{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B2YCLRK2Z4OETICFAQPQXBFXGC","short_pith_number":"pith:B2YCLRK2","schema_version":"1.0","canonical_sha256":"0eb025c55acf1c49a045041f0b84b730840ef420178ae7aa6b08aa423f184cd2","source":{"kind":"arxiv","id":"2312.04883","version":1},"attestation_state":"computed","paper":{"title":"Understanding Community Bias Amplification in Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Divin Yan, Hongwei Zhang, Shengzhong Zhang, Wenjie Yang, Yimin Zhang, Zengfeng Huang","submitted_at":"2023-12-08T07:43:05Z","abstract_excerpt":"In this work, we discover a phenomenon of community bias amplification in graph representation learning, which refers to the exacerbation of performance bias between different classes by graph representation learning. We conduct an in-depth theoretical study of this phenomenon from a novel spectral perspective. Our analysis suggests that structural bias between communities results in varying local convergence speeds for node embeddings. This phenomenon leads to bias amplification in the classification results of downstream tasks. Based on the theoretical insights, we propose random graph coars"},"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":"2312.04883","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-08T07:43:05Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"35bf7703fe0bfe827b62b5174bebcdf99e2104fc83336633120b9c3eeb5aa39c","abstract_canon_sha256":"0267c709375a43495ef291ae37afcd8cabbf84c359d98b48bdff4e98cb81fa1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:53.780243Z","signature_b64":"AhjIMdgMe2FMKEGF6N/GVrEJ3jHSKtcrSwQtyFtrq3uznTcm3T8fICZfmMWjvcIetkHVb4jqKErRc4dPeuxGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eb025c55acf1c49a045041f0b84b730840ef420178ae7aa6b08aa423f184cd2","last_reissued_at":"2026-07-05T07:21:53.779718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:53.779718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Community Bias Amplification in Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Divin Yan, Hongwei Zhang, Shengzhong Zhang, Wenjie Yang, Yimin Zhang, Zengfeng Huang","submitted_at":"2023-12-08T07:43:05Z","abstract_excerpt":"In this work, we discover a phenomenon of community bias amplification in graph representation learning, which refers to the exacerbation of performance bias between different classes by graph representation learning. We conduct an in-depth theoretical study of this phenomenon from a novel spectral perspective. Our analysis suggests that structural bias between communities results in varying local convergence speeds for node embeddings. This phenomenon leads to bias amplification in the classification results of downstream tasks. Based on the theoretical insights, we propose random graph coars"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04883","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/2312.04883/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":"2312.04883","created_at":"2026-07-05T07:21:53.779769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04883v1","created_at":"2026-07-05T07:21:53.779769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04883","created_at":"2026-07-05T07:21:53.779769+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2YCLRK2Z4OE","created_at":"2026-07-05T07:21:53.779769+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2YCLRK2Z4OETICF","created_at":"2026-07-05T07:21:53.779769+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2YCLRK2","created_at":"2026-07-05T07:21:53.779769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05214","citing_title":"Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC","json":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC.json","graph_json":"https://pith.science/api/pith-number/B2YCLRK2Z4OETICFAQPQXBFXGC/graph.json","events_json":"https://pith.science/api/pith-number/B2YCLRK2Z4OETICFAQPQXBFXGC/events.json","paper":"https://pith.science/paper/B2YCLRK2"},"agent_actions":{"view_html":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC","download_json":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC.json","view_paper":"https://pith.science/paper/B2YCLRK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04883&json=true","fetch_graph":"https://pith.science/api/pith-number/B2YCLRK2Z4OETICFAQPQXBFXGC/graph.json","fetch_events":"https://pith.science/api/pith-number/B2YCLRK2Z4OETICFAQPQXBFXGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC/action/storage_attestation","attest_author":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC/action/author_attestation","sign_citation":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC/action/citation_signature","submit_replication":"https://pith.science/pith/B2YCLRK2Z4OETICFAQPQXBFXGC/action/replication_record"}},"created_at":"2026-07-05T07:21:53.779769+00:00","updated_at":"2026-07-05T07:21:53.779769+00:00"}