{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XSLVXNNIM2BFUFYD34OC4HTZ76","short_pith_number":"pith:XSLVXNNI","schema_version":"1.0","canonical_sha256":"bc975bb5a866825a1703df1c2e1e79ffb0d026b80602f52c6f5509a0d5e1871e","source":{"kind":"arxiv","id":"2308.02117","version":3},"attestation_state":"computed","paper":{"title":"VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Jure Leskovec, Ling Yang, Minkai Xu, Muhan Zhang, Shenda Hong, Wei Qu, Wentao Zhang, Ye Tian, Zhongyi Liu","submitted_at":"2023-08-04T02:58:08Z","abstract_excerpt":"GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output representations of teacher GNN. Existing methods mainly make the MLP to mimic the GNN predictions over a few class labels. However, the class space may not be expressive enough for covering numerous diverse local graph structures, thus limiting the performance of knowledge transfer from GNN to MLP. To address this issue, we propose to learn a new powerful graph representation space by directly labeling nodes' diverse l"},"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":"2308.02117","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-04T02:58:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"4617d20b37621a0493dfc64cfa36ff4333303ab38e3a54c4a841d8fbd15cc44f","abstract_canon_sha256":"64ca92e156d952cdb9cae80da6bfa572846db8c19ba1374da3b2e4ecf0c2d53a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:58.556407Z","signature_b64":"/3BR1/XlVsEvEfi0l0RgdoNR4Uj82ND0UqL8PBVZca7dXUf6YC59vuHsQSKCAFwUJBMwcbmlwT1EwqcUwDZ7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc975bb5a866825a1703df1c2e1e79ffb0d026b80602f52c6f5509a0d5e1871e","last_reissued_at":"2026-07-05T07:52:58.555912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:58.555912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bin Cui, Jure Leskovec, Ling Yang, Minkai Xu, Muhan Zhang, Shenda Hong, Wei Qu, Wentao Zhang, Ye Tian, Zhongyi Liu","submitted_at":"2023-08-04T02:58:08Z","abstract_excerpt":"GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output representations of teacher GNN. Existing methods mainly make the MLP to mimic the GNN predictions over a few class labels. However, the class space may not be expressive enough for covering numerous diverse local graph structures, thus limiting the performance of knowledge transfer from GNN to MLP. To address this issue, we propose to learn a new powerful graph representation space by directly labeling nodes' diverse l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02117","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/2308.02117/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":"2308.02117","created_at":"2026-07-05T07:52:58.555974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02117v3","created_at":"2026-07-05T07:52:58.555974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02117","created_at":"2026-07-05T07:52:58.555974+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSLVXNNIM2BF","created_at":"2026-07-05T07:52:58.555974+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSLVXNNIM2BFUFYD","created_at":"2026-07-05T07:52:58.555974+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSLVXNNI","created_at":"2026-07-05T07:52:58.555974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.17036","citing_title":"LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00354","citing_title":"VQ-SAD: Vector Quantized Structure Aware Diffusion For Molecule Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76","json":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76.json","graph_json":"https://pith.science/api/pith-number/XSLVXNNIM2BFUFYD34OC4HTZ76/graph.json","events_json":"https://pith.science/api/pith-number/XSLVXNNIM2BFUFYD34OC4HTZ76/events.json","paper":"https://pith.science/paper/XSLVXNNI"},"agent_actions":{"view_html":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76","download_json":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76.json","view_paper":"https://pith.science/paper/XSLVXNNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02117&json=true","fetch_graph":"https://pith.science/api/pith-number/XSLVXNNIM2BFUFYD34OC4HTZ76/graph.json","fetch_events":"https://pith.science/api/pith-number/XSLVXNNIM2BFUFYD34OC4HTZ76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76/action/storage_attestation","attest_author":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76/action/author_attestation","sign_citation":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76/action/citation_signature","submit_replication":"https://pith.science/pith/XSLVXNNIM2BFUFYD34OC4HTZ76/action/replication_record"}},"created_at":"2026-07-05T07:52:58.555974+00:00","updated_at":"2026-07-05T07:52:58.555974+00:00"}