D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability Article Swipe
Ruizhuo Song
,
Beiming Yuan
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.03452
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.03452
This paper is dedicated to addressing the challenge of enhancing the abstract reasoning capabilities of AI, particularly for tasks involving complex human concepts. We introduce Lico-Net, a novel reasoning engine grounded in deep learning theory, which encodes the logical structure of Raven's Progressive Matrices (RPM) problems into probabilistic representations. Lico-Net excels in solving RPM tasks. Furthermore, we propose Lico-Net-Bongard, a tailored version of Lico-Net for the Bongard-Logo problem, which also achieves high reasoning accuracy through probabilistic representations. However, we observe a mismatch between the way deep learning algorithms and humans induce reasoning concepts, primarily attributed to the inadequate quality of negative samples. Improper configuration of negative samples can convey erroneous conceptual information to deep learning algorithms, thereby distorting their learning objectives. To address this issue, we propose two novel approaches: first, treating different sample points within reasoning problems as mutual negative samples to alter the existing negative sample structure in the data; second, designing a negative sample generator based on a step-wise linear attention mechanism to produce high-quality negative samples. Experimental results demonstrate that these methods significantly improve the performance of Lico-Net (-Bongard) and other baseline models on the RPM and Bongard-Logo datasets, as well as in the domain of foundational vision model processing, particularly when addressing the NICO dataset's distribution shift problem. Our findings emphasize the importance of improving negative sample quality for enhancing the abstract reasoning capabilities of deep learning algorithms and suggest that systems represent a promising direction for future research in this field.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2403.03452
- https://arxiv.org/pdf/2403.03452
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4392575676
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4392575676Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2403.03452Digital Object Identifier
- Title
-
D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning AbilityWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-03-06Full publication date if available
- Authors
-
Ruizhuo Song, Beiming YuanList of authors in order
- Landing page
-
https://arxiv.org/abs/2403.03452Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2403.03452Direct 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/2403.03452Direct OA link when available
- Concepts
-
Logo (programming language), Computer science, Mathematical optimization, Engineering drawing, Computer vision, Artificial intelligence, Mathematics, Programming language, EngineeringTop 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/W4392575676 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2403.03452 |
| ids.doi | https://doi.org/10.48550/arxiv.2403.03452 |
| ids.openalex | https://openalex.org/W4392575676 |
| fwci | |
| type | preprint |
| title | D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10181 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.942300021648407 |
| 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 | Natural Language Processing Techniques |
| topics[1].id | https://openalex.org/T10601 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9254999756813049 |
| 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 | Handwritten Text Recognition Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2778720087 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7342267036437988 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q201436 |
| concepts[0].display_name | Logo (programming language) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5406522154808044 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C126255220 |
| concepts[2].level | 1 |
| concepts[2].score | 0.34411513805389404 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q141495 |
| concepts[2].display_name | Mathematical optimization |
| concepts[3].id | https://openalex.org/C199639397 |
| concepts[3].level | 1 |
| concepts[3].score | 0.3407430648803711 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1788588 |
| concepts[3].display_name | Engineering drawing |
| concepts[4].id | https://openalex.org/C31972630 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3345350921154022 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[4].display_name | Computer vision |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.33232882618904114 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C33923547 |
| concepts[6].level | 0 |
| concepts[6].score | 0.2810227870941162 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[6].display_name | Mathematics |
| concepts[7].id | https://openalex.org/C199360897 |
| concepts[7].level | 1 |
| concepts[7].score | 0.26470237970352173 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[7].display_name | Programming language |
