SFP: Spurious Feature-Targeted Pruning for Out-of-Distribution Generalization Article Swipe
Yingchun Wang
,
Jingcai Guo
,
Song Guo
,
Yi Liu
,
Jie Zhang
,
Weizhan Zhang
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1145/3664647.3680969
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1145/3664647.3680969
Recent studies reveal that even highly biased dense networks can contain an invariant substructure with superior out-of-distribution (OOD) generalization. While existing works commonly seek these substructures using global sparsity constraints, the uniform imposition of sparse penalties across samples with diverse levels of spurious contents renders such methods suboptimal. The precise adaptation of model sparsity, specifically tailored for spurious features, remains a significant challenge. Motivated by the insight that in-distribution (ID) data containing spurious features may exhibit lower experiential risk, we propose a novel Spurious Feature-targeted Pruning framework, dubbed SFP, to induce the authentic invariant substructures without referring to the above concerns. Specifically, SFP distinguishes spurious features within ID instances during training by a theoretically validated threshold. It then penalizes the corresponding feature projections onto the model space, steering the optimization towards subspaces spanned by those invariant factors. Moreover, we also conduct detailed theoretical analysis to provide a rationality guarantee and a proof framework for OOD structures based on model sparsity. Experiments on various OOD datasets show that SFP can significantly outperform both structure-based and non-structure-based OOD generalization state-of-the-art (SOTA) methods by large margins.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3664647.3680969
- OA Status
- gold
- References
- 12
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403791969
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403791969Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3664647.3680969Digital Object Identifier
- Title
-
SFP: Spurious Feature-Targeted Pruning for Out-of-Distribution GeneralizationWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-10-26Full publication date if available
- Authors
-
Yingchun Wang, Jingcai Guo, Song Guo, Yi Liu, Jie Zhang, Weizhan ZhangList of authors in order
- Landing page
-
https://doi.org/10.1145/3664647.3680969Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1145/3664647.3680969Direct OA link when available
- Concepts
-
Spurious relationship, Generalization, Feature (linguistics), Pruning, Computer science, Artificial intelligence, Pattern recognition (psychology), Distribution (mathematics), Mathematics, Machine learning, Biology, Linguistics, Philosophy, Agronomy, Mathematical analysisTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
12Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403791969 |
|---|---|
| doi | https://doi.org/10.1145/3664647.3680969 |
| ids.doi | https://doi.org/10.1145/3664647.3680969 |
| ids.openalex | https://openalex.org/W4403791969 |
| fwci | 0.0 |
| type | article |
| title | SFP: Spurious Feature-Targeted Pruning for Out-of-Distribution Generalization |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 8420 |
| biblio.first_page | 8412 |
| topics[0].id | https://openalex.org/T10775 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9995999932289124 |
| 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 | Generative Adversarial Networks and Image Synthesis |
| topics[1].id | https://openalex.org/T10901 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9980000257492065 |
| 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 | Advanced Data Compression Techniques |
| topics[2].id | https://openalex.org/T11309 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9975000023841858 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1711 |
| topics[2].subfield.display_name | Signal Processing |
| topics[2].display_name | Music and Audio Processing |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C97256817 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8827972412109375 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1462316 |
| concepts[0].display_name | Spurious relationship |
| concepts[1].id | https://openalex.org/C177148314 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7648760080337524 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q170084 |
| concepts[1].display_name | Generalization |
| concepts[2].id | https://openalex.org/C2776401178 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7009315490722656 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[2].display_name | Feature (linguistics) |
