{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PQ37OEZX2VM64S4GCUDRT37TPS","short_pith_number":"pith:PQ37OEZX","schema_version":"1.0","canonical_sha256":"7c37f71337d559ee4b86150719eff37ca764bc96d23994a74a2d050055224728","source":{"kind":"arxiv","id":"2303.11081","version":2},"attestation_state":"computed","paper":{"title":"Provably Convergent Subgraph-wise Sampling for Fast GNN Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Li, Defu Lian, Enhong Chen, Feng Wu, Jie Wang, Shuiwang Ji, Xize Liang, Zhihao Shi","submitted_at":"2023-03-17T05:16:49Z","abstract_excerpt":"Subgraph-wise sampling -- a promising class of mini-batch training techniques for graph neural networks (GNNs -- is critical for real-world applications. During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i.e., the exponentially increasing dependencies of nodes with the number of MP iterations. However, discarding messages may sacrifice the gradient estimation accuracy, posing significant challenges to their convergence analysis and convergence speeds. To addres"},"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":"2303.11081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-17T05:16:49Z","cross_cats_sorted":[],"title_canon_sha256":"632b761299ef088a682c44efa8735a3d98aebcf249ed9f28d22f7ae1f1592a59","abstract_canon_sha256":"1410c119970ea8dcff5b900a44f0386575056b7cf20720c1c0de27fe5992ac42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:32.974033Z","signature_b64":"BGqZjjTs/D8ZF2z8p7ceAEBBSP425T7KU9P0zebYqOJWh2vfMUGIcxzDiU3/i08RwKls7F7zFylfUOOQYlhNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c37f71337d559ee4b86150719eff37ca764bc96d23994a74a2d050055224728","last_reissued_at":"2026-07-05T08:57:32.973586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:32.973586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Convergent Subgraph-wise Sampling for Fast GNN Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Li, Defu Lian, Enhong Chen, Feng Wu, Jie Wang, Shuiwang Ji, Xize Liang, Zhihao Shi","submitted_at":"2023-03-17T05:16:49Z","abstract_excerpt":"Subgraph-wise sampling -- a promising class of mini-batch training techniques for graph neural networks (GNNs -- is critical for real-world applications. During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i.e., the exponentially increasing dependencies of nodes with the number of MP iterations. However, discarding messages may sacrifice the gradient estimation accuracy, posing significant challenges to their convergence analysis and convergence speeds. To addres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11081","kind":"arxiv","version":2},"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/2303.11081/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":"2303.11081","created_at":"2026-07-05T08:57:32.973644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11081v2","created_at":"2026-07-05T08:57:32.973644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11081","created_at":"2026-07-05T08:57:32.973644+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQ37OEZX2VM6","created_at":"2026-07-05T08:57:32.973644+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQ37OEZX2VM64S4G","created_at":"2026-07-05T08:57:32.973644+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQ37OEZX","created_at":"2026-07-05T08:57:32.973644+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/PQ37OEZX2VM64S4GCUDRT37TPS","json":"https://pith.science/pith/PQ37OEZX2VM64S4GCUDRT37TPS.json","graph_json":"https://pith.science/api/pith-number/PQ37OEZX2VM64S4GCUDRT37TPS/graph.json","events_json":"https://pith.science/api/pith-number/PQ37OEZX2VM64S4GCUDRT37TPS/events.json","paper":"https://pith.science/paper/PQ37OEZX"},"agent_actions":{"view_html":"https://pith.science/pith/PQ37OEZX2VM64S4GCUDRT37TPS","download_json":"https://pith.science/pith/PQ37OEZX2VM64S4GCUDRT37TPS.json","view_paper":"https://pith.science/paper/PQ37OEZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11081&json=true","fetch_graph":"https://pith.science/api/pith-number/PQ37OEZX2VM64S4GCUDRT37TPS/graph.json","fetch_events":"https://pith.science/api/pith-number/PQ37OEZX2VM64S4GCUDRT37TPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQ37OEZX2VM64S4GCUDRT37TPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQ37OEZX2VM64S4GCUDRT37TPS/action/storage_attestation","attest_author":"https://pith.science/pith/PQ37OEZX2VM64S4GCUDRT37TPS/action/author_attestation","sign_citation":"https://pith.science/pith/PQ37OEZX2VM64S4GCUDRT37TPS/action/citation_signature","submit_replication":"https://pith.science/pith/PQ37OEZX2VM64S4GCUDRT37TPS/action/replication_record"}},"created_at":"2026-07-05T08:57:32.973644+00:00","updated_at":"2026-07-05T08:57:32.973644+00:00"}