Instance-Prototype Affinity Learning for Non-Exemplar Continual Graph Learning Article Swipe
Lei Song
,
Jiaxing Li
,
Shihan Guan
,
Youyong Kong
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2505.10040
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2505.10040
Graph Neural Networks (GNN) endure catastrophic forgetting, undermining their capacity to preserve previously acquired knowledge amid the assimilation of novel information. Rehearsal-based techniques revisit historical examples, adopted as a principal strategy to alleviate this phenomenon. However, memory explosion and privacy infringements impose significant constraints on their utility. Non-Exemplar methods circumvent the prior issues through Prototype Replay (PR), yet feature drift presents new challenges. In this paper, our empirical findings reveal that Prototype Contrastive Learning (PCL) exhibits less pronounced drift than conventional PR. Drawing upon PCL, we propose Instance-Prototype Affinity Learning (IPAL), a novel paradigm for Non-Exemplar Continual Graph Learning (NECGL). Exploiting graph structural information, we formulate Topology-Integrated Gaussian Prototypes (TIGP), guiding feature distributions towards high-impact nodes to augment the model's capacity for assimilating new knowledge. Instance-Prototype Affinity Distillation (IPAD) safeguards task memory by regularizing discontinuities in class relationships. Moreover, we embed a Decision Boundary Perception (DBP) mechanism within PCL, fostering greater inter-class discriminability. Evaluations on four node classification benchmark datasets demonstrate that our method outperforms existing state-of-the-art methods, achieving a better trade-off between plasticity and stability.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2505.10040
- https://arxiv.org/pdf/2505.10040
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415199282
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415199282Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2505.10040Digital Object Identifier
- Title
-
Instance-Prototype Affinity Learning for Non-Exemplar Continual Graph LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-05-15Full publication date if available
- Authors
-
Lei Song, Jiaxing Li, Shihan Guan, Youyong KongList of authors in order
- Landing page
-
https://arxiv.org/abs/2505.10040Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2505.10040Direct 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/2505.10040Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415199282 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2505.10040 |
| ids.doi | https://doi.org/10.48550/arxiv.2505.10040 |
| ids.openalex | https://openalex.org/W4415199282 |
| fwci | |
| type | preprint |
| title | Instance-Prototype Affinity Learning for Non-Exemplar Continual Graph Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11550 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9937000274658203 |
| 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 | Text and Document Classification Technologies |
| topics[1].id | https://openalex.org/T12535 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9735999703407288 |
| 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 Data Classification |
| topics[2].id | https://openalex.org/T10057 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9625999927520752 |
| 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 | Face and Expression Recognition |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2505.10040 |
| 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/2505.10040 |
| 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/2505.10040 |
| locations[1].id | doi:10.48550/arxiv.2505.10040 |
| 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.2505.10040 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5016557698 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-9287-9643 |
| authorships[0].author.display_name | Lei Song |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Song, Lei |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100636528 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-7048-9284 |
| authorships[1].author.display_name | Jiaxing Li |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Li, Jiaxing |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5071768918 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3563-5308 |
| authorships[2].author.display_name | Shihan Guan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Guan, Shihan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5008751186 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-2095-8470 |
| authorships[3].author.display_name | Youyong Kong |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Kong, Youyong |
| authorships[3].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2505.10040 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-15T00:00:00 |
| display_name | Instance-Prototype Affinity Learning for Non-Exemplar Continual Graph Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11550 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9937000274658203 |
| 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 | Text and Document Classification Technologies |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2505.10040 |
| 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/2505.10040 |
| 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/2505.10040 |
| primary_location.id | pmh:oai:arXiv.org:2505.10040 |
| 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/2505.10040 |
| 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/2505.10040 |
| publication_date | 2025-05-15 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 28, 91, 141, 169 |
| abstract_inverted_index.In | 63 |
| abstract_inverted_index.as | 27 |
| abstract_inverted_index.by | 132 |
| abstract_inverted_index.in | 135 |
| abstract_inverted_index.of | 18 |
| abstract_inverted_index.on | 44, 154 |
| abstract_inverted_index.to | 10, 31, 116 |
| abstract_inverted_index.we | 85, 104, 139 |
| abstract_inverted_index.PR. | 81 |
| abstract_inverted_index.and | 38, 174 |
| abstract_inverted_index.for | 94, 121 |
| abstract_inverted_index.new | 61, 123 |
| abstract_inverted_index.our | 66, 162 |
| abstract_inverted_index.the | 16, 50, 118 |
| abstract_inverted_index.yet | 57 |
| abstract_inverted_index.PCL, | 84, 148 |
| abstract_inverted_index.amid | 15 |
| abstract_inverted_index.four | 155 |
| abstract_inverted_index.less | 76 |
| abstract_inverted_index.node | 156 |
| abstract_inverted_index.task | 130 |
| abstract_inverted_index.than | 79 |
| abstract_inverted_index.that | 70, 161 |
| abstract_inverted_index.this | 33, 64 |
| abstract_inverted_index.upon | 83 |
| abstract_inverted_index.(DBP) | 145 |
| abstract_inverted_index.(GNN) | 3 |
| abstract_inverted_index.(PCL) | 74 |
| abstract_inverted_index.(PR), | 56 |
| abstract_inverted_index.Graph | 0, 97 |
| abstract_inverted_index.class | 136 |
| abstract_inverted_index.drift | 59, 78 |
| abstract_inverted_index.embed | 140 |
| abstract_inverted_index.graph | 101 |
| abstract_inverted_index.nodes | 115 |
| abstract_inverted_index.novel | 19, 92 |
| abstract_inverted_index.prior | 51 |
| abstract_inverted_index.their | 8, 45 |
| abstract_inverted_index.(IPAD) | 128 |
| abstract_inverted_index.Neural | 1 |
| abstract_inverted_index.Replay | 55 |
| abstract_inverted_index.better | 170 |
| abstract_inverted_index.endure | 4 |
| abstract_inverted_index.impose | 41 |
| abstract_inverted_index.issues | 52 |
| abstract_inverted_index.memory | 36, 131 |
| abstract_inverted_index.method | 163 |
| abstract_inverted_index.paper, | 65 |
| abstract_inverted_index.reveal | 69 |
| abstract_inverted_index.within | 147 |
| abstract_inverted_index.(IPAL), | 90 |
| abstract_inverted_index.(TIGP), | 109 |
| abstract_inverted_index.Drawing | 82 |
| abstract_inverted_index.adopted | 26 |
| abstract_inverted_index.augment | 117 |
| abstract_inverted_index.between | 172 |
| abstract_inverted_index.feature | 58, 111 |
| abstract_inverted_index.greater | 150 |
| abstract_inverted_index.guiding | 110 |
| abstract_inverted_index.methods | 48 |
| abstract_inverted_index.model's | 119 |
| abstract_inverted_index.privacy | 39 |
| abstract_inverted_index.propose | 86 |
| abstract_inverted_index.revisit | 23 |
| abstract_inverted_index.through | 53 |
| abstract_inverted_index.towards | 113 |
| abstract_inverted_index.(NECGL). | 99 |
| abstract_inverted_index.Affinity | 88, 126 |
| abstract_inverted_index.Boundary | 143 |
| abstract_inverted_index.Decision | 142 |
| abstract_inverted_index.Gaussian | 107 |
| abstract_inverted_index.However, | 35 |
| abstract_inverted_index.Learning | 73, 89, 98 |
| abstract_inverted_index.Networks | 2 |
| abstract_inverted_index.acquired | 13 |
| abstract_inverted_index.capacity | 9, 120 |
| abstract_inverted_index.datasets | 159 |
| abstract_inverted_index.exhibits | 75 |
| abstract_inverted_index.existing | 165 |
| abstract_inverted_index.findings | 68 |
| abstract_inverted_index.methods, | 167 |
| abstract_inverted_index.paradigm | 93 |
| abstract_inverted_index.presents | 60 |
| abstract_inverted_index.preserve | 11 |
| abstract_inverted_index.strategy | 30 |
| abstract_inverted_index.utility. | 46 |
| abstract_inverted_index.Continual | 96 |
| abstract_inverted_index.Moreover, | 138 |
| abstract_inverted_index.Prototype | 54, 71 |
| abstract_inverted_index.achieving | 168 |
| abstract_inverted_index.alleviate | 32 |
| abstract_inverted_index.benchmark | 158 |
| abstract_inverted_index.empirical | 67 |
| abstract_inverted_index.examples, | 25 |
| abstract_inverted_index.explosion | 37 |
| abstract_inverted_index.formulate | 105 |
| abstract_inverted_index.fostering | 149 |
| abstract_inverted_index.knowledge | 14 |
| abstract_inverted_index.mechanism | 146 |
| abstract_inverted_index.principal | 29 |
| abstract_inverted_index.trade-off | 171 |
| abstract_inverted_index.Exploiting | 100 |
| abstract_inverted_index.Perception | 144 |
| abstract_inverted_index.Prototypes | 108 |
| abstract_inverted_index.circumvent | 49 |
| abstract_inverted_index.historical | 24 |
| abstract_inverted_index.knowledge. | 124 |
| abstract_inverted_index.plasticity | 173 |
| abstract_inverted_index.previously | 12 |
| abstract_inverted_index.pronounced | 77 |
| abstract_inverted_index.safeguards | 129 |
| abstract_inverted_index.stability. | 175 |
| abstract_inverted_index.structural | 102 |
| abstract_inverted_index.techniques | 22 |
| abstract_inverted_index.Contrastive | 72 |
| abstract_inverted_index.Evaluations | 153 |
| abstract_inverted_index.challenges. | 62 |
| abstract_inverted_index.constraints | 43 |
| abstract_inverted_index.demonstrate | 160 |
| abstract_inverted_index.forgetting, | 6 |
| abstract_inverted_index.high-impact | 114 |
| abstract_inverted_index.inter-class | 151 |
| abstract_inverted_index.outperforms | 164 |
| abstract_inverted_index.phenomenon. | 34 |
| abstract_inverted_index.significant | 42 |
| abstract_inverted_index.undermining | 7 |
| abstract_inverted_index.Distillation | 127 |
| abstract_inverted_index.Non-Exemplar | 47, 95 |
| abstract_inverted_index.assimilating | 122 |
| abstract_inverted_index.assimilation | 17 |
| abstract_inverted_index.catastrophic | 5 |
| abstract_inverted_index.conventional | 80 |
| abstract_inverted_index.information, | 103 |
| abstract_inverted_index.information. | 20 |
| abstract_inverted_index.regularizing | 133 |
| abstract_inverted_index.distributions | 112 |
| abstract_inverted_index.infringements | 40 |
| abstract_inverted_index.classification | 157 |
| abstract_inverted_index.relationships. | 137 |
| abstract_inverted_index.Rehearsal-based | 21 |
| abstract_inverted_index.discontinuities | 134 |
| abstract_inverted_index.state-of-the-art | 166 |
| abstract_inverted_index.discriminability. | 152 |
| abstract_inverted_index.Instance-Prototype | 87, 125 |
| abstract_inverted_index.Topology-Integrated | 106 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |