{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IBOKCEYSUGK4JESW5SGMT2AGBL","short_pith_number":"pith:IBOKCEYS","schema_version":"1.0","canonical_sha256":"405ca11312a195c49256ec8cc9e8060aed3f09861e6ceb42f1b59e1882d819f5","source":{"kind":"arxiv","id":"2103.13125","version":2},"attestation_state":"computed","paper":{"title":"Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Chenguang Wang, Ziwen Liu","submitted_at":"2021-03-24T12:06:12Z","abstract_excerpt":"In this paper, we introduce a self-supervised learning method to enhance the graph-level representations with the help of a set of subgraphs. For this purpose, we propose a universal framework to generate subgraphs in an auto-regressive way and then using these subgraphs to guide the learning of graph representation by Graph Neural Networks. Under this framework, we can get a comprehensive understanding of the graph structure in a learnable way. And to fully capture enough information of original graphs, we design three information aggregators: \\textbf{attribute-conv}, \\textbf{layer-conv} and "},"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":"2103.13125","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-24T12:06:12Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"59b9771231cf4106bbd9df3b71468c3944533b3fc9ae0204567fd3621ad2ceda","abstract_canon_sha256":"9709fc1b174d2819818df701dace91a8e8b8e4eb9b40ff88f4245e1d9db987f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:18.269774Z","signature_b64":"6Gn+iVfY8Pa2nL/FPvQVeDhLarDib62O0v/2y3oGHHb7waDgfPaXhcgwjYzHAF55/bVPP+DTnKCpe8kqRmWUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405ca11312a195c49256ec8cc9e8060aed3f09861e6ceb42f1b59e1882d819f5","last_reissued_at":"2026-07-05T02:38:18.269140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:18.269140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Chenguang Wang, Ziwen Liu","submitted_at":"2021-03-24T12:06:12Z","abstract_excerpt":"In this paper, we introduce a self-supervised learning method to enhance the graph-level representations with the help of a set of subgraphs. For this purpose, we propose a universal framework to generate subgraphs in an auto-regressive way and then using these subgraphs to guide the learning of graph representation by Graph Neural Networks. Under this framework, we can get a comprehensive understanding of the graph structure in a learnable way. And to fully capture enough information of original graphs, we design three information aggregators: \\textbf{attribute-conv}, \\textbf{layer-conv} and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13125","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/2103.13125/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":"2103.13125","created_at":"2026-07-05T02:38:18.269235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.13125v2","created_at":"2026-07-05T02:38:18.269235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13125","created_at":"2026-07-05T02:38:18.269235+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBOKCEYSUGK4","created_at":"2026-07-05T02:38:18.269235+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBOKCEYSUGK4JESW","created_at":"2026-07-05T02:38:18.269235+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBOKCEYS","created_at":"2026-07-05T02:38:18.269235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08326","citing_title":"Graph Prompting for Graph Learning Models: Recent Advances and Future Directions","ref_index":99,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL","json":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL.json","graph_json":"https://pith.science/api/pith-number/IBOKCEYSUGK4JESW5SGMT2AGBL/graph.json","events_json":"https://pith.science/api/pith-number/IBOKCEYSUGK4JESW5SGMT2AGBL/events.json","paper":"https://pith.science/paper/IBOKCEYS"},"agent_actions":{"view_html":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL","download_json":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL.json","view_paper":"https://pith.science/paper/IBOKCEYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.13125&json=true","fetch_graph":"https://pith.science/api/pith-number/IBOKCEYSUGK4JESW5SGMT2AGBL/graph.json","fetch_events":"https://pith.science/api/pith-number/IBOKCEYSUGK4JESW5SGMT2AGBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL/action/storage_attestation","attest_author":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL/action/author_attestation","sign_citation":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL/action/citation_signature","submit_replication":"https://pith.science/pith/IBOKCEYSUGK4JESW5SGMT2AGBL/action/replication_record"}},"created_at":"2026-07-05T02:38:18.269235+00:00","updated_at":"2026-07-05T02:38:18.269235+00:00"}