{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PDF6PV3RZNPK2KP2RRKSMZFEF5","short_pith_number":"pith:PDF6PV3R","schema_version":"1.0","canonical_sha256":"78cbe7d771cb5ead29fa8c552664a42f558ef03e34aa825aa3bbacdc26c618bc","source":{"kind":"arxiv","id":"1906.05488","version":1},"attestation_state":"computed","paper":{"title":"Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chang-Yu Hsieh, Guangyong Chen, Pengfei Chen, Shengyu Zhang, Weiwen Liu","submitted_at":"2019-06-13T05:36:56Z","abstract_excerpt":"Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during which parameterized transformation matrices should be learned for the node feature updating. However, existing propagation schemes are far from being optimal since they do not fully utilize the relational information between nodes. We propose the information maximizing graph neural networks (IGNN), which maximizes the mutual information between edge states and transform parameters. We reformulate the mutual information"},"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":"1906.05488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T05:36:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d48e0277eb56a397440ff4685d65df2ef671413cf95a499dd3b720f1d1fa1194","abstract_canon_sha256":"f0421be544740c49e91890cf7a88ce1000743131823661cb046131637d130817"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:25.240545Z","signature_b64":"wb3Y7XTf/ScUZSEcKjykQ6w1UqP1f+OCZdV/yLs7IqyzzKWL0s/jAO2zjU+d+TRxx4uGTLJu1HQowLm7MJZOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78cbe7d771cb5ead29fa8c552664a42f558ef03e34aa825aa3bbacdc26c618bc","last_reissued_at":"2026-05-17T23:43:25.240082Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:25.240082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chang-Yu Hsieh, Guangyong Chen, Pengfei Chen, Shengyu Zhang, Weiwen Liu","submitted_at":"2019-06-13T05:36:56Z","abstract_excerpt":"Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during which parameterized transformation matrices should be learned for the node feature updating. However, existing propagation schemes are far from being optimal since they do not fully utilize the relational information between nodes. We propose the information maximizing graph neural networks (IGNN), which maximizes the mutual information between edge states and transform parameters. We reformulate the mutual information"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05488","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":""},"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":"1906.05488","created_at":"2026-05-17T23:43:25.240160+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05488v1","created_at":"2026-05-17T23:43:25.240160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05488","created_at":"2026-05-17T23:43:25.240160+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDF6PV3RZNPK","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDF6PV3RZNPK2KP2","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDF6PV3R","created_at":"2026-05-18T12:33:24.271573+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/PDF6PV3RZNPK2KP2RRKSMZFEF5","json":"https://pith.science/pith/PDF6PV3RZNPK2KP2RRKSMZFEF5.json","graph_json":"https://pith.science/api/pith-number/PDF6PV3RZNPK2KP2RRKSMZFEF5/graph.json","events_json":"https://pith.science/api/pith-number/PDF6PV3RZNPK2KP2RRKSMZFEF5/events.json","paper":"https://pith.science/paper/PDF6PV3R"},"agent_actions":{"view_html":"https://pith.science/pith/PDF6PV3RZNPK2KP2RRKSMZFEF5","download_json":"https://pith.science/pith/PDF6PV3RZNPK2KP2RRKSMZFEF5.json","view_paper":"https://pith.science/paper/PDF6PV3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05488&json=true","fetch_graph":"https://pith.science/api/pith-number/PDF6PV3RZNPK2KP2RRKSMZFEF5/graph.json","fetch_events":"https://pith.science/api/pith-number/PDF6PV3RZNPK2KP2RRKSMZFEF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDF6PV3RZNPK2KP2RRKSMZFEF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDF6PV3RZNPK2KP2RRKSMZFEF5/action/storage_attestation","attest_author":"https://pith.science/pith/PDF6PV3RZNPK2KP2RRKSMZFEF5/action/author_attestation","sign_citation":"https://pith.science/pith/PDF6PV3RZNPK2KP2RRKSMZFEF5/action/citation_signature","submit_replication":"https://pith.science/pith/PDF6PV3RZNPK2KP2RRKSMZFEF5/action/replication_record"}},"created_at":"2026-05-17T23:43:25.240160+00:00","updated_at":"2026-05-17T23:43:25.240160+00:00"}