Examining graph neural networks for crystal structures: limitations and opportunities for capturing periodicity Article Swipe
Sheng Gong
,
Tian Xie
,
Yang Shao‐Horn
,
Rafael Gómez‐Bombarelli
,
Jeffrey C. Grossman
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2208.05039
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2208.05039
Historically, materials informatics has relied on human-designed descriptors of materials structures. In recent years, graph neural networks (GNNs) have been proposed for learning representations of crystal structures from data end-to-end producing vectorial embeddings that are optimized for downstream prediction tasks. However, a systematic scheme is lacking to analyze and understand the limits of GNNs for capturing crystal structures. In this work, we propose to use human-designed descriptors as a bank of human knowledge to test whether black-box GNNs can capture the knowledge of crystal structures. We find that current state-of-the-art GNNs cannot capture the periodicity of crystal structures well, and we analyze the limitations of the GNN models that result in this failure from three aspects: local expressive power, long-range information, and readout function. We propose an initial solution, hybridizing descriptors with GNNs, to improve the prediction of GNNs for materials properties, especially phonon internal energy and heat capacity with 90% lower errors, and we analyze the mechanisms for the improved prediction. All the analysis can be extended easily to other deep representation learning models, human-designed descriptors, and systems such as molecules and amorphous materials.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2208.05039
- https://arxiv.org/pdf/2208.05039
- OA Status
- green
- Cited By
- 2
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4290860383
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4290860383Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2208.05039Digital Object Identifier
- Title
-
Examining graph neural networks for crystal structures: limitations and opportunities for capturing periodicityWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-08-09Full publication date if available
- Authors
-
Sheng Gong, Tian Xie, Yang Shao‐Horn, Rafael Gómez‐Bombarelli, Jeffrey C. GrossmanList of authors in order
- Landing page
-
https://arxiv.org/abs/2208.05039Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2208.05039Direct 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/2208.05039Direct OA link when available
- Concepts
-
Computer science, Representation (politics), Graph, Artificial intelligence, Artificial neural network, Machine learning, Theoretical computer science, Political science, Law, PoliticsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2023: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4290860383 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2208.05039 |
| ids.doi | https://doi.org/10.48550/arxiv.2208.05039 |
| ids.openalex | https://openalex.org/W4290860383 |
| fwci | |
| type | preprint |
| title | Examining graph neural networks for crystal structures: limitations and opportunities for capturing periodicity |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11948 |
| topics[0].field.id | https://openalex.org/fields/25 |
| topics[0].field.display_name | Materials Science |
| topics[0].score | 1.0 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2505 |
| topics[0].subfield.display_name | Materials Chemistry |
| topics[0].display_name | Machine Learning in Materials Science |
| topics[1].id | https://openalex.org/T10211 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.987500011920929 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1703 |
| topics[1].subfield.display_name | Computational Theory and Mathematics |
| topics[1].display_name | Computational Drug Discovery Methods |
| topics[2].id | https://openalex.org/T11273 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9782999753952026 |
| 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 | Advanced Graph Neural Networks |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6897290349006653 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2776359362 |
| concepts[1].level | 3 |
| concepts[1].score | 0.5584977269172668 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[1].display_name | Representation (politics) |
| concepts[2].id | https://openalex.org/C132525143 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5206262469291687 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[2].display_name | Graph |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.4948839545249939 |
| 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 | 0.45722001791000366 |
| 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 | 0.4498613476753235 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C80444323 |
| concepts[6].level | 1 |
| concepts[6].score | 0.400213360786438 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[6].display_name | Theoretical computer science |
| concepts[7].id | https://openalex.org/C17744445 |
| concepts[7].level | 0 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[7].display_name | Political science |
| concepts[8].id | https://openalex.org/C199539241 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[8].display_name | Law |
| concepts[9].id | https://openalex.org/C94625758 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[9].display_name | Politics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6897290349006653 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/representation |
| keywords[1].score | 0.5584977269172668 |
| keywords[1].display_name | Representation (politics) |
| keywords[2].id | https://openalex.org/keywords/graph |
| keywords[2].score | 0.5206262469291687 |
| keywords[2].display_name | Graph |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.4948839545249939 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[4].score | 0.45722001791000366 |
| keywords[4].display_name | Artificial neural network |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.4498613476753235 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[6].score | 0.400213360786438 |
| keywords[6].display_name | Theoretical computer science |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2208.05039 |
| 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/2208.05039 |
| 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/2208.05039 |
| locations[1].id | pmh:oai:zenodo.org:8403882 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400562 |
| 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 | Zenodo (CERN European Organization for Nuclear Research) |
| locations[1].source.host_organization | https://openalex.org/I67311998 |
| locations[1].source.host_organization_name | European Organization for Nuclear Research |
| locations[1].source.host_organization_lineage | https://openalex.org/I67311998 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | info:eu-repo/semantics/article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://zenodo.org/record/8403882 |
| locations[2].id | doi:10.48550/arxiv.2208.05039 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | article |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://doi.org/10.48550/arxiv.2208.05039 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100570052 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Sheng Gong |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Gong, Sheng |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101773689 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2916-6250 |
| authorships[1].author.display_name | Tian Xie |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xie, Tian |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100601237 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-8714-2121 |
| authorships[2].author.display_name | Yang Shao‐Horn |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Shao-Horn, Yang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5018079613 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-9495-8599 |
| authorships[3].author.display_name | Rafael Gómez‐Bombarelli |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Gomez-Bombarelli, Rafael |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5083309623 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Jeffrey C. Grossman |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Grossman, Jeffrey C. |
| authorships[4].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/2208.05039 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Examining graph neural networks for crystal structures: limitations and opportunities for capturing periodicity |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11948 |
| primary_topic.field.id | https://openalex.org/fields/25 |
| primary_topic.field.display_name | Materials Science |
| primary_topic.score | 1.0 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2505 |
| primary_topic.subfield.display_name | Materials Chemistry |
| primary_topic.display_name | Machine Learning in Materials Science |
| related_works | https://openalex.org/W2062195135, https://openalex.org/W2795079307, https://openalex.org/W2961085424, https://openalex.org/W2391251536, https://openalex.org/W2793058541, https://openalex.org/W2362198218, https://openalex.org/W1983629434, https://openalex.org/W1982750869, https://openalex.org/W2019521278, https://openalex.org/W1984922432 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:arXiv.org:2208.05039 |
| 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/2208.05039 |
| 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/2208.05039 |
| primary_location.id | pmh:oai:arXiv.org:2208.05039 |
| 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/2208.05039 |
| 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/2208.05039 |
| publication_date | 2022-08-09 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 41, 68 |
| abstract_inverted_index.In | 11, 58 |
| abstract_inverted_index.We | 85, 124 |
| abstract_inverted_index.an | 126 |
| abstract_inverted_index.as | 67, 180 |
| abstract_inverted_index.be | 166 |
| abstract_inverted_index.in | 110 |
| abstract_inverted_index.is | 44 |
| abstract_inverted_index.of | 8, 24, 52, 70, 82, 95, 104, 137 |
| abstract_inverted_index.on | 5 |
| abstract_inverted_index.to | 46, 63, 73, 133, 169 |
| abstract_inverted_index.we | 61, 100, 154 |
| abstract_inverted_index.90% | 150 |
| abstract_inverted_index.All | 162 |
| abstract_inverted_index.GNN | 106 |
| abstract_inverted_index.and | 48, 99, 121, 146, 153, 177, 182 |
| abstract_inverted_index.are | 34 |
| abstract_inverted_index.can | 78, 165 |
| abstract_inverted_index.for | 21, 36, 54, 139, 158 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.the | 50, 80, 93, 102, 105, 135, 156, 159, 163 |
| abstract_inverted_index.use | 64 |
| abstract_inverted_index.GNNs | 53, 77, 90, 138 |
| abstract_inverted_index.bank | 69 |
| abstract_inverted_index.been | 19 |
| abstract_inverted_index.data | 28 |
| abstract_inverted_index.deep | 171 |
| abstract_inverted_index.find | 86 |
| abstract_inverted_index.from | 27, 113 |
| abstract_inverted_index.have | 18 |
| abstract_inverted_index.heat | 147 |
| abstract_inverted_index.such | 179 |
| abstract_inverted_index.test | 74 |
| abstract_inverted_index.that | 33, 87, 108 |
| abstract_inverted_index.this | 59, 111 |
| abstract_inverted_index.with | 131, 149 |
| abstract_inverted_index.GNNs, | 132 |
| abstract_inverted_index.graph | 14 |
| abstract_inverted_index.human | 71 |
| abstract_inverted_index.local | 116 |
| abstract_inverted_index.lower | 151 |
| abstract_inverted_index.other | 170 |
| abstract_inverted_index.three | 114 |
| abstract_inverted_index.well, | 98 |
| abstract_inverted_index.work, | 60 |
| abstract_inverted_index.(GNNs) | 17 |
| abstract_inverted_index.cannot | 91 |
| abstract_inverted_index.easily | 168 |
| abstract_inverted_index.energy | 145 |
| abstract_inverted_index.limits | 51 |
| abstract_inverted_index.models | 107 |
| abstract_inverted_index.neural | 15 |
| abstract_inverted_index.phonon | 143 |
| abstract_inverted_index.power, | 118 |
| abstract_inverted_index.recent | 12 |
| abstract_inverted_index.relied | 4 |
| abstract_inverted_index.result | 109 |
| abstract_inverted_index.scheme | 43 |
| abstract_inverted_index.tasks. | 39 |
| abstract_inverted_index.years, | 13 |
| abstract_inverted_index.analyze | 47, 101, 155 |
| abstract_inverted_index.capture | 79, 92 |
| abstract_inverted_index.crystal | 25, 56, 83, 96 |
| abstract_inverted_index.current | 88 |
| abstract_inverted_index.errors, | 152 |
| abstract_inverted_index.failure | 112 |
| abstract_inverted_index.improve | 134 |
| abstract_inverted_index.initial | 127 |
| abstract_inverted_index.lacking | 45 |
| abstract_inverted_index.models, | 174 |
| abstract_inverted_index.propose | 62, 125 |
| abstract_inverted_index.readout | 122 |
| abstract_inverted_index.systems | 178 |
| abstract_inverted_index.whether | 75 |
| abstract_inverted_index.However, | 40 |
| abstract_inverted_index.analysis | 164 |
| abstract_inverted_index.aspects: | 115 |
| abstract_inverted_index.capacity | 148 |
| abstract_inverted_index.extended | 167 |
| abstract_inverted_index.improved | 160 |
| abstract_inverted_index.internal | 144 |
| abstract_inverted_index.learning | 22, 173 |
| abstract_inverted_index.networks | 16 |
| abstract_inverted_index.proposed | 20 |
| abstract_inverted_index.amorphous | 183 |
| abstract_inverted_index.black-box | 76 |
| abstract_inverted_index.capturing | 55 |
| abstract_inverted_index.function. | 123 |
| abstract_inverted_index.knowledge | 72, 81 |
| abstract_inverted_index.materials | 1, 9, 140 |
| abstract_inverted_index.molecules | 181 |
| abstract_inverted_index.optimized | 35 |
| abstract_inverted_index.producing | 30 |
| abstract_inverted_index.solution, | 128 |
| abstract_inverted_index.vectorial | 31 |
| abstract_inverted_index.downstream | 37 |
| abstract_inverted_index.embeddings | 32 |
| abstract_inverted_index.end-to-end | 29 |
| abstract_inverted_index.especially | 142 |
| abstract_inverted_index.expressive | 117 |
| abstract_inverted_index.long-range | 119 |
| abstract_inverted_index.materials. | 184 |
| abstract_inverted_index.mechanisms | 157 |
| abstract_inverted_index.prediction | 38, 136 |
| abstract_inverted_index.structures | 26, 97 |
| abstract_inverted_index.systematic | 42 |
| abstract_inverted_index.understand | 49 |
| abstract_inverted_index.descriptors | 7, 66, 130 |
| abstract_inverted_index.hybridizing | 129 |
| abstract_inverted_index.informatics | 2 |
| abstract_inverted_index.limitations | 103 |
| abstract_inverted_index.periodicity | 94 |
| abstract_inverted_index.prediction. | 161 |
| abstract_inverted_index.properties, | 141 |
| abstract_inverted_index.structures. | 10, 57, 84 |
| abstract_inverted_index.descriptors, | 176 |
| abstract_inverted_index.information, | 120 |
| abstract_inverted_index.Historically, | 0 |
| abstract_inverted_index.human-designed | 6, 65, 175 |
| abstract_inverted_index.representation | 172 |
| abstract_inverted_index.representations | 23 |
| abstract_inverted_index.state-of-the-art | 89 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/7 |
| sustainable_development_goals[0].score | 0.44999998807907104 |
| sustainable_development_goals[0].display_name | Affordable and clean energy |
| citation_normalized_percentile |