| concepts[8].id | https://openalex.org/C127413603 |
| concepts[8].level | 0 |
| concepts[8].score | 0.1865536868572235 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[8].display_name | Engineering |
| keywords[0].id | https://openalex.org/keywords/logo |
| keywords[0].score | 0.7342267036437988 |
| keywords[0].display_name | Logo (programming language) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5406522154808044 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/mathematical-optimization |
| keywords[2].score | 0.34411513805389404 |
| keywords[2].display_name | Mathematical optimization |
| keywords[3].id | https://openalex.org/keywords/engineering-drawing |
| keywords[3].score | 0.3407430648803711 |
| keywords[3].display_name | Engineering drawing |
| keywords[4].id | https://openalex.org/keywords/computer-vision |
| keywords[4].score | 0.3345350921154022 |
| keywords[4].display_name | Computer vision |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.33232882618904114 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/mathematics |
| keywords[6].score | 0.2810227870941162 |
| keywords[6].display_name | Mathematics |
| keywords[7].id | https://openalex.org/keywords/programming-language |
| keywords[7].score | 0.26470237970352173 |
| keywords[7].display_name | Programming language |
| keywords[8].id | https://openalex.org/keywords/engineering |
| keywords[8].score | 0.1865536868572235 |
| keywords[8].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2403.03452 |
| 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/2403.03452 |
| 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/2403.03452 |
| locations[1].id | doi:10.48550/arxiv.2403.03452 |
| 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.2403.03452 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5040323322 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-6693-2738 |
| authorships[0].author.display_name | Ruizhuo Song |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Song, Ruizhuo |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5082057290 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Beiming Yuan |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Yuan, Beiming |
| authorships[1].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/2403.03452 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-03-08T00:00:00 |
| display_name | D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10181 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.942300021648407 |
| 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 | Natural Language Processing Techniques |
| related_works | https://openalex.org/W2058170566, https://openalex.org/W2755342338, https://openalex.org/W2772917594, https://openalex.org/W2775347418, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407, https://openalex.org/W2079911747, https://openalex.org/W1969923398 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2403.03452 |
| 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/2403.03452 |
| 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/2403.03452 |
| primary_location.id | pmh:oai:arXiv.org:2403.03452 |
| 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/2403.03452 |
| 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/2403.03452 |
| publication_date | 2024-03-06 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 26, 59, 80, 154, 160, 238 |
| abstract_inverted_index.To | 121 |
| abstract_inverted_index.We | 23 |
| abstract_inverted_index.as | 138, 193, 195 |
| abstract_inverted_index.in | 31, 51, 149, 196, 244 |
| abstract_inverted_index.is | 2 |
| abstract_inverted_index.of | 8, 14, 40, 62, 99, 104, 180, 199, 218, 229 |
| abstract_inverted_index.on | 159, 187 |
| abstract_inverted_index.to | 4, 95, 112, 142, 165 |
| abstract_inverted_index.we | 56, 78, 125 |
| abstract_inverted_index.AI, | 15 |
| abstract_inverted_index.Our | 213 |
| abstract_inverted_index.RPM | 53, 189 |
| abstract_inverted_index.and | 88, 183, 190, 233 |
| abstract_inverted_index.can | 107 |
| abstract_inverted_index.for | 17, 64, 223, 241 |
| abstract_inverted_index.the | 6, 10, 37, 65, 83, 96, 144, 150, 178, 188, 197, 207, 216, 225 |
| abstract_inverted_index.two | 127 |
| abstract_inverted_index.way | 84 |
| abstract_inverted_index.NICO | 208 |
| abstract_inverted_index.This | 0 |
| abstract_inverted_index.also | 69 |
| abstract_inverted_index.deep | 32, 85, 113, 230 |
| abstract_inverted_index.high | 71 |
| abstract_inverted_index.into | 46 |
| abstract_inverted_index.that | 173, 235 |
| abstract_inverted_index.this | 123, 245 |
| abstract_inverted_index.well | 194 |
| abstract_inverted_index.when | 205 |
| abstract_inverted_index.(RPM) | 44 |
| abstract_inverted_index.alter | 143 |
| abstract_inverted_index.based | 158 |
| abstract_inverted_index.data; | 151 |
| abstract_inverted_index.human | 21 |
| abstract_inverted_index.model | 202 |
| abstract_inverted_index.novel | 27, 128 |
| abstract_inverted_index.other | 184 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.shift | 211 |
| abstract_inverted_index.tasks | 18 |
| abstract_inverted_index.their | 118 |
| abstract_inverted_index.these | 174 |