| concepts[3].id | https://openalex.org/C108010975 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6951961517333984 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q500094 |
| concepts[3].display_name | Pruning |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.5960667133331299 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5330326557159424 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C153180895 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5207531452178955 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[6].display_name | Pattern recognition (psychology) |
| concepts[7].id | https://openalex.org/C110121322 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4285818338394165 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q865811 |
| concepts[7].display_name | Distribution (mathematics) |
| concepts[8].id | https://openalex.org/C33923547 |
| concepts[8].level | 0 |
| concepts[8].score | 0.28772836923599243 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[8].display_name | Mathematics |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.2614027261734009 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C86803240 |
| concepts[10].level | 0 |
| concepts[10].score | 0.04730919003486633 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[10].display_name | Biology |
| concepts[11].id | https://openalex.org/C41895202 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[11].display_name | Linguistics |
| concepts[12].id | https://openalex.org/C138885662 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[12].display_name | Philosophy |
| concepts[13].id | https://openalex.org/C6557445 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q173113 |
| concepts[13].display_name | Agronomy |
| concepts[14].id | https://openalex.org/C134306372 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[14].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/spurious-relationship |
| keywords[0].score | 0.8827972412109375 |
| keywords[0].display_name | Spurious relationship |
| keywords[1].id | https://openalex.org/keywords/generalization |
| keywords[1].score | 0.7648760080337524 |
| keywords[1].display_name | Generalization |
| keywords[2].id | https://openalex.org/keywords/feature |
| keywords[2].score | 0.7009315490722656 |
| keywords[2].display_name | Feature (linguistics) |
| keywords[3].id | https://openalex.org/keywords/pruning |
| keywords[3].score | 0.6951961517333984 |
| keywords[3].display_name | Pruning |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.5960667133331299 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.5330326557159424 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/pattern-recognition |
| keywords[6].score | 0.5207531452178955 |
| keywords[6].display_name | Pattern recognition (psychology) |
| keywords[7].id | https://openalex.org/keywords/distribution |
| keywords[7].score | 0.4285818338394165 |
| keywords[7].display_name | Distribution (mathematics) |
| keywords[8].id | https://openalex.org/keywords/mathematics |
| keywords[8].score | 0.28772836923599243 |
| keywords[8].display_name | Mathematics |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.2614027261734009 |
| keywords[9].display_name | Machine learning |
| keywords[10].id | https://openalex.org/keywords/biology |
| keywords[10].score | 0.04730919003486633 |
| keywords[10].display_name | Biology |
| language | en |
| locations[0].id | doi:10.1145/3664647.3680969 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-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 | Proceedings of the 32nd ACM International Conference on Multimedia |
| locations[0].landing_page_url | https://doi.org/10.1145/3664647.3680969 |
| locations[1].id | pmh:oai:repository.hkust.edu.hk:1783.1-146794 |
| locations[1].is_oa | False |
| locations[1].source | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | Conference paper |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://repository.hkust.edu.hk/ir/Record/1783.1-146794 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5107656468 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-0980-8738 |
| authorships[0].author.display_name | Yingchun Wang |
| authorships[0].countries | CN, HK |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I14243506, https://openalex.org/I87445476 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Computer Science and Technology & MOEKLINNS Lab, Xi'an Jiaotong University & Department of Computing, Hong Kong Polytechnic University, Xi'an, China |
| authorships[0].institutions[0].id | https://openalex.org/I87445476 |
