{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JTIJP4OM6EVOPRXPKXKEWS2YH2","short_pith_number":"pith:JTIJP4OM","schema_version":"1.0","canonical_sha256":"4cd097f1ccf12ae7c6ef55d44b4b583e82d7f04094eafaa5612533a1b38130fc","source":{"kind":"arxiv","id":"2310.14166","version":1},"attestation_state":"computed","paper":{"title":"Ensemble Learning for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ling Yue, Quanming Yao, Zhen Hao Wong","submitted_at":"2023-10-22T03:55:13Z","abstract_excerpt":"Graph Neural Networks (GNNs) have shown success in various fields for learning from graph-structured data. This paper investigates the application of ensemble learning techniques to improve the performance and robustness of Graph Neural Networks (GNNs). By training multiple GNN models with diverse initializations or architectures, we create an ensemble model named ELGNN that captures various aspects of the data and uses the Tree-Structured Parzen Estimator algorithm to determine the ensemble weights. Combining the predictions of these models enhances overall accuracy, reduces bias and variance"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.14166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-22T03:55:13Z","cross_cats_sorted":[],"title_canon_sha256":"10a59276438cd99cc03f314eeac9a5bb8322f713560192bcf374343fdc906545","abstract_canon_sha256":"1aee9cdb521d9e668dbae976ed190e0abd1c12e2c912632922a837f840948122"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:40.604080Z","signature_b64":"Ye3fOyn8aNPJfr+P3hjHTimfeArFCkkSPAjurSnKTZSXIxhihtJvR8hzTO69zJp7gU3ubk5Rv1gT+pXC76qAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cd097f1ccf12ae7c6ef55d44b4b583e82d7f04094eafaa5612533a1b38130fc","last_reissued_at":"2026-07-05T07:03:40.603592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:40.603592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Learning for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ling Yue, Quanming Yao, Zhen Hao Wong","submitted_at":"2023-10-22T03:55:13Z","abstract_excerpt":"Graph Neural Networks (GNNs) have shown success in various fields for learning from graph-structured data. This paper investigates the application of ensemble learning techniques to improve the performance and robustness of Graph Neural Networks (GNNs). By training multiple GNN models with diverse initializations or architectures, we create an ensemble model named ELGNN that captures various aspects of the data and uses the Tree-Structured Parzen Estimator algorithm to determine the ensemble weights. Combining the predictions of these models enhances overall accuracy, reduces bias and variance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14166","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.14166/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.14166","created_at":"2026-07-05T07:03:40.603651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14166v1","created_at":"2026-07-05T07:03:40.603651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14166","created_at":"2026-07-05T07:03:40.603651+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTIJP4OM6EVO","created_at":"2026-07-05T07:03:40.603651+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTIJP4OM6EVOPRXP","created_at":"2026-07-05T07:03:40.603651+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTIJP4OM","created_at":"2026-07-05T07:03:40.603651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22593","citing_title":"Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2","json":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2.json","graph_json":"https://pith.science/api/pith-number/JTIJP4OM6EVOPRXPKXKEWS2YH2/graph.json","events_json":"https://pith.science/api/pith-number/JTIJP4OM6EVOPRXPKXKEWS2YH2/events.json","paper":"https://pith.science/paper/JTIJP4OM"},"agent_actions":{"view_html":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2","download_json":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2.json","view_paper":"https://pith.science/paper/JTIJP4OM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14166&json=true","fetch_graph":"https://pith.science/api/pith-number/JTIJP4OM6EVOPRXPKXKEWS2YH2/graph.json","fetch_events":"https://pith.science/api/pith-number/JTIJP4OM6EVOPRXPKXKEWS2YH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2/action/storage_attestation","attest_author":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2/action/author_attestation","sign_citation":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2/action/citation_signature","submit_replication":"https://pith.science/pith/JTIJP4OM6EVOPRXPKXKEWS2YH2/action/replication_record"}},"created_at":"2026-07-05T07:03:40.603651+00:00","updated_at":"2026-07-05T07:03:40.603651+00:00"}