{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TOXKP3RY632LLSEVHAXXICTRE7","short_pith_number":"pith:TOXKP3RY","schema_version":"1.0","canonical_sha256":"9baea7ee38f6f4b5c895382f740a7127df3f8a5c5cb081f8b6e4e324a50356e8","source":{"kind":"arxiv","id":"1911.08795","version":1},"attestation_state":"computed","paper":{"title":"On Node Features for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Thang Duong, Ha The Hien Dang, Karl Aberer, Quoc Viet Hung Nguyen, Thanh Dat Hoang","submitted_at":"2019-11-20T10:02:19Z","abstract_excerpt":"Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-a"},"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":"1911.08795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T10:02:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d66a95c00b87eff951f44b9cc60a097cdab13ee7fb462ca3d7a022a10038ac4e","abstract_canon_sha256":"0b38435f49c10180588d3acb0b9d0d1dfa4d4ecd0a3e34a69beb146170ca617d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:45.764004Z","signature_b64":"GB1cUNr/0TSUPKWccPUvE8DdlWeOR9vGddxKDshYZvoZCDHUnkoWf9EBlrTqIS4QZcWb2yspzHPzGcIJdC9lCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9baea7ee38f6f4b5c895382f740a7127df3f8a5c5cb081f8b6e4e324a50356e8","last_reissued_at":"2026-07-05T00:20:45.763549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:45.763549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Node Features for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Thang Duong, Ha The Hien Dang, Karl Aberer, Quoc Viet Hung Nguyen, Thanh Dat Hoang","submitted_at":"2019-11-20T10:02:19Z","abstract_excerpt":"Graph neural network (GNN) is a deep model for graph representation learning. One advantage of graph neural network is its ability to incorporate node features into the learning process. However, this prevents graph neural network from being applied into featureless graphs. In this paper, we first analyze the effects of node features on the performance of graph neural network. We show that GNNs work well if there is a strong correlation between node features and node labels. Based on these results, we propose new feature initialization methods that allows to apply graph neural network to non-a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08795","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/1911.08795/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":"1911.08795","created_at":"2026-07-05T00:20:45.763619+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.08795v1","created_at":"2026-07-05T00:20:45.763619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08795","created_at":"2026-07-05T00:20:45.763619+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOXKP3RY632L","created_at":"2026-07-05T00:20:45.763619+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOXKP3RY632LLSEV","created_at":"2026-07-05T00:20:45.763619+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOXKP3RY","created_at":"2026-07-05T00:20:45.763619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05046","citing_title":"Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07788","citing_title":"Bridging the Programming Language Gap: Constructing a Multilingual Shared Semantic Space through AST Unification and Graph Matching","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7","json":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7.json","graph_json":"https://pith.science/api/pith-number/TOXKP3RY632LLSEVHAXXICTRE7/graph.json","events_json":"https://pith.science/api/pith-number/TOXKP3RY632LLSEVHAXXICTRE7/events.json","paper":"https://pith.science/paper/TOXKP3RY"},"agent_actions":{"view_html":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7","download_json":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7.json","view_paper":"https://pith.science/paper/TOXKP3RY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.08795&json=true","fetch_graph":"https://pith.science/api/pith-number/TOXKP3RY632LLSEVHAXXICTRE7/graph.json","fetch_events":"https://pith.science/api/pith-number/TOXKP3RY632LLSEVHAXXICTRE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7/action/storage_attestation","attest_author":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7/action/author_attestation","sign_citation":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7/action/citation_signature","submit_replication":"https://pith.science/pith/TOXKP3RY632LLSEVHAXXICTRE7/action/replication_record"}},"created_at":"2026-07-05T00:20:45.763619+00:00","updated_at":"2026-07-05T00:20:45.763619+00:00"}