Learning the travelling salesperson problem requires rethinking generalization Article Swipe
Chaitanya K. Joshi
,
Quentin Cappart
,
Louis-Martin Rousseau
,
Thomas Laurent
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1007/s10601-022-09327-y
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1007/s10601-022-09327-y
End-to-end training of neural network solvers for graph combinatorial optimization problems such as the Travelling Salesperson Problem (TSP) have seen a surge of interest recently, but remain intractable and inefficient beyond graphs with few hundreds of nodes. While state-of-the-art learning-driven approaches for TSP perform closely to classical solvers when trained on trivially small sizes, they are unable to generalize the learnt policy to larger instances at practical scales. This work presents an end-to-end neural combinatorial optimization pipeline that unifies several recent papers in order to identify the inductive biases, model architectures and learning algorithms that promote generalization to instances larger than those seen in training. Our controlled experiments provide the first principled investigation into such zero-shot generalization, revealing that extrapolating beyond training data requires rethinking the neural combinatorial optimization pipeline, from network layers and learning paradigms to evaluation protocols. Additionally, we analyze recent advances in deep learning for routing problems through the lens of our pipeline and provide new directions to stimulate future research.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1007/s10601-022-09327-y
- OA Status
- hybrid
- Cited By
- 68
- References
- 59
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4293107948
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4293107948Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1007/s10601-022-09327-yDigital Object Identifier
- Title
-
Learning the travelling salesperson problem requires rethinking generalizationWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-04-01Full publication date if available
- Authors
-
Chaitanya K. Joshi, Quentin Cappart, Louis-Martin Rousseau, Thomas LaurentList of authors in order
- Landing page
-
https://doi.org/10.1007/s10601-022-09327-yPublisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1007/s10601-022-09327-yDirect OA link when available
- Concepts
-
Generalization, Computer science, Pipeline (software), Artificial intelligence, Artificial neural network, Machine learning, Deep learning, Graph, Theoretical computer science, Mathematics, Mathematical analysis, Programming languageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
68Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 31, 2024: 28, 2023: 7, 2022: 2Per-year citation counts (last 5 years)
- References (count)
-
59Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4293107948 |
|---|---|
| doi | https://doi.org/10.1007/s10601-022-09327-y |
| ids.doi | https://doi.org/10.1007/s10601-022-09327-y |
| ids.openalex | https://openalex.org/W4293107948 |
| fwci | 13.31431978 |
| type | article |
| title | Learning the travelling salesperson problem requires rethinking generalization |
| biblio.issue | 1-2 |
| biblio.volume | 27 |
| biblio.last_page | 98 |
| biblio.first_page | 70 |
| 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 | 0.9980000257492065 |
| 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/T12072 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9937999844551086 |
| 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 | Machine Learning and Algorithms |
| topics[2].id | https://openalex.org/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9916999936103821 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Topic Modeling |
| is_xpac | False |
| apc_list.value | 2290 |
| apc_list.currency | EUR |
| apc_list.value_usd | 2890 |
| apc_paid.value | 2290 |
| apc_paid.currency | EUR |
| apc_paid.value_usd | 2890 |
| concepts[0].id | https://openalex.org/C177148314 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7621183395385742 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q170084 |
| concepts[0].display_name | Generalization |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7367192506790161 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C43521106 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6465436816215515 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q2165493 |
| concepts[2].display_name | Pipeline (software) |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6151784062385559 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C50644808 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5023818016052246 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[4].display_name | Artificial neural network |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4549323320388794 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C108583219 |
| concepts[6].level | 2 |
| concepts[6].score | 0.42215263843536377 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[6].display_name | Deep learning |
| concepts[7].id | https://openalex.org/C132525143 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4144875109195709 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[7].display_name | Graph |
| concepts[8].id | https://openalex.org/C80444323 |
| concepts[8].level | 1 |
| concepts[8].score | 0.36453211307525635 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[8].display_name | Theoretical computer science |
| concepts[9].id | https://openalex.org/C33923547 |
| concepts[9].level | 0 |
