{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SANOBGOWOU34IJLFC542JAMA7J","short_pith_number":"pith:SANOBGOW","schema_version":"1.0","canonical_sha256":"901ae099d67537c425651779a48180fa4abb943b0c306abc33a9bab2357e8086","source":{"kind":"arxiv","id":"2104.05960","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Dongsheng Li, Hongzuo Xu, Ning Liu, Songlei Jian, Yiming Zhang, Zhiquan Lai","submitted_at":"2021-04-13T06:22:24Z","abstract_excerpt":"Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks. However, the graph pooling technique for learning expressive graph-level representation is critical yet still challenging. Existing pooling methods either struggle to capture the local substructure or fail to effectively utilize high-order dependency, thus diminishing the expression capability. In this paper we propose HAP, a hierarchical graph-level representation learning framework, which is adaptively sensitive to graph structures, i.e., HAP "},"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":"2104.05960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-13T06:22:24Z","cross_cats_sorted":["cs.NI","cs.SI"],"title_canon_sha256":"07903d796bf2124616899a3d9ed62d8404e2f5865bc0e596f18e0d1b927dc618","abstract_canon_sha256":"4b36e66d290f1a94d189961f41b44e8d4fd15bf11567742393764a0fb7027e69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:27.420113Z","signature_b64":"nTvTNB0LKfErO03UknvdB0v47Jprjz+0DD0iEyunyTqXVEXO7qMSqlU/rSSrpitCXM8JBO/LdF9hBvxC3FGfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"901ae099d67537c425651779a48180fa4abb943b0c306abc33a9bab2357e8086","last_reissued_at":"2026-07-05T02:31:27.419713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:27.419713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Dongsheng Li, Hongzuo Xu, Ning Liu, Songlei Jian, Yiming Zhang, Zhiquan Lai","submitted_at":"2021-04-13T06:22:24Z","abstract_excerpt":"Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks. However, the graph pooling technique for learning expressive graph-level representation is critical yet still challenging. Existing pooling methods either struggle to capture the local substructure or fail to effectively utilize high-order dependency, thus diminishing the expression capability. In this paper we propose HAP, a hierarchical graph-level representation learning framework, which is adaptively sensitive to graph structures, i.e., HAP "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05960","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/2104.05960/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":"2104.05960","created_at":"2026-07-05T02:31:27.419770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05960v1","created_at":"2026-07-05T02:31:27.419770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05960","created_at":"2026-07-05T02:31:27.419770+00:00"},{"alias_kind":"pith_short_12","alias_value":"SANOBGOWOU34","created_at":"2026-07-05T02:31:27.419770+00:00"},{"alias_kind":"pith_short_16","alias_value":"SANOBGOWOU34IJLF","created_at":"2026-07-05T02:31:27.419770+00:00"},{"alias_kind":"pith_short_8","alias_value":"SANOBGOW","created_at":"2026-07-05T02:31:27.419770+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/SANOBGOWOU34IJLFC542JAMA7J","json":"https://pith.science/pith/SANOBGOWOU34IJLFC542JAMA7J.json","graph_json":"https://pith.science/api/pith-number/SANOBGOWOU34IJLFC542JAMA7J/graph.json","events_json":"https://pith.science/api/pith-number/SANOBGOWOU34IJLFC542JAMA7J/events.json","paper":"https://pith.science/paper/SANOBGOW"},"agent_actions":{"view_html":"https://pith.science/pith/SANOBGOWOU34IJLFC542JAMA7J","download_json":"https://pith.science/pith/SANOBGOWOU34IJLFC542JAMA7J.json","view_paper":"https://pith.science/paper/SANOBGOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05960&json=true","fetch_graph":"https://pith.science/api/pith-number/SANOBGOWOU34IJLFC542JAMA7J/graph.json","fetch_events":"https://pith.science/api/pith-number/SANOBGOWOU34IJLFC542JAMA7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SANOBGOWOU34IJLFC542JAMA7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SANOBGOWOU34IJLFC542JAMA7J/action/storage_attestation","attest_author":"https://pith.science/pith/SANOBGOWOU34IJLFC542JAMA7J/action/author_attestation","sign_citation":"https://pith.science/pith/SANOBGOWOU34IJLFC542JAMA7J/action/citation_signature","submit_replication":"https://pith.science/pith/SANOBGOWOU34IJLFC542JAMA7J/action/replication_record"}},"created_at":"2026-07-05T02:31:27.419770+00:00","updated_at":"2026-07-05T02:31:27.419770+00:00"}