{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5T4ERQ3FCYSFZIZXHFCJ6UDV2L","short_pith_number":"pith:5T4ERQ3F","schema_version":"1.0","canonical_sha256":"ecf848c36516245ca33739449f5075d2d95482713a6c31ae89f378e709ddbeae","source":{"kind":"arxiv","id":"1911.08538","version":5},"attestation_state":"computed","paper":{"title":"Heterogeneous Deep Graph Infomax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Chao Huang, Jiawei Zhang, Liefeng Bo, Peng Dai, Yuxiang Ren","submitted_at":"2019-11-19T20:07:45Z","abstract_excerpt":"Graph representation learning is to learn universal node representations that preserve both node attributes and structural information. The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering. When a graph is heterogeneous, the problem becomes more challenging than the homogeneous graph node learning problem. Inspired by the emerging information theoretic-based learning algorithm, in this paper we propose an unsupervised graph neural network Heterogeneous Deep Graph Infomax (HDGI) for heterogeneous graph representation lea"},"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":"1911.08538","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-19T20:07:45Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"8ec7f1ff8e4158e4f2ff65e9e2ecb70664cbe2fe897faf227d3534d1256248f2","abstract_canon_sha256":"77d83ed73b2f143983a393b22e1d1afb2c3776d900731213c77311a9a9c6ce4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:17.957106Z","signature_b64":"/QDgCMyu/eB2ep8ClYWDVJlUVh/V76K4tEnMvi0SrxmoYac3oXODPQnUQ3ToPBxBGIYKOYDlrjLD4bkGPe0pCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecf848c36516245ca33739449f5075d2d95482713a6c31ae89f378e709ddbeae","last_reissued_at":"2026-07-05T01:51:17.956657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:17.956657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Deep Graph Infomax","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Chao Huang, Jiawei Zhang, Liefeng Bo, Peng Dai, Yuxiang Ren","submitted_at":"2019-11-19T20:07:45Z","abstract_excerpt":"Graph representation learning is to learn universal node representations that preserve both node attributes and structural information. The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering. When a graph is heterogeneous, the problem becomes more challenging than the homogeneous graph node learning problem. Inspired by the emerging information theoretic-based learning algorithm, in this paper we propose an unsupervised graph neural network Heterogeneous Deep Graph Infomax (HDGI) for heterogeneous graph representation lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08538","kind":"arxiv","version":5},"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/1911.08538/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":"1911.08538","created_at":"2026-07-05T01:51:17.956710+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.08538v5","created_at":"2026-07-05T01:51:17.956710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08538","created_at":"2026-07-05T01:51:17.956710+00:00"},{"alias_kind":"pith_short_12","alias_value":"5T4ERQ3FCYSF","created_at":"2026-07-05T01:51:17.956710+00:00"},{"alias_kind":"pith_short_16","alias_value":"5T4ERQ3FCYSFZIZX","created_at":"2026-07-05T01:51:17.956710+00:00"},{"alias_kind":"pith_short_8","alias_value":"5T4ERQ3F","created_at":"2026-07-05T01:51:17.956710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05463","citing_title":"Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06928","citing_title":"Leveraging LLMs and Heterogeneous Knowledge Graphs for Persona-Driven Session-Based Recommendation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L","json":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L.json","graph_json":"https://pith.science/api/pith-number/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/graph.json","events_json":"https://pith.science/api/pith-number/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/events.json","paper":"https://pith.science/paper/5T4ERQ3F"},"agent_actions":{"view_html":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L","download_json":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L.json","view_paper":"https://pith.science/paper/5T4ERQ3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.08538&json=true","fetch_graph":"https://pith.science/api/pith-number/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/graph.json","fetch_events":"https://pith.science/api/pith-number/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/action/storage_attestation","attest_author":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/action/author_attestation","sign_citation":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/action/citation_signature","submit_replication":"https://pith.science/pith/5T4ERQ3FCYSFZIZXHFCJ6UDV2L/action/replication_record"}},"created_at":"2026-07-05T01:51:17.956710+00:00","updated_at":"2026-07-05T01:51:17.956710+00:00"}