{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:APOHL5OBYTXGVLIPYLUUOTMVBF","short_pith_number":"pith:APOHL5OB","schema_version":"1.0","canonical_sha256":"03dc75f5c1c4ee6aad0fc2e9474d950963b8375ab0138987614ec82a685f722d","source":{"kind":"arxiv","id":"1710.10568","version":3},"attestation_state":"computed","paper":{"title":"Stochastic Training of Graph Convolutional Networks with Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jianfei Chen, Jun Zhu, Le Song","submitted_at":"2017-10-29T06:14:00Z","abstract_excerpt":"Graph convolutional networks (GCNs) are powerful deep neural networks for graph-structured data. However, GCN computes the representation of a node recursively from its neighbors, making the receptive field size grow exponentially with the number of layers. Previous attempts on reducing the receptive field size by subsampling neighbors do not have a convergence guarantee, and their receptive field size per node is still in the order of hundreds. In this paper, we develop control variate based algorithms which allow sampling an arbitrarily small neighbor size. Furthermore, we prove new theoreti"},"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":"1710.10568","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-29T06:14:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f52ef012e6c3c4dce35a9703855099cf95826badf7f41e66d1613e5efe59e01","abstract_canon_sha256":"08db5f5a82eaab308df5aa28f623d5ebbca195716e40797b64d30499713d573e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:11.965207Z","signature_b64":"SEGyWXrfduPoHOF9RjkmIwBiB06PnvjYJl1y9f+unUm7Y/Z8XDfHdAfsa5PUmt4rUNj4U1ZrH3M2zFIyiKBeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03dc75f5c1c4ee6aad0fc2e9474d950963b8375ab0138987614ec82a685f722d","last_reissued_at":"2026-05-18T00:22:11.964610Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:11.964610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Training of Graph Convolutional Networks with Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jianfei Chen, Jun Zhu, Le Song","submitted_at":"2017-10-29T06:14:00Z","abstract_excerpt":"Graph convolutional networks (GCNs) are powerful deep neural networks for graph-structured data. However, GCN computes the representation of a node recursively from its neighbors, making the receptive field size grow exponentially with the number of layers. Previous attempts on reducing the receptive field size by subsampling neighbors do not have a convergence guarantee, and their receptive field size per node is still in the order of hundreds. In this paper, we develop control variate based algorithms which allow sampling an arbitrarily small neighbor size. Furthermore, we prove new theoreti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10568","kind":"arxiv","version":3},"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":"1710.10568","created_at":"2026-05-18T00:22:11.964706+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10568v3","created_at":"2026-05-18T00:22:11.964706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10568","created_at":"2026-05-18T00:22:11.964706+00:00"},{"alias_kind":"pith_short_12","alias_value":"APOHL5OBYTXG","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"APOHL5OBYTXGVLIP","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"APOHL5OB","created_at":"2026-05-18T12:31:05.417338+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/APOHL5OBYTXGVLIPYLUUOTMVBF","json":"https://pith.science/pith/APOHL5OBYTXGVLIPYLUUOTMVBF.json","graph_json":"https://pith.science/api/pith-number/APOHL5OBYTXGVLIPYLUUOTMVBF/graph.json","events_json":"https://pith.science/api/pith-number/APOHL5OBYTXGVLIPYLUUOTMVBF/events.json","paper":"https://pith.science/paper/APOHL5OB"},"agent_actions":{"view_html":"https://pith.science/pith/APOHL5OBYTXGVLIPYLUUOTMVBF","download_json":"https://pith.science/pith/APOHL5OBYTXGVLIPYLUUOTMVBF.json","view_paper":"https://pith.science/paper/APOHL5OB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10568&json=true","fetch_graph":"https://pith.science/api/pith-number/APOHL5OBYTXGVLIPYLUUOTMVBF/graph.json","fetch_events":"https://pith.science/api/pith-number/APOHL5OBYTXGVLIPYLUUOTMVBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APOHL5OBYTXGVLIPYLUUOTMVBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APOHL5OBYTXGVLIPYLUUOTMVBF/action/storage_attestation","attest_author":"https://pith.science/pith/APOHL5OBYTXGVLIPYLUUOTMVBF/action/author_attestation","sign_citation":"https://pith.science/pith/APOHL5OBYTXGVLIPYLUUOTMVBF/action/citation_signature","submit_replication":"https://pith.science/pith/APOHL5OBYTXGVLIPYLUUOTMVBF/action/replication_record"}},"created_at":"2026-05-18T00:22:11.964706+00:00","updated_at":"2026-05-18T00:22:11.964706+00:00"}