{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6BVATLYWGXCSMRJMWPVAZNMNSJ","short_pith_number":"pith:6BVATLYW","schema_version":"1.0","canonical_sha256":"f06a09af1635c526452cb3ea0cb58d927b84622f1381352b4283577db8dc40ad","source":{"kind":"arxiv","id":"2109.03856","version":4},"attestation_state":"computed","paper":{"title":"Local Augmentation for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dinghao Wu, HanZe Dong, Junzhou Huang, Lanqing Li, Peilin Zhao, Rex Ying, Songtao Liu, Tingyang Xu, Yu Rong","submitted_at":"2021-09-08T18:10:08Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved remarkable performance on graph-based tasks. The key idea for GNNs is to obtain informative representation through aggregating information from local neighborhoods. However, it remains an open question whether the neighborhood information is adequately aggregated for learning representations of nodes with few neighbors. To address this, we propose a simple and efficient data augmentation strategy, local augmentation, to learn the distribution of the node features of the neighbors conditioned on the central node's feature and enhance GNN's expressive p"},"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":"2109.03856","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-08T18:10:08Z","cross_cats_sorted":[],"title_canon_sha256":"f88e6332a00f4a79a997c3fedffc3b419198295f3c055defeaa6ec1bb7f82f84","abstract_canon_sha256":"875a394be5bbbd226a92d78f9631adc176d9635c78307d50bb2f72b6617dab2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:09.173469Z","signature_b64":"slazLIwE467XSxaCiXhEnRhxnR14lRZbQ4v5ptNpdM3GFGotbax6/618TNAxo+GXroMe5VP35D/At0+SjdAYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f06a09af1635c526452cb3ea0cb58d927b84622f1381352b4283577db8dc40ad","last_reissued_at":"2026-07-05T04:35:09.173049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:09.173049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Augmentation for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dinghao Wu, HanZe Dong, Junzhou Huang, Lanqing Li, Peilin Zhao, Rex Ying, Songtao Liu, Tingyang Xu, Yu Rong","submitted_at":"2021-09-08T18:10:08Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved remarkable performance on graph-based tasks. The key idea for GNNs is to obtain informative representation through aggregating information from local neighborhoods. However, it remains an open question whether the neighborhood information is adequately aggregated for learning representations of nodes with few neighbors. To address this, we propose a simple and efficient data augmentation strategy, local augmentation, to learn the distribution of the node features of the neighbors conditioned on the central node's feature and enhance GNN's expressive p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03856","kind":"arxiv","version":4},"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/2109.03856/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":"2109.03856","created_at":"2026-07-05T04:35:09.173106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.03856v4","created_at":"2026-07-05T04:35:09.173106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03856","created_at":"2026-07-05T04:35:09.173106+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BVATLYWGXCS","created_at":"2026-07-05T04:35:09.173106+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BVATLYWGXCSMRJM","created_at":"2026-07-05T04:35:09.173106+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BVATLYW","created_at":"2026-07-05T04:35:09.173106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ","json":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ.json","graph_json":"https://pith.science/api/pith-number/6BVATLYWGXCSMRJMWPVAZNMNSJ/graph.json","events_json":"https://pith.science/api/pith-number/6BVATLYWGXCSMRJMWPVAZNMNSJ/events.json","paper":"https://pith.science/paper/6BVATLYW"},"agent_actions":{"view_html":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ","download_json":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ.json","view_paper":"https://pith.science/paper/6BVATLYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.03856&json=true","fetch_graph":"https://pith.science/api/pith-number/6BVATLYWGXCSMRJMWPVAZNMNSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6BVATLYWGXCSMRJMWPVAZNMNSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ/action/storage_attestation","attest_author":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ/action/author_attestation","sign_citation":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ/action/citation_signature","submit_replication":"https://pith.science/pith/6BVATLYWGXCSMRJMWPVAZNMNSJ/action/replication_record"}},"created_at":"2026-07-05T04:35:09.173106+00:00","updated_at":"2026-07-05T04:35:09.173106+00:00"}