{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5GCHE2SZ3MXMFAK7C6X43SLLQD","short_pith_number":"pith:5GCHE2SZ","schema_version":"1.0","canonical_sha256":"e984726a59db2ec2815f17afcdc96b80f7ef146901a88659a2c0dbbfe9e7a77a","source":{"kind":"arxiv","id":"2303.06344","version":2},"attestation_state":"computed","paper":{"title":"Graph Contrastive Learning under Heterophily via Graph Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baharan Mirzasoleiman, Wenhan Yang","submitted_at":"2023-03-11T08:32:39Z","abstract_excerpt":"Graph contrastive learning (CL) methods learn node representations in a self-supervised manner by maximizing the similarity between the augmented node representations obtained via a GNN-based encoder. However, CL methods perform poorly on graphs with heterophily, where connected nodes tend to belong to different classes. In this work, we address this problem by proposing an effective graph CL method, namely HLCL, for learning graph representations under heterophily. HLCL first identifies a homophilic and a heterophilic subgraph based on the cosine similarity of node features. It then uses a lo"},"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":"2303.06344","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-11T08:32:39Z","cross_cats_sorted":[],"title_canon_sha256":"cb9138716bbe0bf1e7cf3d8566ff7b39070e7f3960a95c2f16621d1a381a61dc","abstract_canon_sha256":"41712562debcc7f7f6db09f07a740f14ac77709320714efde70b8179fa56d987"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:44.088399Z","signature_b64":"Qq8S5dD67p/Nd0Iq48HplmHJOKrOK2kZcM73t+3wO2oiyTPET9bJLHNrDJp+kuQEO9xZuzYkElhTXbsZloYxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e984726a59db2ec2815f17afcdc96b80f7ef146901a88659a2c0dbbfe9e7a77a","last_reissued_at":"2026-07-05T08:29:44.088035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:44.088035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Contrastive Learning under Heterophily via Graph Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baharan Mirzasoleiman, Wenhan Yang","submitted_at":"2023-03-11T08:32:39Z","abstract_excerpt":"Graph contrastive learning (CL) methods learn node representations in a self-supervised manner by maximizing the similarity between the augmented node representations obtained via a GNN-based encoder. However, CL methods perform poorly on graphs with heterophily, where connected nodes tend to belong to different classes. In this work, we address this problem by proposing an effective graph CL method, namely HLCL, for learning graph representations under heterophily. HLCL first identifies a homophilic and a heterophilic subgraph based on the cosine similarity of node features. It then uses a lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06344","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/2303.06344/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":"2303.06344","created_at":"2026-07-05T08:29:44.088096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06344v2","created_at":"2026-07-05T08:29:44.088096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06344","created_at":"2026-07-05T08:29:44.088096+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GCHE2SZ3MXM","created_at":"2026-07-05T08:29:44.088096+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GCHE2SZ3MXMFAK7","created_at":"2026-07-05T08:29:44.088096+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GCHE2SZ","created_at":"2026-07-05T08:29:44.088096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01595","citing_title":"Adaptive Homophily Clustering: Structure Homophily Graph Learning with Adaptive Filter for Hyperspectral Image","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD","json":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD.json","graph_json":"https://pith.science/api/pith-number/5GCHE2SZ3MXMFAK7C6X43SLLQD/graph.json","events_json":"https://pith.science/api/pith-number/5GCHE2SZ3MXMFAK7C6X43SLLQD/events.json","paper":"https://pith.science/paper/5GCHE2SZ"},"agent_actions":{"view_html":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD","download_json":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD.json","view_paper":"https://pith.science/paper/5GCHE2SZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06344&json=true","fetch_graph":"https://pith.science/api/pith-number/5GCHE2SZ3MXMFAK7C6X43SLLQD/graph.json","fetch_events":"https://pith.science/api/pith-number/5GCHE2SZ3MXMFAK7C6X43SLLQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD/action/storage_attestation","attest_author":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD/action/author_attestation","sign_citation":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD/action/citation_signature","submit_replication":"https://pith.science/pith/5GCHE2SZ3MXMFAK7C6X43SLLQD/action/replication_record"}},"created_at":"2026-07-05T08:29:44.088096+00:00","updated_at":"2026-07-05T08:29:44.088096+00:00"}