{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KP7FKE4OGXUY4SLWKYEN6KWLXD","short_pith_number":"pith:KP7FKE4O","schema_version":"1.0","canonical_sha256":"53fe55138e35e98e49765608df2acbb8c313c07c388e5b76bdcace9816d1bbb6","source":{"kind":"arxiv","id":"2104.02478","version":1},"attestation_state":"computed","paper":{"title":"Topological Regularization for Graph Neural Networks Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fausto Giunchiglia, Hao Xu, Ke Zhao, Rui Song","submitted_at":"2021-04-03T01:37:44Z","abstract_excerpt":"The complexity and non-Euclidean structure of graph data hinder the development of data augmentation methods similar to those in computer vision. In this paper, we propose a feature augmentation method for graph nodes based on topological regularization, in which topological structure information is introduced into end-to-end model. Specifically, we first obtain topology embedding of nodes through unsupervised representation learning method based on random walk. Then, the topological embedding as additional features and the original node features are input into a dual graph neural network for "},"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":"2104.02478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-03T01:37:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f11f56d886937e557ed4f3565d22f56e53e4de2c34e67a521cb32b306a4d773","abstract_canon_sha256":"a89e6fc6aa41547b0255254569e43f2f7af0fecebe90aa7f587de92c33f04bbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:48.793381Z","signature_b64":"Yaceo1iOyYC0vORO03fli9N1vBhdBEv2H7kJA2uegV+6eUNUOg52tRjDctVzX0NjwetenNeWnviS0uM5M/cKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53fe55138e35e98e49765608df2acbb8c313c07c388e5b76bdcace9816d1bbb6","last_reissued_at":"2026-07-05T02:29:48.792971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:48.792971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topological Regularization for Graph Neural Networks Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fausto Giunchiglia, Hao Xu, Ke Zhao, Rui Song","submitted_at":"2021-04-03T01:37:44Z","abstract_excerpt":"The complexity and non-Euclidean structure of graph data hinder the development of data augmentation methods similar to those in computer vision. In this paper, we propose a feature augmentation method for graph nodes based on topological regularization, in which topological structure information is introduced into end-to-end model. Specifically, we first obtain topology embedding of nodes through unsupervised representation learning method based on random walk. Then, the topological embedding as additional features and the original node features are input into a dual graph neural network for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02478","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/2104.02478/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":"2104.02478","created_at":"2026-07-05T02:29:48.793032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02478v1","created_at":"2026-07-05T02:29:48.793032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02478","created_at":"2026-07-05T02:29:48.793032+00:00"},{"alias_kind":"pith_short_12","alias_value":"KP7FKE4OGXUY","created_at":"2026-07-05T02:29:48.793032+00:00"},{"alias_kind":"pith_short_16","alias_value":"KP7FKE4OGXUY4SLW","created_at":"2026-07-05T02:29:48.793032+00:00"},{"alias_kind":"pith_short_8","alias_value":"KP7FKE4O","created_at":"2026-07-05T02:29:48.793032+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/KP7FKE4OGXUY4SLWKYEN6KWLXD","json":"https://pith.science/pith/KP7FKE4OGXUY4SLWKYEN6KWLXD.json","graph_json":"https://pith.science/api/pith-number/KP7FKE4OGXUY4SLWKYEN6KWLXD/graph.json","events_json":"https://pith.science/api/pith-number/KP7FKE4OGXUY4SLWKYEN6KWLXD/events.json","paper":"https://pith.science/paper/KP7FKE4O"},"agent_actions":{"view_html":"https://pith.science/pith/KP7FKE4OGXUY4SLWKYEN6KWLXD","download_json":"https://pith.science/pith/KP7FKE4OGXUY4SLWKYEN6KWLXD.json","view_paper":"https://pith.science/paper/KP7FKE4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02478&json=true","fetch_graph":"https://pith.science/api/pith-number/KP7FKE4OGXUY4SLWKYEN6KWLXD/graph.json","fetch_events":"https://pith.science/api/pith-number/KP7FKE4OGXUY4SLWKYEN6KWLXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KP7FKE4OGXUY4SLWKYEN6KWLXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KP7FKE4OGXUY4SLWKYEN6KWLXD/action/storage_attestation","attest_author":"https://pith.science/pith/KP7FKE4OGXUY4SLWKYEN6KWLXD/action/author_attestation","sign_citation":"https://pith.science/pith/KP7FKE4OGXUY4SLWKYEN6KWLXD/action/citation_signature","submit_replication":"https://pith.science/pith/KP7FKE4OGXUY4SLWKYEN6KWLXD/action/replication_record"}},"created_at":"2026-07-05T02:29:48.793032+00:00","updated_at":"2026-07-05T02:29:48.793032+00:00"}