| authorships[0].institutions[0].ror | https://ror.org/017zhmm22 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I87445476 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Xi'an Jiaotong University |
| authorships[0].institutions[1].id | https://openalex.org/I14243506 |
| authorships[0].institutions[1].ror | https://ror.org/0030zas98 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I14243506 |
| authorships[0].institutions[1].country_code | HK |
| authorships[0].institutions[1].display_name | Hong Kong Polytechnic University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yingchun Wang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Computer Science and Technology & MOEKLINNS Lab, Xi'an Jiaotong University & Department of Computing, Hong Kong Polytechnic University, Xi'an, China |
| authorships[1].author.id | https://openalex.org/A5038505509 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0449-4525 |
| authorships[1].author.display_name | Jingcai Guo |
| authorships[1].countries | HK |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I14243506 |
| authorships[1].affiliations[0].raw_affiliation_string | Department of Computing, Hong Kong Polytechnic University, Hong Kong, China |
| authorships[1].institutions[0].id | https://openalex.org/I14243506 |
| authorships[1].institutions[0].ror | https://ror.org/0030zas98 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I14243506 |
| authorships[1].institutions[0].country_code | HK |
| authorships[1].institutions[0].display_name | Hong Kong Polytechnic University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jingcai Guo |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Department of Computing, Hong Kong Polytechnic University, Hong Kong, China |
| authorships[2].author.id | https://openalex.org/A5043464306 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-9831-2202 |
| authorships[2].author.display_name | Song Guo |
| authorships[2].countries | HK |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I200769079, https://openalex.org/I889458895 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of CSE, Hong Kong University of Science and Technology, Hong Kong, China |
| authorships[2].institutions[0].id | https://openalex.org/I200769079 |
| authorships[2].institutions[0].ror | https://ror.org/00q4vv597 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I200769079 |
| authorships[2].institutions[0].country_code | HK |
| authorships[2].institutions[0].display_name | Hong Kong University of Science and Technology |
| authorships[2].institutions[1].id | https://openalex.org/I889458895 |
| authorships[2].institutions[1].ror | https://ror.org/02zhqgq86 |
| authorships[2].institutions[1].type | education |
| authorships[2].institutions[1].lineage | https://openalex.org/I889458895 |
| authorships[2].institutions[1].country_code | HK |
| authorships[2].institutions[1].display_name | University of Hong Kong |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Song Guo |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Department of CSE, Hong Kong University of Science and Technology, Hong Kong, China |
| authorships[3].author.id | https://openalex.org/A5000371319 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-9280-1136 |
| authorships[3].author.display_name | Yi Liu |
| authorships[3].countries | HK |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I14243506 |
| authorships[3].affiliations[0].raw_affiliation_string | Department of Computing, Hong Kong Polytechnic University, Hong Kong, China |
| authorships[3].institutions[0].id | https://openalex.org/I14243506 |
| authorships[3].institutions[0].ror | https://ror.org/0030zas98 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I14243506 |
| authorships[3].institutions[0].country_code | HK |
| authorships[3].institutions[0].display_name | Hong Kong Polytechnic University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yi Liu |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Department of Computing, Hong Kong Polytechnic University, Hong Kong, China |
| authorships[4].author.id | https://openalex.org/A5007296623 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-8073-2118 |
| authorships[4].author.display_name | Jie Zhang |
| authorships[4].countries | HK |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I14243506 |
| authorships[4].affiliations[0].raw_affiliation_string | Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China |
| authorships[4].institutions[0].id | https://openalex.org/I14243506 |
| authorships[4].institutions[0].ror | https://ror.org/0030zas98 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I14243506 |
| authorships[4].institutions[0].country_code | HK |