| abstract_inverted_index.which | 35, 68 |
| abstract_inverted_index.convey | 108 |
| abstract_inverted_index.domain | 198 |
| abstract_inverted_index.engine | 29 |
| abstract_inverted_index.excels | 50 |
| abstract_inverted_index.field. | 246 |
| abstract_inverted_index.first, | 130 |
| abstract_inverted_index.future | 242 |
| abstract_inverted_index.humans | 89 |
| abstract_inverted_index.induce | 90 |
| abstract_inverted_index.issue, | 124 |
| abstract_inverted_index.linear | 162 |
| abstract_inverted_index.models | 186 |
| abstract_inverted_index.mutual | 139 |
| abstract_inverted_index.points | 134 |
| abstract_inverted_index.sample | 133, 147, 156, 221 |
| abstract_inverted_index.tasks. | 54 |
| abstract_inverted_index.vision | 201 |
| abstract_inverted_index.within | 135 |
| abstract_inverted_index.Raven's | 41 |
| abstract_inverted_index.address | 122 |
| abstract_inverted_index.between | 82 |
| abstract_inverted_index.complex | 20 |
| abstract_inverted_index.encodes | 36 |
| abstract_inverted_index.improve | 177 |
| abstract_inverted_index.logical | 38 |
| abstract_inverted_index.methods | 175 |
| abstract_inverted_index.observe | 79 |
| abstract_inverted_index.produce | 166 |
| abstract_inverted_index.propose | 57, 126 |
| abstract_inverted_index.quality | 98, 222 |
| abstract_inverted_index.results | 171 |
| abstract_inverted_index.samples | 106, 141 |
| abstract_inverted_index.second, | 152 |
| abstract_inverted_index.solving | 52 |
| abstract_inverted_index.suggest | 234 |
| abstract_inverted_index.systems | 236 |
| abstract_inverted_index.theory, | 34 |
| abstract_inverted_index.thereby | 116 |
| abstract_inverted_index.through | 74 |
| abstract_inverted_index.version | 61 |
| abstract_inverted_index.However, | 77 |
| abstract_inverted_index.Improper | 102 |
| abstract_inverted_index.Lico-Net | 49, 63, 181 |
| abstract_inverted_index.Matrices | 43 |
| abstract_inverted_index.abstract | 11, 226 |
| abstract_inverted_index.accuracy | 73 |
| abstract_inverted_index.achieves | 70 |
| abstract_inverted_index.baseline | 185 |
| abstract_inverted_index.existing | 145 |
| abstract_inverted_index.findings | 214 |
| abstract_inverted_index.grounded | 30 |
| abstract_inverted_index.learning | 33, 86, 114, 119, 231 |
| abstract_inverted_index.mismatch | 81 |
| abstract_inverted_index.negative | 100, 105, 140, 146, 155, 168, 220 |
| abstract_inverted_index.problem, | 67 |
| abstract_inverted_index.problem. | 212 |
| abstract_inverted_index.problems | 45, 137 |
| abstract_inverted_index.research | 243 |
| abstract_inverted_index.samples. | 101, 169 |
| abstract_inverted_index.tailored | 60 |
| abstract_inverted_index.treating | 131 |
| abstract_inverted_index.Lico-Net, | 25 |
| abstract_inverted_index.attention | 163 |
| abstract_inverted_index.challenge | 7 |
| abstract_inverted_index.concepts, | 92 |
| abstract_inverted_index.concepts. | 22 |
| abstract_inverted_index.dataset's | 209 |
| abstract_inverted_index.datasets, | 192 |
| abstract_inverted_index.dedicated | 3 |
| abstract_inverted_index.designing | 153 |
| abstract_inverted_index.different | 132 |
| abstract_inverted_index.direction | 240 |
| abstract_inverted_index.emphasize | 215 |
| abstract_inverted_index.enhancing | 9, 224 |
| abstract_inverted_index.erroneous | 109 |
| abstract_inverted_index.generator | 157 |
| abstract_inverted_index.improving | 219 |
| abstract_inverted_index.introduce | 24 |
| abstract_inverted_index.involving | 19 |
| abstract_inverted_index.mechanism | 164 |
| abstract_inverted_index.primarily | 93 |
| abstract_inverted_index.promising | 239 |
| abstract_inverted_index.reasoning | 12, 28, 72, 91, 136, 227 |
| abstract_inverted_index.represent | 237 |
| abstract_inverted_index.step-wise | 161 |
| abstract_inverted_index.structure | 39, 148 |
| abstract_inverted_index.(-Bongard) | 182 |
| abstract_inverted_index.addressing | 5, 206 |
| abstract_inverted_index.algorithms | 87, 232 |
| abstract_inverted_index.attributed | 94 |
| abstract_inverted_index.conceptual | 110 |
| abstract_inverted_index.distorting | 117 |
| abstract_inverted_index.importance | 217 |
| abstract_inverted_index.inadequate | 97 |
| abstract_inverted_index.Progressive | 42 |
| abstract_inverted_index.algorithms, | 115 |
| abstract_inverted_index.approaches: | 129 |
| abstract_inverted_index.demonstrate | 172 |
| abstract_inverted_index.information | 111 |
| abstract_inverted_index.objectives. | 120 |
| abstract_inverted_index.performance | 179 |
| abstract_inverted_index.processing, | 203 |
| abstract_inverted_index.Bongard-Logo | 66, 191 |
| abstract_inverted_index.Experimental | 170 |
| abstract_inverted_index.Furthermore, | 55 |
| abstract_inverted_index.capabilities | 13, 228 |
| abstract_inverted_index.distribution | 210 |
| abstract_inverted_index.foundational | 200 |
| abstract_inverted_index.high-quality | 167 |
| abstract_inverted_index.particularly | 16, 204 |
| abstract_inverted_index.configuration | 103 |
| abstract_inverted_index.probabilistic | 47, 75 |
| abstract_inverted_index.significantly | 176 |
| abstract_inverted_index.representations. | 48, 76 |
| abstract_inverted_index.Lico-Net-Bongard, | 58 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile |