{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JF6KZLSF2FCG24C3OMMGYBCZJU","short_pith_number":"pith:JF6KZLSF","schema_version":"1.0","canonical_sha256":"497cacae45d1446d705b73186c04594d272e20d0fe45997074f0b884f1652a90","source":{"kind":"arxiv","id":"2011.07057","version":1},"attestation_state":"computed","paper":{"title":"Learning to Drop: Robust Graph Neural Network via Topological Denoising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Zong, Dongsheng Luo, Haifeng Chen, Jingchao Ni, Wei Cheng, Wenchao Yu, Xiang Zhang","submitted_at":"2020-11-13T18:53:21Z","abstract_excerpt":"Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along edges of the given graph. Despite their success, however, the existing GNNs are usually sensitive to the quality of the input graph. Real-world graphs are often noisy and contain task-irrelevant edges, which may lead to suboptimal generalization performance in the learned GNN models. In this paper, we propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of GNNs by learning to"},"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":"2011.07057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T18:53:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e56ae96b5ef7c8d92525b62edeefc9b6b9f0f3960233ddb2a50bca11cd30f2b2","abstract_canon_sha256":"cbc5f50460ef7b9bb13a7aa42809cd4a823bc3e7f52d0cbe631cef0c4d7ee2b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:27.256705Z","signature_b64":"RnwAIInm2F3TI6SZQMXMHaTQDHwEKUIzeGsiHv49TtAEdj76kH+2VY7oU6fuOBlywa4QC0lfh1aL42Ni63tABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"497cacae45d1446d705b73186c04594d272e20d0fe45997074f0b884f1652a90","last_reissued_at":"2026-07-05T01:51:27.256355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:27.256355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Drop: Robust Graph Neural Network via Topological Denoising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Zong, Dongsheng Luo, Haifeng Chen, Jingchao Ni, Wei Cheng, Wenchao Yu, Xiang Zhang","submitted_at":"2020-11-13T18:53:21Z","abstract_excerpt":"Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along edges of the given graph. Despite their success, however, the existing GNNs are usually sensitive to the quality of the input graph. Real-world graphs are often noisy and contain task-irrelevant edges, which may lead to suboptimal generalization performance in the learned GNN models. In this paper, we propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of GNNs by learning to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07057","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/2011.07057/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":"2011.07057","created_at":"2026-07-05T01:51:27.256419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.07057v1","created_at":"2026-07-05T01:51:27.256419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07057","created_at":"2026-07-05T01:51:27.256419+00:00"},{"alias_kind":"pith_short_12","alias_value":"JF6KZLSF2FCG","created_at":"2026-07-05T01:51:27.256419+00:00"},{"alias_kind":"pith_short_16","alias_value":"JF6KZLSF2FCG24C3","created_at":"2026-07-05T01:51:27.256419+00:00"},{"alias_kind":"pith_short_8","alias_value":"JF6KZLSF","created_at":"2026-07-05T01:51:27.256419+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/JF6KZLSF2FCG24C3OMMGYBCZJU","json":"https://pith.science/pith/JF6KZLSF2FCG24C3OMMGYBCZJU.json","graph_json":"https://pith.science/api/pith-number/JF6KZLSF2FCG24C3OMMGYBCZJU/graph.json","events_json":"https://pith.science/api/pith-number/JF6KZLSF2FCG24C3OMMGYBCZJU/events.json","paper":"https://pith.science/paper/JF6KZLSF"},"agent_actions":{"view_html":"https://pith.science/pith/JF6KZLSF2FCG24C3OMMGYBCZJU","download_json":"https://pith.science/pith/JF6KZLSF2FCG24C3OMMGYBCZJU.json","view_paper":"https://pith.science/paper/JF6KZLSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.07057&json=true","fetch_graph":"https://pith.science/api/pith-number/JF6KZLSF2FCG24C3OMMGYBCZJU/graph.json","fetch_events":"https://pith.science/api/pith-number/JF6KZLSF2FCG24C3OMMGYBCZJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JF6KZLSF2FCG24C3OMMGYBCZJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JF6KZLSF2FCG24C3OMMGYBCZJU/action/storage_attestation","attest_author":"https://pith.science/pith/JF6KZLSF2FCG24C3OMMGYBCZJU/action/author_attestation","sign_citation":"https://pith.science/pith/JF6KZLSF2FCG24C3OMMGYBCZJU/action/citation_signature","submit_replication":"https://pith.science/pith/JF6KZLSF2FCG24C3OMMGYBCZJU/action/replication_record"}},"created_at":"2026-07-05T01:51:27.256419+00:00","updated_at":"2026-07-05T01:51:27.256419+00:00"}