{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3J2BH52P6AXWEQM5NT6FBLAVF3","short_pith_number":"pith:3J2BH52P","schema_version":"1.0","canonical_sha256":"da7413f74ff02f62419d6cfc50ac152eeba857e2479a8c8f4d840ed209505bb0","source":{"kind":"arxiv","id":"2302.00924","version":4},"attestation_state":"computed","paper":{"title":"LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Wang, Xize Liang, Zhihao Shi","submitted_at":"2023-02-02T07:52:34Z","abstract_excerpt":"The message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. However, training GNNs on large-scale graphs suffers from the well-known neighbor explosion problem, i.e., the exponentially increasing dependencies of nodes with the number of message passing layers. Subgraph-wise sampling methods -- a promising class of mini-batch training techniques -- discard messages outside the mini-batches in backward passes to avoid the neighbor explosion problem at the expense of gradient estimation accuracy. This poses significant challenges to their co"},"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":"2302.00924","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T07:52:34Z","cross_cats_sorted":[],"title_canon_sha256":"6edb90ed7121a59ef95f98de29a7f8ebe50998019b4a38efb7d49fd2ee4967d8","abstract_canon_sha256":"81bd5a43c3a0d78159351c14248fa5ae8939d6d5278dbbaf04686427a2d39d4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:38.406482Z","signature_b64":"Im/SEGDwPVwdXIIjYbH/EMGGomhr3X2/JVT7Wr87CJtJb5G1KthaCyxgwdDiQ658VofpPp5EM9W/Dgsc5EwxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da7413f74ff02f62419d6cfc50ac152eeba857e2479a8c8f4d840ed209505bb0","last_reissued_at":"2026-07-05T10:31:38.405955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:38.405955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Wang, Xize Liang, Zhihao Shi","submitted_at":"2023-02-02T07:52:34Z","abstract_excerpt":"The message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. However, training GNNs on large-scale graphs suffers from the well-known neighbor explosion problem, i.e., the exponentially increasing dependencies of nodes with the number of message passing layers. Subgraph-wise sampling methods -- a promising class of mini-batch training techniques -- discard messages outside the mini-batches in backward passes to avoid the neighbor explosion problem at the expense of gradient estimation accuracy. This poses significant challenges to their co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00924","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/2302.00924/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":"2302.00924","created_at":"2026-07-05T10:31:38.406019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00924v4","created_at":"2026-07-05T10:31:38.406019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00924","created_at":"2026-07-05T10:31:38.406019+00:00"},{"alias_kind":"pith_short_12","alias_value":"3J2BH52P6AXW","created_at":"2026-07-05T10:31:38.406019+00:00"},{"alias_kind":"pith_short_16","alias_value":"3J2BH52P6AXWEQM5","created_at":"2026-07-05T10:31:38.406019+00:00"},{"alias_kind":"pith_short_8","alias_value":"3J2BH52P","created_at":"2026-07-05T10:31:38.406019+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/3J2BH52P6AXWEQM5NT6FBLAVF3","json":"https://pith.science/pith/3J2BH52P6AXWEQM5NT6FBLAVF3.json","graph_json":"https://pith.science/api/pith-number/3J2BH52P6AXWEQM5NT6FBLAVF3/graph.json","events_json":"https://pith.science/api/pith-number/3J2BH52P6AXWEQM5NT6FBLAVF3/events.json","paper":"https://pith.science/paper/3J2BH52P"},"agent_actions":{"view_html":"https://pith.science/pith/3J2BH52P6AXWEQM5NT6FBLAVF3","download_json":"https://pith.science/pith/3J2BH52P6AXWEQM5NT6FBLAVF3.json","view_paper":"https://pith.science/paper/3J2BH52P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00924&json=true","fetch_graph":"https://pith.science/api/pith-number/3J2BH52P6AXWEQM5NT6FBLAVF3/graph.json","fetch_events":"https://pith.science/api/pith-number/3J2BH52P6AXWEQM5NT6FBLAVF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3J2BH52P6AXWEQM5NT6FBLAVF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3J2BH52P6AXWEQM5NT6FBLAVF3/action/storage_attestation","attest_author":"https://pith.science/pith/3J2BH52P6AXWEQM5NT6FBLAVF3/action/author_attestation","sign_citation":"https://pith.science/pith/3J2BH52P6AXWEQM5NT6FBLAVF3/action/citation_signature","submit_replication":"https://pith.science/pith/3J2BH52P6AXWEQM5NT6FBLAVF3/action/replication_record"}},"created_at":"2026-07-05T10:31:38.406019+00:00","updated_at":"2026-07-05T10:31:38.406019+00:00"}