| concepts[9].score | 0.1160283088684082 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[9].display_name | Mathematics |
| concepts[10].id | https://openalex.org/C134306372 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[10].display_name | Mathematical analysis |
| concepts[11].id | https://openalex.org/C199360897 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[11].display_name | Programming language |
| keywords[0].id | https://openalex.org/keywords/generalization |
| keywords[0].score | 0.7621183395385742 |
| keywords[0].display_name | Generalization |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7367192506790161 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/pipeline |
| keywords[2].score | 0.6465436816215515 |
| keywords[2].display_name | Pipeline (software) |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.6151784062385559 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[4].score | 0.5023818016052246 |
| keywords[4].display_name | Artificial neural network |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.4549323320388794 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/deep-learning |
| keywords[6].score | 0.42215263843536377 |
| keywords[6].display_name | Deep learning |
| keywords[7].id | https://openalex.org/keywords/graph |
| keywords[7].score | 0.4144875109195709 |
| keywords[7].display_name | Graph |
| keywords[8].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[8].score | 0.36453211307525635 |
| keywords[8].display_name | Theoretical computer science |
| keywords[9].id | https://openalex.org/keywords/mathematics |
| keywords[9].score | 0.1160283088684082 |
| keywords[9].display_name | Mathematics |
| language | en |
| locations[0].id | doi:10.1007/s10601-022-09327-y |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S75534514 |
| locations[0].source.issn | 1383-7133, 1572-9354 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1383-7133 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Constraints |
| locations[0].source.host_organization | https://openalex.org/P4310319900 |
| locations[0].source.host_organization_name | Springer Science+Business Media |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319900, https://openalex.org/P4310319965 |
| locations[0].source.host_organization_lineage_names | Springer Science+Business Media, Springer Nature |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Constraints |
| locations[0].landing_page_url | https://doi.org/10.1007/s10601-022-09327-y |
| locations[1].id | pmh:oai:publications.polymtl.ca:50836 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306401013 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | PolyPublie (École Polytechnique de Montréal) |
| locations[1].source.host_organization | https://openalex.org/I45683168 |
| locations[1].source.host_organization_name | Polytechnique Montréal |
| locations[1].source.host_organization_lineage | https://openalex.org/I45683168 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | PeerReviewed |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://publications.polymtl.ca/50836/ |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5041429006 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4722-1815 |
| authorships[0].author.display_name | Chaitanya K. Joshi |
| authorships[0].countries | GB |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I241749 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Cambridge, Cambridge, UK |
| authorships[0].institutions[0].id | https://openalex.org/I241749 |
| authorships[0].institutions[0].ror | https://ror.org/013meh722 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I241749 |
| authorships[0].institutions[0].country_code | GB |
| authorships[0].institutions[0].display_name | University of Cambridge |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Chaitanya K. Joshi |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | University of Cambridge, Cambridge, UK |
| authorships[1].author.id | https://openalex.org/A5065781444 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-8742-0774 |
| authorships[1].author.display_name | Quentin Cappart |
| authorships[1].countries | CA |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I45683168 |
| authorships[1].affiliations[0].raw_affiliation_string | Ecole Polytechnique de Montréal, Montreal, Canada |
| authorships[1].institutions[0].id | https://openalex.org/I45683168 |
| authorships[1].institutions[0].ror | https://ror.org/05f8d4e86 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I45683168 |
| authorships[1].institutions[0].country_code | CA |
| authorships[1].institutions[0].display_name | Polytechnique Montréal |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Quentin Cappart |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Ecole Polytechnique de Montréal, Montreal, Canada |
| authorships[2].author.id | https://openalex.org/A5039209533 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6949-6014 |
| authorships[2].author.display_name | Louis-Martin Rousseau |
| authorships[2].countries | CA |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I45683168 |
| authorships[2].affiliations[0].raw_affiliation_string | Ecole Polytechnique de Montréal, Montreal, Canada |
| authorships[2].institutions[0].id | https://openalex.org/I45683168 |
| authorships[2].institutions[0].ror | https://ror.org/05f8d4e86 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I45683168 |
| authorships[2].institutions[0].country_code | CA |
