.complicated, | 41 |
| abstract_inverted_index.continuously | 10 |
| abstract_inverted_index.memory-based | 124, 200 |
| abstract_inverted_index.surprisingly | 157 |
| abstract_inverted_index.comprehensive | 112 |
| abstract_inverted_index.significantly | 167 |
| abstract_inverted_index.sophisticated | 177 |
| abstract_inverted_index.experimentally | 32 |
| abstract_inverted_index.systematically | 53, 102 |
| abstract_inverted_index.momentum-updated | 214 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |