{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PNVHSGCSCJB356RTTDYNJSWUGS","short_pith_number":"pith:PNVHSGCS","schema_version":"1.0","canonical_sha256":"7b6a7918521243befa3398f0d4cad434a3a8dced7ca36aebcde00cfa220b8dc9","source":{"kind":"arxiv","id":"2012.12533","version":3},"attestation_state":"computed","paper":{"title":"Motif-Driven Contrastive Learning of Graph Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arjun Subramonian, Shichang Zhang, Yizhou Sun, Ziniu Hu","submitted_at":"2020-12-23T08:10:19Z","abstract_excerpt":"Pre-training Graph Neural Networks (GNN) via self-supervised contrastive learning has recently drawn lots of attention. However, most existing works focus on node-level contrastive learning, which cannot capture global graph structure. The key challenge to conducting subgraph-level contrastive learning is to sample informative subgraphs that are semantically meaningful. To solve it, we propose to learn graph motifs, which are frequently-occurring subgraph patterns (e.g. functional groups of molecules), for better subgraph sampling. Our framework MotIf-driven Contrastive leaRning Of Graph repre"},"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":"2012.12533","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-23T08:10:19Z","cross_cats_sorted":[],"title_canon_sha256":"0469a3a9776b7d865351de1e151acbc8cb824080dbb3e20ee124a3be2d13b27f","abstract_canon_sha256":"763cb21973f4256e4b9a30ef4e3a512e888aa3800eb297c7ebad166a2eb68aea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:34.974667Z","signature_b64":"R2HDDSunFwZFoZqFczBzGEIwjI3IMWtlW+FngG7+x5hJoOAWWpV8JzAPSJeKDMg8QajJJDX6E2I6ck1yeug8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b6a7918521243befa3398f0d4cad434a3a8dced7ca36aebcde00cfa220b8dc9","last_reissued_at":"2026-07-05T02:32:34.974187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:34.974187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motif-Driven Contrastive Learning of Graph Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arjun Subramonian, Shichang Zhang, Yizhou Sun, Ziniu Hu","submitted_at":"2020-12-23T08:10:19Z","abstract_excerpt":"Pre-training Graph Neural Networks (GNN) via self-supervised contrastive learning has recently drawn lots of attention. However, most existing works focus on node-level contrastive learning, which cannot capture global graph structure. The key challenge to conducting subgraph-level contrastive learning is to sample informative subgraphs that are semantically meaningful. To solve it, we propose to learn graph motifs, which are frequently-occurring subgraph patterns (e.g. functional groups of molecules), for better subgraph sampling. Our framework MotIf-driven Contrastive leaRning Of Graph repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.12533","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/2012.12533/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":"2012.12533","created_at":"2026-07-05T02:32:34.974231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.12533v3","created_at":"2026-07-05T02:32:34.974231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.12533","created_at":"2026-07-05T02:32:34.974231+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNVHSGCSCJB3","created_at":"2026-07-05T02:32:34.974231+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNVHSGCSCJB356RT","created_at":"2026-07-05T02:32:34.974231+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNVHSGCS","created_at":"2026-07-05T02:32:34.974231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.02082","citing_title":"FARM: Enhancing Molecular Representations with Functional Group Awareness","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16088","citing_title":"Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS","json":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS.json","graph_json":"https://pith.science/api/pith-number/PNVHSGCSCJB356RTTDYNJSWUGS/graph.json","events_json":"https://pith.science/api/pith-number/PNVHSGCSCJB356RTTDYNJSWUGS/events.json","paper":"https://pith.science/paper/PNVHSGCS"},"agent_actions":{"view_html":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS","download_json":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS.json","view_paper":"https://pith.science/paper/PNVHSGCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.12533&json=true","fetch_graph":"https://pith.science/api/pith-number/PNVHSGCSCJB356RTTDYNJSWUGS/graph.json","fetch_events":"https://pith.science/api/pith-number/PNVHSGCSCJB356RTTDYNJSWUGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS/action/storage_attestation","attest_author":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS/action/author_attestation","sign_citation":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS/action/citation_signature","submit_replication":"https://pith.science/pith/PNVHSGCSCJB356RTTDYNJSWUGS/action/replication_record"}},"created_at":"2026-07-05T02:32:34.974231+00:00","updated_at":"2026-07-05T02:32:34.974231+00:00"}