| authorships[4].institutions[0].display_name | Hong Kong Polytechnic University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Jie Zhang |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China |
| authorships[5].author.id | https://openalex.org/A5028268587 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-0330-5435 |
| authorships[5].author.display_name | Weizhan Zhang |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I87445476 |
| authorships[5].affiliations[0].raw_affiliation_string | School of Computer Science and Technology & BDKE Lab, Xi'an Jiaotong University, Xi'an, China |
| authorships[5].institutions[0].id | https://openalex.org/I87445476 |
| authorships[5].institutions[0].ror | https://ror.org/017zhmm22 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I87445476 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | Xi'an Jiaotong University |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Weizhan Zhang |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | School of Computer Science and Technology & BDKE Lab, Xi'an Jiaotong University, Xi'an, China |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1145/3664647.3680969 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | SFP: Spurious Feature-Targeted Pruning for Out-of-Distribution Generalization |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10775 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9995999932289124 |
| 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 | Generative Adversarial Networks and Image Synthesis |
| related_works | https://openalex.org/W3113091479, https://openalex.org/W2162899405, https://openalex.org/W941090075, https://openalex.org/W2044987316, https://openalex.org/W3134374554, https://openalex.org/W2237480245, https://openalex.org/W2075065631, https://openalex.org/W2519167559, https://openalex.org/W4311248832, https://openalex.org/W4386113923 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1145/3664647.3680969 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-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 | Proceedings of the 32nd ACM International Conference on Multimedia |
| best_oa_location.landing_page_url | https://doi.org/10.1145/3664647.3680969 |
| primary_location.id | doi:10.1145/3664647.3680969 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-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 | Proceedings of the 32nd ACM International Conference on Multimedia |
| primary_location.landing_page_url | https://doi.org/10.1145/3664647.3680969 |
| publication_date | 2024-10-26 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W2768783441, https://openalex.org/W4385764314, https://openalex.org/W4387250121, https://openalex.org/W2808168148, https://openalex.org/W3191808899, https://openalex.org/W2894728917, https://openalex.org/W1834627138, https://openalex.org/W2149298154, https://openalex.org/W4312776478, https://openalex.org/W4312106989, https://openalex.org/W2747329762, https://openalex.org/W2964266063 |
| referenced_works_count | 12 |
| abstract_inverted_index.a | 60, 81, 112, 146, 150 |
| abstract_inverted_index.ID | 107 |
| abstract_inverted_index.It | 116 |
| abstract_inverted_index.an | 11 |
| abstract_inverted_index.by | 64, 111, 133, 180 |
| abstract_inverted_index.of | 33, 41, 51 |
| abstract_inverted_index.on | 157, 161 |
| abstract_inverted_index.to | 89, 97, 144 |
| abstract_inverted_index.we | 79, 138 |
| abstract_inverted_index.OOD | 154, 163, 175 |
| abstract_inverted_index.SFP | 102, 167 |
| abstract_inverted_index.The | 48 |
| abstract_inverted_index.and | 149, 173 |
| abstract_inverted_index.can | 9, 168 |
| abstract_inverted_index.for | 56, 153 |
| abstract_inverted_index.may | 74 |
| abstract_inverted_index.the | 30, 65, 91, 98, 119, 124, 128 |
| abstract_inverted_index.(ID) | 69 |
| abstract_inverted_index.SFP, | 88 |
| abstract_inverted_index.also | 139 |
| abstract_inverted_index.both | 171 |
| abstract_inverted_index.data | 70 |
| abstract_inverted_index.even | 4 |
| abstract_inverted_index.onto | 123 |
| abstract_inverted_index.seek | 23 |
| abstract_inverted_index.show | 165 |
| abstract_inverted_index.such | 45 |
| abstract_inverted_index.that | 3, 67, 166 |
| abstract_inverted_index.then | 117 |
| abstract_inverted_index.with | 14, 38 |
| abstract_inverted_index.(OOD) | 17 |
| abstract_inverted_index.While | 19 |
| abstract_inverted_index.above | 99 |
| abstract_inverted_index.based | 156 |
| abstract_inverted_index.dense | 7 |
| abstract_inverted_index.large | 181 |
| abstract_inverted_index.lower | 76 |
| abstract_inverted_index.model | 52, 125, 158 |
| abstract_inverted_index.novel | 82 |
| abstract_inverted_index.proof | 151 |