| authorships[2].institutions[0].display_name | Polytechnique Montréal |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Louis-Martin Rousseau |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Ecole Polytechnique de Montréal, Montreal, Canada |
| authorships[3].author.id | https://openalex.org/A5024411628 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0953-774X |
| authorships[3].author.display_name | Thomas Laurent |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I35566140 |
| authorships[3].affiliations[0].raw_affiliation_string | Loyola Marymount University, Los Angeles, USA |
| authorships[3].institutions[0].id | https://openalex.org/I35566140 |
| authorships[3].institutions[0].ror | https://ror.org/00xhj8c72 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I35566140 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Loyola Marymount University |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Thomas Laurent |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Loyola Marymount University, Los Angeles, USA |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1007/s10601-022-09327-y |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Learning the travelling salesperson problem requires rethinking generalization |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9980000257492065 |
| 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/W4375867731, https://openalex.org/W2371138613, https://openalex.org/W2048963458, https://openalex.org/W43109613, https://openalex.org/W2359952343, https://openalex.org/W2080152487, https://openalex.org/W3037187668, https://openalex.org/W2239445980, https://openalex.org/W2995553446, https://openalex.org/W2120455979 |
| cited_by_count | 68 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 31 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 28 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 7 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 2 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1007/s10601-022-09327-y |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S75534514 |
| best_oa_location.source.issn | 1383-7133, 1572-9354 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 1383-7133 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Constraints |
| best_oa_location.source.host_organization | https://openalex.org/P4310319900 |
| best_oa_location.source.host_organization_name | Springer Science+Business Media |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319900, https://openalex.org/P4310319965 |
| best_oa_location.source.host_organization_lineage_names | Springer Science+Business Media, Springer Nature |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Constraints |
| best_oa_location.landing_page_url | https://doi.org/10.1007/s10601-022-09327-y |
| primary_location.id | doi:10.1007/s10601-022-09327-y |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S75534514 |
| primary_location.source.issn | 1383-7133, 1572-9354 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1383-7133 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Constraints |
| primary_location.source.host_organization | https://openalex.org/P4310319900 |
| primary_location.source.host_organization_name | Springer Science+Business Media |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319900, https://openalex.org/P4310319965 |
| primary_location.source.host_organization_lineage_names | Springer Science+Business Media, Springer Nature |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Constraints |
| primary_location.landing_page_url | https://doi.org/10.1007/s10601-022-09327-y |
| publication_date | 2022-04-01 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2054630393, https://openalex.org/W626292722, https://openalex.org/W2999044305, https://openalex.org/W3171752851, https://openalex.org/W6725207838, https://openalex.org/W2560592986, https://openalex.org/W3047863327, https://openalex.org/W2607264901, https://openalex.org/W6748262478, https://openalex.org/W2891230096, https://openalex.org/W2519887557, https://openalex.org/W6736685754, https://openalex.org/W6758687306, https://openalex.org/W2887603607, https://openalex.org/W2805798351, https://openalex.org/W2948268323, https://openalex.org/W2963772421, https://openalex.org/W3176327512, https://openalex.org/W2891638642, https://openalex.org/W2998339876, https://openalex.org/W6679436768, https://openalex.org/W2987288550, https://openalex.org/W3097232108, https://openalex.org/W6765959096, https://openalex.org/W3177337956, https://openalex.org/W6769524888, https://openalex.org/W2787189213, https://openalex.org/W2944956154, https://openalex.org/W2971093758, https://openalex.org/W2946061017, https://openalex.org/W3188522200, https://openalex.org/W3158330599, https://openalex.org/W6775947557, https://openalex.org/W6763392795, https://openalex.org/W3088584794, https://openalex.org/W2529996553, https://openalex.org/W2968986602, https://openalex.org/W2617411258, https://openalex.org/W3047687953, https://openalex.org/W2948162129, https://openalex.org/W2786722833, https://openalex.org/W2805177834, https://openalex.org/W2906351695, https://openalex.org/W6739901393, https://openalex.org/W6910730993, https://openalex.org/W2016589492, https://openalex.org/W4230563027, https://openalex.org/W6754929296, https://openalex.org/W3005941526, https://openalex.org/W3007134945, https://openalex.org/W2950220847, https://openalex.org/W6761551260, https://openalex.org/W2981852735, https://openalex.org/W3034214690, https://openalex.org/W3146106549, https://openalex.org/W3185606095, https://openalex.org/W3205832574, https://openalex.org/W3203997865, https://openalex.org/W2811124557 |
