{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MNB36WFIYVG3E3RJFQFMRCVWTI","short_pith_number":"pith:MNB36WFI","schema_version":"1.0","canonical_sha256":"6343bf58a8c54db26e292c0ac88ab69a31325d6a1981e95ecab093092a0f8d2d","source":{"kind":"arxiv","id":"1801.10247","version":1},"attestation_state":"computed","paper":{"title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cao Xiao, Jie Chen, Tengfei Ma","submitted_at":"2018-01-30T22:36:16Z","abstract_excerpt":"The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning. This model, however, was originally designed to be learned with the presence of both training and test data. Moreover, the recursive neighborhood expansion across layers poses time and memory challenges for training with large, dense graphs. To relax the requirement of simultaneous availability of test data, we interpret graph convolutions as integral transforms of embedding functions under probability measures. Such an interpretation allows for the use of Mon"},"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":"1801.10247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-30T22:36:16Z","cross_cats_sorted":[],"title_canon_sha256":"ee91d0ff2eeb999f3c80873ef3fe26e0ff7e6e8d32321c9e6650b9d2578634fd","abstract_canon_sha256":"0ebce73132e853262f5dc6975b5b5002e3d93e3812eae6f72dd6ba029d2fc88d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:41.365855Z","signature_b64":"hu8myu8iP8teBy/xPEKp8397qoQcM0DbXTxRFZ1w4y/WiJi2ykwSiIT4oCo8dE7Gfci9ok8fB9MtWHCcZmi0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6343bf58a8c54db26e292c0ac88ab69a31325d6a1981e95ecab093092a0f8d2d","last_reissued_at":"2026-05-18T00:24:41.365180Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:41.365180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cao Xiao, Jie Chen, Tengfei Ma","submitted_at":"2018-01-30T22:36:16Z","abstract_excerpt":"The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning. This model, however, was originally designed to be learned with the presence of both training and test data. Moreover, the recursive neighborhood expansion across layers poses time and memory challenges for training with large, dense graphs. To relax the requirement of simultaneous availability of test data, we interpret graph convolutions as integral transforms of embedding functions under probability measures. Such an interpretation allows for the use of Mon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.10247","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":""},"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":"1801.10247","created_at":"2026-05-18T00:24:41.365285+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.10247v1","created_at":"2026-05-18T00:24:41.365285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.10247","created_at":"2026-05-18T00:24:41.365285+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNB36WFIYVG3","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNB36WFIYVG3E3RJ","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNB36WFI","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22480","citing_title":"Implicit Regularization of Mini-Batch Training in Graph Neural Networks","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02651","citing_title":"Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27356","citing_title":"TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI","json":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI.json","graph_json":"https://pith.science/api/pith-number/MNB36WFIYVG3E3RJFQFMRCVWTI/graph.json","events_json":"https://pith.science/api/pith-number/MNB36WFIYVG3E3RJFQFMRCVWTI/events.json","paper":"https://pith.science/paper/MNB36WFI"},"agent_actions":{"view_html":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI","download_json":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI.json","view_paper":"https://pith.science/paper/MNB36WFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.10247&json=true","fetch_graph":"https://pith.science/api/pith-number/MNB36WFIYVG3E3RJFQFMRCVWTI/graph.json","fetch_events":"https://pith.science/api/pith-number/MNB36WFIYVG3E3RJFQFMRCVWTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI/action/storage_attestation","attest_author":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI/action/author_attestation","sign_citation":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI/action/citation_signature","submit_replication":"https://pith.science/pith/MNB36WFIYVG3E3RJFQFMRCVWTI/action/replication_record"}},"created_at":"2026-05-18T00:24:41.365285+00:00","updated_at":"2026-05-18T00:24:41.365285+00:00"}