{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QJXDUIEMVXJKOSF55EB326I3P5","short_pith_number":"pith:QJXDUIEM","schema_version":"1.0","canonical_sha256":"826e3a208cadd2a748bde903bd791b7f5062a9a23f4ab758b00232ff07385f95","source":{"kind":"arxiv","id":"2212.09083","version":1},"attestation_state":"computed","paper":{"title":"Influence-Based Mini-Batching for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chendi Qian, Johannes Gasteiger, Stephan G\\\"unnemann","submitted_at":"2022-12-18T13:27:01Z","abstract_excerpt":"Using graph neural networks for large graphs is challenging since there is no clear way of constructing mini-batches. To solve this, previous methods have relied on sampling or graph clustering. While these approaches often lead to good training convergence, they introduce significant overhead due to expensive random data accesses and perform poorly during inference. In this work we instead focus on model behavior during inference. We theoretically model batch construction via maximizing the influence score of nodes on the outputs. This formulation leads to optimal approximation of the output "},"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":"2212.09083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-18T13:27:01Z","cross_cats_sorted":["cs.AI","cs.SI","stat.ML"],"title_canon_sha256":"46b07451a9becc44cbac477454f6102b65e16563d5b791bd4c6daf3cd867d17d","abstract_canon_sha256":"ad72595d2df4f0f95e6260a946a293bc260474afb2230fdc3a706241f3fa8bb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:17.974495Z","signature_b64":"OJDfqBahcTRbZNUYXgSolvqtGSsL/N6g2GWos9UDQ/chkYA7FuOI7OZX1+U6RlvsXl37+kYbmQ8h89KmpQ8CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"826e3a208cadd2a748bde903bd791b7f5062a9a23f4ab758b00232ff07385f95","last_reissued_at":"2026-07-05T05:26:17.974034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:17.974034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Influence-Based Mini-Batching for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chendi Qian, Johannes Gasteiger, Stephan G\\\"unnemann","submitted_at":"2022-12-18T13:27:01Z","abstract_excerpt":"Using graph neural networks for large graphs is challenging since there is no clear way of constructing mini-batches. To solve this, previous methods have relied on sampling or graph clustering. While these approaches often lead to good training convergence, they introduce significant overhead due to expensive random data accesses and perform poorly during inference. In this work we instead focus on model behavior during inference. We theoretically model batch construction via maximizing the influence score of nodes on the outputs. This formulation leads to optimal approximation of the output "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09083","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/2212.09083/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":"2212.09083","created_at":"2026-07-05T05:26:17.974090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09083v1","created_at":"2026-07-05T05:26:17.974090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09083","created_at":"2026-07-05T05:26:17.974090+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJXDUIEMVXJK","created_at":"2026-07-05T05:26:17.974090+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJXDUIEMVXJKOSF5","created_at":"2026-07-05T05:26:17.974090+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJXDUIEM","created_at":"2026-07-05T05:26:17.974090+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/QJXDUIEMVXJKOSF55EB326I3P5","json":"https://pith.science/pith/QJXDUIEMVXJKOSF55EB326I3P5.json","graph_json":"https://pith.science/api/pith-number/QJXDUIEMVXJKOSF55EB326I3P5/graph.json","events_json":"https://pith.science/api/pith-number/QJXDUIEMVXJKOSF55EB326I3P5/events.json","paper":"https://pith.science/paper/QJXDUIEM"},"agent_actions":{"view_html":"https://pith.science/pith/QJXDUIEMVXJKOSF55EB326I3P5","download_json":"https://pith.science/pith/QJXDUIEMVXJKOSF55EB326I3P5.json","view_paper":"https://pith.science/paper/QJXDUIEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09083&json=true","fetch_graph":"https://pith.science/api/pith-number/QJXDUIEMVXJKOSF55EB326I3P5/graph.json","fetch_events":"https://pith.science/api/pith-number/QJXDUIEMVXJKOSF55EB326I3P5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJXDUIEMVXJKOSF55EB326I3P5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJXDUIEMVXJKOSF55EB326I3P5/action/storage_attestation","attest_author":"https://pith.science/pith/QJXDUIEMVXJKOSF55EB326I3P5/action/author_attestation","sign_citation":"https://pith.science/pith/QJXDUIEMVXJKOSF55EB326I3P5/action/citation_signature","submit_replication":"https://pith.science/pith/QJXDUIEMVXJKOSF55EB326I3P5/action/replication_record"}},"created_at":"2026-07-05T05:26:17.974090+00:00","updated_at":"2026-07-05T05:26:17.974090+00:00"}