{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JYNMVR2ANQ2Z2A7ZJDKYQMXTGT","short_pith_number":"pith:JYNMVR2A","schema_version":"1.0","canonical_sha256":"4e1acac7406c359d03f948d58832f334dead44f1ced80106e72933a0a6c0b546","source":{"kind":"arxiv","id":"2305.10758","version":2},"attestation_state":"computed","paper":{"title":"Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haitao Lin, Lirong Wu, Stan Z. Li, Tianyu Fan, Yufei Huang","submitted_at":"2023-05-18T06:57:06Z","abstract_excerpt":"Recent years have witnessed the great success of Graph Neural Networks (GNNs) in handling graph-related tasks. However, MLPs remain the primary workhorse for practical industrial applications due to their desirable inference efficiency and scalability. To reduce their gaps, one can directly distill knowledge from a well-designed teacher GNN to a student MLP, which is termed as GNN-to-MLP distillation. However, the process of distillation usually entails a loss of information, and ``which knowledge patterns of GNNs are more likely to be left and distilled into MLPs?\" becomes an important questi"},"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":"2305.10758","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T06:57:06Z","cross_cats_sorted":[],"title_canon_sha256":"040559005eb7be817ceeb1fc7b45e9281951493ea9667df96f2a73029d6b6815","abstract_canon_sha256":"adda6e56724af7643ad73a3874f0d555b81cb017bb422f5cdd8306e47925ea9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:06.978302Z","signature_b64":"ASVhNrUca8isvL7d2JY2yN1oFxU5t8ylFxJmgkC95WtKkM2xbIE5R8aygY9eun21DP5RA6BObq29Hz1Jl3mGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e1acac7406c359d03f948d58832f334dead44f1ced80106e72933a0a6c0b546","last_reissued_at":"2026-07-05T06:17:06.977765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:06.977765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haitao Lin, Lirong Wu, Stan Z. Li, Tianyu Fan, Yufei Huang","submitted_at":"2023-05-18T06:57:06Z","abstract_excerpt":"Recent years have witnessed the great success of Graph Neural Networks (GNNs) in handling graph-related tasks. However, MLPs remain the primary workhorse for practical industrial applications due to their desirable inference efficiency and scalability. To reduce their gaps, one can directly distill knowledge from a well-designed teacher GNN to a student MLP, which is termed as GNN-to-MLP distillation. However, the process of distillation usually entails a loss of information, and ``which knowledge patterns of GNNs are more likely to be left and distilled into MLPs?\" becomes an important questi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10758","kind":"arxiv","version":2},"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/2305.10758/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":"2305.10758","created_at":"2026-07-05T06:17:06.977831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10758v2","created_at":"2026-07-05T06:17:06.977831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10758","created_at":"2026-07-05T06:17:06.977831+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYNMVR2ANQ2Z","created_at":"2026-07-05T06:17:06.977831+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYNMVR2ANQ2Z2A7Z","created_at":"2026-07-05T06:17:06.977831+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYNMVR2A","created_at":"2026-07-05T06:17:06.977831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19031","citing_title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT","json":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT.json","graph_json":"https://pith.science/api/pith-number/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/graph.json","events_json":"https://pith.science/api/pith-number/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/events.json","paper":"https://pith.science/paper/JYNMVR2A"},"agent_actions":{"view_html":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT","download_json":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT.json","view_paper":"https://pith.science/paper/JYNMVR2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10758&json=true","fetch_graph":"https://pith.science/api/pith-number/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/graph.json","fetch_events":"https://pith.science/api/pith-number/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/action/storage_attestation","attest_author":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/action/author_attestation","sign_citation":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/action/citation_signature","submit_replication":"https://pith.science/pith/JYNMVR2ANQ2Z2A7ZJDKYQMXTGT/action/replication_record"}},"created_at":"2026-07-05T06:17:06.977831+00:00","updated_at":"2026-07-05T06:17:06.977831+00:00"}