| referenced_works_count | 59 |
| abstract_inverted_index.a | 21 |
| abstract_inverted_index.an | 72 |
| abstract_inverted_index.as | 13 |
| abstract_inverted_index.at | 66 |
| abstract_inverted_index.in | 83, 104, 145 |
| abstract_inverted_index.of | 3, 23, 36, 154 |
| abstract_inverted_index.on | 51 |
| abstract_inverted_index.to | 46, 58, 63, 85, 98, 137, 161 |
| abstract_inverted_index.we | 141 |
| abstract_inverted_index.Our | 106 |
| abstract_inverted_index.TSP | 43 |
| abstract_inverted_index.and | 29, 92, 134, 157 |
| abstract_inverted_index.are | 56 |
| abstract_inverted_index.but | 26 |
| abstract_inverted_index.few | 34 |
| abstract_inverted_index.for | 7, 42, 148 |
| abstract_inverted_index.new | 159 |
| abstract_inverted_index.our | 155 |
| abstract_inverted_index.the | 14, 60, 87, 110, 126, 152 |
| abstract_inverted_index.This | 69 |
| abstract_inverted_index.data | 123 |
| abstract_inverted_index.deep | 146 |
| abstract_inverted_index.from | 131 |
| abstract_inverted_index.have | 19 |
| abstract_inverted_index.into | 114 |
| abstract_inverted_index.lens | 153 |
| abstract_inverted_index.seen | 20, 103 |
| abstract_inverted_index.such | 12, 115 |
| abstract_inverted_index.than | 101 |
| abstract_inverted_index.that | 78, 95, 119 |
| abstract_inverted_index.they | 55 |
| abstract_inverted_index.when | 49 |
| abstract_inverted_index.with | 33 |
| abstract_inverted_index.work | 70 |
| abstract_inverted_index.(TSP) | 18 |
| abstract_inverted_index.While | 38 |
| abstract_inverted_index.first | 111 |
| abstract_inverted_index.graph | 8 |
| abstract_inverted_index.model | 90 |
| abstract_inverted_index.order | 84 |
| abstract_inverted_index.small | 53 |
| abstract_inverted_index.surge | 22 |
| abstract_inverted_index.those | 102 |
| abstract_inverted_index.beyond | 31, 121 |
| abstract_inverted_index.future | 163 |
| abstract_inverted_index.graphs | 32 |
| abstract_inverted_index.larger | 64, 100 |
| abstract_inverted_index.layers | 133 |
| abstract_inverted_index.learnt | 61 |
| abstract_inverted_index.neural | 4, 74, 127 |
| abstract_inverted_index.nodes. | 37 |
| abstract_inverted_index.papers | 82 |
| abstract_inverted_index.policy | 62 |
| abstract_inverted_index.recent | 81, 143 |
| abstract_inverted_index.remain | 27 |
| abstract_inverted_index.sizes, | 54 |
| abstract_inverted_index.unable | 57 |
| abstract_inverted_index.Problem | 17 |
| abstract_inverted_index.analyze | 142 |
| abstract_inverted_index.biases, | 89 |
| abstract_inverted_index.closely | 45 |
| abstract_inverted_index.network | 5, 132 |
| abstract_inverted_index.perform | 44 |
| abstract_inverted_index.promote | 96 |
| abstract_inverted_index.provide | 109, 158 |
| abstract_inverted_index.routing | 149 |
| abstract_inverted_index.scales. | 68 |
| abstract_inverted_index.several | 80 |
| abstract_inverted_index.solvers | 6, 48 |
| abstract_inverted_index.through | 151 |
| abstract_inverted_index.trained | 50 |
| abstract_inverted_index.unifies | 79 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.advances | 144 |
| abstract_inverted_index.hundreds | 35 |
| abstract_inverted_index.identify | 86 |
| abstract_inverted_index.interest | 24 |
| abstract_inverted_index.learning | 93, 135, 147 |
| abstract_inverted_index.pipeline | 77, 156 |
| abstract_inverted_index.presents | 71 |
| abstract_inverted_index.problems | 11, 150 |
| abstract_inverted_index.requires | 124 |
| abstract_inverted_index.training | 2, 122 |
| abstract_inverted_index.classical | 47 |
| abstract_inverted_index.inductive | 88 |
| abstract_inverted_index.instances | 65, 99 |
| abstract_inverted_index.paradigms | 136 |
| abstract_inverted_index.pipeline, | 130 |
| abstract_inverted_index.practical | 67 |
| abstract_inverted_index.recently, | 25 |
| abstract_inverted_index.research. | 164 |
| abstract_inverted_index.revealing | 118 |
| abstract_inverted_index.stimulate | 162 |
| abstract_inverted_index.training. | 105 |
| abstract_inverted_index.trivially | 52 |
| abstract_inverted_index.zero-shot | 116 |
| abstract_inverted_index.End-to-end | 1 |
| abstract_inverted_index.Travelling | 15 |
| abstract_inverted_index.algorithms | 94 |
| abstract_inverted_index.approaches | 41 |
| abstract_inverted_index.controlled | 107 |
| abstract_inverted_index.directions | 160 |
| abstract_inverted_index.end-to-end | 73 |
| abstract_inverted_index.evaluation | 138 |
| abstract_inverted_index.generalize | 59 |
| abstract_inverted_index.principled | 112 |
| abstract_inverted_index.protocols. | 139 |
| abstract_inverted_index.rethinking | 125 |
| abstract_inverted_index.Salesperson | 16 |
| abstract_inverted_index.experiments | 108 |
| abstract_inverted_index.inefficient | 30 |
| abstract_inverted_index.intractable | 28 |
| abstract_inverted_index.optimization | 10, 76, 129 |
| abstract_inverted_index.Additionally, | 140 |
| abstract_inverted_index.architectures | 91 |
| abstract_inverted_index.combinatorial | 9, 75, 128 |
| abstract_inverted_index.extrapolating | 120 |
| abstract_inverted_index.investigation | 113 |
| abstract_inverted_index.generalization | 97 |
| abstract_inverted_index.generalization, | 117 |
| abstract_inverted_index.learning-driven | 40 |
| abstract_inverted_index.state-of-the-art | 39 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 94 |
| corresponding_author_ids | https://openalex.org/A5041429006 |
| countries_distinct_count | 3 |
| institutions_distinct_count | 4 |
| corresponding_institution_ids | https://openalex.org/I241749 |
| citation_normalized_percentile.value | 0.98458203 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |