FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning Article Swipe
Renqiang Luo
,
Huafei Huang
,
Ivan Lee
,
Chengpei Xu
,
Jianzhong Qi
,
Feng Xia
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2412.10669
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2412.10669
Recent studies have highlighted significant fairness issues in Graph Transformer (GT) models, particularly against subgroups defined by sensitive features. Additionally, GTs are computationally intensive and memory-demanding, limiting their application to large-scale graphs. Our experiments demonstrate that graph partitioning can enhance the fairness of GT models while reducing computational complexity. To understand this improvement, we conducted a theoretical investigation into the root causes of fairness issues in GT models. We found that the sensitive features of higher-order nodes disproportionately influence lower-order nodes, resulting in sensitive feature bias. We propose Fairness-aware scalable GT based on Graph Partitioning (FairGP), which partitions the graph to minimize the negative impact of higher-order nodes. By optimizing attention mechanisms, FairGP mitigates the bias introduced by global attention, thereby enhancing fairness. Extensive empirical evaluations on six real-world datasets validate the superior performance of FairGP in achieving fairness compared to state-of-the-art methods. The codes are available at https://github.com/LuoRenqiang/FairGP.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2412.10669
- https://arxiv.org/pdf/2412.10669
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4405468239
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4405468239Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2412.10669Digital Object Identifier
- Title
-
FairGP: A Scalable and Fair Graph Transformer Using Graph PartitioningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-12-14Full publication date if available
- Authors
-
Renqiang Luo, Huafei Huang, Ivan Lee, Chengpei Xu, Jianzhong Qi, Feng XiaList of authors in order
- Landing page
-
https://arxiv.org/abs/2412.10669Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2412.10669Direct 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/2412.10669Direct OA link when available
- Concepts
-
Computer science, Scalability, Graph, Parallel computing, Theoretical computer science, DatabaseTop 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/W4405468239 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2412.10669 |
| ids.doi | https://doi.org/10.48550/arxiv.2412.10669 |
| ids.openalex | https://openalex.org/W4405468239 |
| fwci | |
| type | preprint |
| title | FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning |
| 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 | 0.9639999866485596 |
| 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/T10883 |
| topics[1].field.id | https://openalex.org/fields/33 |
| topics[1].field.display_name | Social Sciences |
| topics[1].score | 0.9354000091552734 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/3311 |
| topics[1].subfield.display_name | Safety Research |
| topics[1].display_name | Ethics and Social Impacts of AI |
| topics[2].id | https://openalex.org/T10720 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9143999814987183 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1703 |
| topics[2].subfield.display_name | Computational Theory and Mathematics |
| topics[2].display_name | Complexity and Algorithms in Graphs |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6106670498847961 |
| 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 | 0.561793863773346 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q727490 |
| concepts[1].display_name | Scalability |
| concepts[2].id | https://openalex.org/C132525143 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5224924683570862 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[2].display_name | Graph |
| concepts[3].id | https://openalex.org/C173608175 |
| concepts[3].level | 1 |
| concepts[3].score | 0.42502880096435547 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[3].display_name | Parallel computing |
| concepts[4].id | https://openalex.org/C80444323 |
| concepts[4].level | 1 |
| concepts[4].score | 0.399834543466568 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[4].display_name | Theoretical computer science |
| concepts[5].id | https://openalex.org/C77088390 |
| concepts[5].level | 1 |
| concepts[5].score | 0.09538319706916809 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q8513 |
| concepts[5].display_name | Database |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6106670498847961 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/scalability |
| keywords[1].score | 0.561793863773346 |
| keywords[1].display_name | Scalability |
| keywords[2].id | https://openalex.org/keywords/graph |
| keywords[2].score | 0.5224924683570862 |
| keywords[2].display_name | Graph |
| keywords[3].id | https://openalex.org/keywords/parallel-computing |
| keywords[3].score | 0.42502880096435547 |
| keywords[3].display_name | Parallel computing |
| keywords[4].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[4].score | 0.399834543466568 |
| keywords[4].display_name | Theoretical computer science |
| keywords[5].id | https://openalex.org/keywords/database |
| keywords[5].score | 0.09538319706916809 |
| keywords[5].display_name | Database |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2412.10669 |
| 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/2412.10669 |
| 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/2412.10669 |
| locations[1].id | doi:10.48550/arxiv.2412.10669 |
| 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.2412.10669 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5070730125 |
| authorships[0].author.orcid | https://orcid.org/0009-0002-8313-9835 |
| authorships[0].author.display_name | Renqiang Luo |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Luo, Renqiang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5076195752 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-7916-1645 |
| authorships[1].author.display_name | Huafei Huang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Huang, Huafei |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5067502218 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2826-6367 |
| authorships[2].author.display_name | Ivan Lee |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Lee, Ivan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5002596064 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8860-7701 |
| authorships[3].author.display_name | Chengpei Xu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Xu, Chengpei |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5022290876 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6501-9050 |
| authorships[4].author.display_name | Jianzhong Qi |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Qi, Jianzhong |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5089615958 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-8324-1859 |
| authorships[5].author.display_name | Feng Xia |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Xia, Feng |
| authorships[5].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/2412.10669 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | FairGP: A Scalable and Fair Graph Transformer Using Graph Partitioning |
| 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 | 0.9639999866485596 |
| 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/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4401278057 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2412.10669 |
| 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/2412.10669 |
| 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/2412.10669 |
| primary_location.id | pmh:oai:arXiv.org:2412.10669 |
| 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/2412.10669 |
| 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/2412.10669 |
| publication_date | 2024-12-14 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 55 |
| abstract_inverted_index.By | 108 |
| abstract_inverted_index.GT | 43, 66, 90 |
| abstract_inverted_index.To | 49 |
| abstract_inverted_index.We | 68, 86 |
| abstract_inverted_index.at | 147 |
| abstract_inverted_index.by | 16, 117 |
| abstract_inverted_index.in | 7, 65, 82, 136 |
| abstract_inverted_index.of | 42, 62, 74, 105, 134 |
| abstract_inverted_index.on | 92, 126 |
| abstract_inverted_index.to | 29, 100, 140 |
| abstract_inverted_index.we | 53 |
| abstract_inverted_index.GTs | 20 |
| abstract_inverted_index.Our | 32 |
| abstract_inverted_index.The | 143 |
| abstract_inverted_index.and | 24 |
| abstract_inverted_index.are | 21, 145 |
| abstract_inverted_index.can | 38 |
| abstract_inverted_index.six | 127 |
| abstract_inverted_index.the | 40, 59, 71, 98, 102, 114, 131 |
| abstract_inverted_index.(GT) | 10 |
| abstract_inverted_index.bias | 115 |
| abstract_inverted_index.have | 2 |
| abstract_inverted_index.into | 58 |
| abstract_inverted_index.root | 60 |
| abstract_inverted_index.that | 35, 70 |
| abstract_inverted_index.this | 51 |
| abstract_inverted_index.Graph | 8, 93 |
| abstract_inverted_index.based | 91 |
| abstract_inverted_index.bias. | 85 |
| abstract_inverted_index.codes | 144 |
| abstract_inverted_index.found | 69 |
| abstract_inverted_index.graph | 36, 99 |
| abstract_inverted_index.nodes | 76 |
| abstract_inverted_index.their | 27 |
| abstract_inverted_index.which | 96 |
| abstract_inverted_index.while | 45 |
| abstract_inverted_index.FairGP | 112, 135 |
| abstract_inverted_index.Recent | 0 |
| abstract_inverted_index.causes | 61 |
| abstract_inverted_index.global | 118 |
| abstract_inverted_index.impact | 104 |
| abstract_inverted_index.issues | 6, 64 |
| abstract_inverted_index.models | 44 |
| abstract_inverted_index.nodes, | 80 |
| abstract_inverted_index.nodes. | 107 |
| abstract_inverted_index.against | 13 |
| abstract_inverted_index.defined | 15 |
| abstract_inverted_index.enhance | 39 |
| abstract_inverted_index.feature | 84 |
| abstract_inverted_index.graphs. | 31 |
| abstract_inverted_index.models, | 11 |
| abstract_inverted_index.models. | 67 |
| abstract_inverted_index.propose | 87 |
| abstract_inverted_index.studies | 1 |
| abstract_inverted_index.thereby | 120 |
| abstract_inverted_index.compared | 139 |
| abstract_inverted_index.datasets | 129 |
| abstract_inverted_index.fairness | 5, 41, 63, 138 |
| abstract_inverted_index.features | 73 |
| abstract_inverted_index.limiting | 26 |
| abstract_inverted_index.methods. | 142 |
| abstract_inverted_index.minimize | 101 |
| abstract_inverted_index.negative | 103 |
| abstract_inverted_index.reducing | 46 |
| abstract_inverted_index.scalable | 89 |
| abstract_inverted_index.superior | 132 |
| abstract_inverted_index.validate | 130 |
| abstract_inverted_index.(FairGP), | 95 |
| abstract_inverted_index.Extensive | 123 |
| abstract_inverted_index.achieving | 137 |
| abstract_inverted_index.attention | 110 |
| abstract_inverted_index.available | 146 |
| abstract_inverted_index.conducted | 54 |
| abstract_inverted_index.empirical | 124 |
| abstract_inverted_index.enhancing | 121 |
| abstract_inverted_index.fairness. | 122 |
| abstract_inverted_index.features. | 18 |
| abstract_inverted_index.influence | 78 |
| abstract_inverted_index.intensive | 23 |
| abstract_inverted_index.mitigates | 113 |
| abstract_inverted_index.resulting | 81 |
| abstract_inverted_index.sensitive | 17, 72, 83 |
| abstract_inverted_index.subgroups | 14 |
| abstract_inverted_index.attention, | 119 |
| abstract_inverted_index.introduced | 116 |
| abstract_inverted_index.optimizing | 109 |
| abstract_inverted_index.partitions | 97 |
| abstract_inverted_index.real-world | 128 |
| abstract_inverted_index.understand | 50 |
| abstract_inverted_index.Transformer | 9 |
| abstract_inverted_index.application | 28 |
| abstract_inverted_index.complexity. | 48 |
| abstract_inverted_index.demonstrate | 34 |
| abstract_inverted_index.evaluations | 125 |
| abstract_inverted_index.experiments | 33 |
| abstract_inverted_index.highlighted | 3 |
| abstract_inverted_index.large-scale | 30 |
| abstract_inverted_index.lower-order | 79 |
| abstract_inverted_index.mechanisms, | 111 |
| abstract_inverted_index.performance | 133 |
| abstract_inverted_index.significant | 4 |
| abstract_inverted_index.theoretical | 56 |
| abstract_inverted_index.Partitioning | 94 |
| abstract_inverted_index.higher-order | 75, 106 |
| abstract_inverted_index.improvement, | 52 |
| abstract_inverted_index.particularly | 12 |
| abstract_inverted_index.partitioning | 37 |
| abstract_inverted_index.Additionally, | 19 |
| abstract_inverted_index.computational | 47 |
| abstract_inverted_index.investigation | 57 |
| abstract_inverted_index.Fairness-aware | 88 |
| abstract_inverted_index.computationally | 22 |
| abstract_inverted_index.state-of-the-art | 141 |
| abstract_inverted_index.memory-demanding, | 25 |
| abstract_inverted_index.disproportionately | 77 |
| abstract_inverted_index.https://github.com/LuoRenqiang/FairGP. | 148 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |