{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R63GS2NJJC2CWKKFBFJ7T5KR5G","short_pith_number":"pith:R63GS2NJ","schema_version":"1.0","canonical_sha256":"8fb66969a948b42b29450953f9f551e98a0106e4511003f373f31f933b588897","source":{"kind":"arxiv","id":"2210.00102","version":3},"attestation_state":"computed","paper":{"title":"MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Neil Shah, Tong Zhao, Xia Hu, Xiaotian Han, Yozen Liu","submitted_at":"2022-09-30T21:33:51Z","abstract_excerpt":"Training graph neural networks (GNNs) on large graphs is complex and extremely time consuming. This is attributed to overheads caused by sparse matrix multiplication, which are sidestepped when training multi-layer perceptrons (MLPs) with only node features. MLPs, by ignoring graph context, are simple and faster for graph data, however they usually sacrifice prediction accuracy, limiting their applications for graph data. We observe that for most message passing-based GNNs, we can trivially derive an analog MLP (we call this a PeerMLP) with an equivalent weight space, by setting the trainable "},"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":"2210.00102","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T21:33:51Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"e873236876312ded920a5af7e2535d70a786a8c6413316e657c03f3ad4fe2ecd","abstract_canon_sha256":"102a603e4a19670825298ff719d6734bbef51c2b9f53e711c37c1c7d31593b15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:04.425028Z","signature_b64":"h3n9/WnBBhKydIkiVMPLJJToOwo3n00QLwzZqRRHsmUu1i7omc40WONhonm+LEVToJSKG+YtKf7ULuF+zLk+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fb66969a948b42b29450953f9f551e98a0106e4511003f373f31f933b588897","last_reissued_at":"2026-07-05T05:59:04.424461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:04.424461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Neil Shah, Tong Zhao, Xia Hu, Xiaotian Han, Yozen Liu","submitted_at":"2022-09-30T21:33:51Z","abstract_excerpt":"Training graph neural networks (GNNs) on large graphs is complex and extremely time consuming. This is attributed to overheads caused by sparse matrix multiplication, which are sidestepped when training multi-layer perceptrons (MLPs) with only node features. MLPs, by ignoring graph context, are simple and faster for graph data, however they usually sacrifice prediction accuracy, limiting their applications for graph data. We observe that for most message passing-based GNNs, we can trivially derive an analog MLP (we call this a PeerMLP) with an equivalent weight space, by setting the trainable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00102","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.00102/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":"2210.00102","created_at":"2026-07-05T05:59:04.424520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00102v3","created_at":"2026-07-05T05:59:04.424520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00102","created_at":"2026-07-05T05:59:04.424520+00:00"},{"alias_kind":"pith_short_12","alias_value":"R63GS2NJJC2C","created_at":"2026-07-05T05:59:04.424520+00:00"},{"alias_kind":"pith_short_16","alias_value":"R63GS2NJJC2CWKKF","created_at":"2026-07-05T05:59:04.424520+00:00"},{"alias_kind":"pith_short_8","alias_value":"R63GS2NJ","created_at":"2026-07-05T05:59:04.424520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01158","citing_title":"Attending To Syntactic Information In Biomedical Event Extraction Via Graph Neural Networks","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G","json":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G.json","graph_json":"https://pith.science/api/pith-number/R63GS2NJJC2CWKKFBFJ7T5KR5G/graph.json","events_json":"https://pith.science/api/pith-number/R63GS2NJJC2CWKKFBFJ7T5KR5G/events.json","paper":"https://pith.science/paper/R63GS2NJ"},"agent_actions":{"view_html":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G","download_json":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G.json","view_paper":"https://pith.science/paper/R63GS2NJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00102&json=true","fetch_graph":"https://pith.science/api/pith-number/R63GS2NJJC2CWKKFBFJ7T5KR5G/graph.json","fetch_events":"https://pith.science/api/pith-number/R63GS2NJJC2CWKKFBFJ7T5KR5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G/action/storage_attestation","attest_author":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G/action/author_attestation","sign_citation":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G/action/citation_signature","submit_replication":"https://pith.science/pith/R63GS2NJJC2CWKKFBFJ7T5KR5G/action/replication_record"}},"created_at":"2026-07-05T05:59:04.424520+00:00","updated_at":"2026-07-05T05:59:04.424520+00:00"}