| abstract_inverted_index.risk, | 78 |
| abstract_inverted_index.these | 24 |
| abstract_inverted_index.those | 134 |
| abstract_inverted_index.using | 26 |
| abstract_inverted_index.works | 21 |
| abstract_inverted_index.(SOTA) | 178 |
| abstract_inverted_index.Recent | 0 |
| abstract_inverted_index.across | 36 |
| abstract_inverted_index.biased | 6 |
| abstract_inverted_index.dubbed | 87 |
| abstract_inverted_index.during | 109 |
| abstract_inverted_index.global | 27 |
| abstract_inverted_index.highly | 5 |
| abstract_inverted_index.induce | 90 |
| abstract_inverted_index.levels | 40 |
| abstract_inverted_index.reveal | 2 |
| abstract_inverted_index.space, | 126 |
| abstract_inverted_index.sparse | 34 |
| abstract_inverted_index.within | 106 |
| abstract_inverted_index.Pruning | 85 |
| abstract_inverted_index.conduct | 140 |
| abstract_inverted_index.contain | 10 |
| abstract_inverted_index.diverse | 39 |
| abstract_inverted_index.exhibit | 75 |
| abstract_inverted_index.feature | 121 |
| abstract_inverted_index.insight | 66 |
| abstract_inverted_index.methods | 46, 179 |
| abstract_inverted_index.precise | 49 |
| abstract_inverted_index.propose | 80 |
| abstract_inverted_index.provide | 145 |
| abstract_inverted_index.remains | 59 |
| abstract_inverted_index.renders | 44 |
| abstract_inverted_index.samples | 37 |
| abstract_inverted_index.spanned | 132 |
| abstract_inverted_index.studies | 1 |
| abstract_inverted_index.towards | 130 |
| abstract_inverted_index.uniform | 31 |
| abstract_inverted_index.various | 162 |
| abstract_inverted_index.without | 95 |
| abstract_inverted_index.Spurious | 83 |
| abstract_inverted_index.analysis | 143 |
| abstract_inverted_index.commonly | 22 |
| abstract_inverted_index.contents | 43 |
| abstract_inverted_index.datasets | 164 |
| abstract_inverted_index.detailed | 141 |
| abstract_inverted_index.existing | 20 |
| abstract_inverted_index.factors. | 136 |
| abstract_inverted_index.features | 73, 105 |
| abstract_inverted_index.margins. | 182 |
| abstract_inverted_index.networks | 8 |
| abstract_inverted_index.sparsity | 28 |
| abstract_inverted_index.spurious | 42, 57, 72, 104 |
| abstract_inverted_index.steering | 127 |
| abstract_inverted_index.superior | 15 |
| abstract_inverted_index.tailored | 55 |
| abstract_inverted_index.training | 110 |
| abstract_inverted_index.Moreover, | 137 |
| abstract_inverted_index.Motivated | 63 |
| abstract_inverted_index.authentic | 92 |
| abstract_inverted_index.concerns. | 100 |
| abstract_inverted_index.features, | 58 |
| abstract_inverted_index.framework | 152 |
| abstract_inverted_index.guarantee | 148 |
| abstract_inverted_index.instances | 108 |
| abstract_inverted_index.invariant | 12, 93, 135 |
| abstract_inverted_index.penalizes | 118 |
| abstract_inverted_index.penalties | 35 |
| abstract_inverted_index.referring | 96 |
| abstract_inverted_index.sparsity, | 53 |
| abstract_inverted_index.sparsity. | 159 |
| abstract_inverted_index.subspaces | 131 |
| abstract_inverted_index.validated | 114 |
| abstract_inverted_index.adaptation | 50 |
| abstract_inverted_index.challenge. | 62 |
| abstract_inverted_index.containing | 71 |
| abstract_inverted_index.framework, | 86 |
| abstract_inverted_index.imposition | 32 |
| abstract_inverted_index.outperform | 170 |
| abstract_inverted_index.structures | 155 |
| abstract_inverted_index.threshold. | 115 |
| abstract_inverted_index.Experiments | 160 |
| abstract_inverted_index.projections | 122 |
| abstract_inverted_index.rationality | 147 |
| abstract_inverted_index.significant | 61 |
| abstract_inverted_index.suboptimal. | 47 |
| abstract_inverted_index.theoretical | 142 |
| abstract_inverted_index.constraints, | 29 |
| abstract_inverted_index.experiential | 77 |
| abstract_inverted_index.optimization | 129 |
| abstract_inverted_index.specifically | 54 |
| abstract_inverted_index.substructure | 13 |
| abstract_inverted_index.Specifically, | 101 |
| abstract_inverted_index.corresponding | 120 |
| abstract_inverted_index.distinguishes | 103 |
| abstract_inverted_index.significantly | 169 |
| abstract_inverted_index.substructures | 25, 94 |
| abstract_inverted_index.theoretically | 113 |
| abstract_inverted_index.generalization | 176 |
| abstract_inverted_index.generalization. | 18 |
| abstract_inverted_index.in-distribution | 68 |
| abstract_inverted_index.structure-based | 172 |
| abstract_inverted_index.Feature-targeted | 84 |
| abstract_inverted_index.state-of-the-art | 177 |
| abstract_inverted_index.non-structure-based | 174 |
| abstract_inverted_index.out-of-distribution | 16 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile.value | 0.23741474 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |