{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GMLYYDMCIF3NQGPMCIOHFJQMS3","short_pith_number":"pith:GMLYYDMC","schema_version":"1.0","canonical_sha256":"33178c0d824176d819ec121c72a60c96d7447948cdaf2dfc59ee903ec8a3e9e6","source":{"kind":"arxiv","id":"2410.11765","version":1},"attestation_state":"computed","paper":{"title":"ECGN: A Cluster-Aware Approach to Graph Neural Networks for Imbalanced Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anh Nguyen, Antonios Valkanas, Bilel Fehri, Bishal Thapaliya, Deepayan Chakraborty, Fudong Lin, Igor Grudetskyi, Jingyu Liu, Tian Xie, Yao Lu","submitted_at":"2024-10-15T16:39:38Z","abstract_excerpt":"Classifying nodes in a graph is a common problem. The ideal classifier must adapt to any imbalances in the class distribution. It must also use information in the clustering structure of real-world graphs. Existing Graph Neural Networks (GNNs) have not addressed both problems together. We propose the Enhanced Cluster-aware Graph Network (ECGN), a novel method that addresses these issues by integrating cluster-specific training with synthetic node generation. Unlike traditional GNNs that apply the same node update process for all nodes, ECGN learns different aggregations for different clusters."},"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":"2410.11765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T16:39:38Z","cross_cats_sorted":[],"title_canon_sha256":"356ea36bbcba7550f33c39c9ea593444356f6116751a80fd50578bf4f274f46b","abstract_canon_sha256":"36bb582c11f98db0a446f759768c47e704253bb2ed602d690067b43327cf1849"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:58.778154Z","signature_b64":"xJF3QSql6Wid69WNN9wF729YSh9jDyXH1U90AF/dVIy/wgInsnVUb2I0M7pH0knizyI0QwTUXXBfphfHnh/QDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33178c0d824176d819ec121c72a60c96d7447948cdaf2dfc59ee903ec8a3e9e6","last_reissued_at":"2026-07-05T09:20:58.777621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:58.777621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECGN: A Cluster-Aware Approach to Graph Neural Networks for Imbalanced Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anh Nguyen, Antonios Valkanas, Bilel Fehri, Bishal Thapaliya, Deepayan Chakraborty, Fudong Lin, Igor Grudetskyi, Jingyu Liu, Tian Xie, Yao Lu","submitted_at":"2024-10-15T16:39:38Z","abstract_excerpt":"Classifying nodes in a graph is a common problem. The ideal classifier must adapt to any imbalances in the class distribution. It must also use information in the clustering structure of real-world graphs. Existing Graph Neural Networks (GNNs) have not addressed both problems together. We propose the Enhanced Cluster-aware Graph Network (ECGN), a novel method that addresses these issues by integrating cluster-specific training with synthetic node generation. Unlike traditional GNNs that apply the same node update process for all nodes, ECGN learns different aggregations for different clusters."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11765","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/2410.11765/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":"2410.11765","created_at":"2026-07-05T09:20:58.777687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11765v1","created_at":"2026-07-05T09:20:58.777687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11765","created_at":"2026-07-05T09:20:58.777687+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMLYYDMCIF3N","created_at":"2026-07-05T09:20:58.777687+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMLYYDMCIF3NQGPM","created_at":"2026-07-05T09:20:58.777687+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMLYYDMC","created_at":"2026-07-05T09:20:58.777687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3","json":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3.json","graph_json":"https://pith.science/api/pith-number/GMLYYDMCIF3NQGPMCIOHFJQMS3/graph.json","events_json":"https://pith.science/api/pith-number/GMLYYDMCIF3NQGPMCIOHFJQMS3/events.json","paper":"https://pith.science/paper/GMLYYDMC"},"agent_actions":{"view_html":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3","download_json":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3.json","view_paper":"https://pith.science/paper/GMLYYDMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11765&json=true","fetch_graph":"https://pith.science/api/pith-number/GMLYYDMCIF3NQGPMCIOHFJQMS3/graph.json","fetch_events":"https://pith.science/api/pith-number/GMLYYDMCIF3NQGPMCIOHFJQMS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3/action/storage_attestation","attest_author":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3/action/author_attestation","sign_citation":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3/action/citation_signature","submit_replication":"https://pith.science/pith/GMLYYDMCIF3NQGPMCIOHFJQMS3/action/replication_record"}},"created_at":"2026-07-05T09:20:58.777687+00:00","updated_at":"2026-07-05T09:20:58.777687+00:00"}