{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:S5B5FQV34QJM4KPOQJJHMRLCHR","short_pith_number":"pith:S5B5FQV3","schema_version":"1.0","canonical_sha256":"9743d2c2bbe412ce29ee82527645623c4a62f2afeec2b59ca8040a64a070b304","source":{"kind":"arxiv","id":"2107.11666","version":1},"attestation_state":"computed","paper":{"title":"Graph Convolutional Network with Generalized Factorized Bilinear Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hao Zhu, Piotr Koniusz","submitted_at":"2021-07-24T17:57:06Z","abstract_excerpt":"Although Graph Convolutional Networks (GCNs) have demonstrated their power in various applications, the graph convolutional layers, as the most important component of GCN, are still using linear transformations and a simple pooling step. In this paper, we propose a novel generalization of Factorized Bilinear (FB) layer to model the feature interactions in GCNs. FB performs two matrix-vector multiplications, that is, the weight matrix is multiplied with the outer product of the vector of hidden features from both sides. However, the FB layer suffers from the quadratic number of coefficients, ov"},"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":"2107.11666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-24T17:57:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1171eaac527a4932f44a015b9aca49375481b10387c3befec267afdf65854a7e","abstract_canon_sha256":"722c70a648f0abadbd2d0690b96f09d30606f2b5c0998f8940d664ad6b7d7fdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:36.071934Z","signature_b64":"DVfZB8ywjxcKc+0+8Tcqik/+a8I8b7t6+MBDFbmt6b4tNKbCvkCaPi8AnN+ozIomFsAAUKyTXbJBtwrQoxyZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9743d2c2bbe412ce29ee82527645623c4a62f2afeec2b59ca8040a64a070b304","last_reissued_at":"2026-07-05T03:00:36.071523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:36.071523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Convolutional Network with Generalized Factorized Bilinear Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hao Zhu, Piotr Koniusz","submitted_at":"2021-07-24T17:57:06Z","abstract_excerpt":"Although Graph Convolutional Networks (GCNs) have demonstrated their power in various applications, the graph convolutional layers, as the most important component of GCN, are still using linear transformations and a simple pooling step. In this paper, we propose a novel generalization of Factorized Bilinear (FB) layer to model the feature interactions in GCNs. FB performs two matrix-vector multiplications, that is, the weight matrix is multiplied with the outer product of the vector of hidden features from both sides. However, the FB layer suffers from the quadratic number of coefficients, ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11666","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/2107.11666/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":"2107.11666","created_at":"2026-07-05T03:00:36.071579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.11666v1","created_at":"2026-07-05T03:00:36.071579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11666","created_at":"2026-07-05T03:00:36.071579+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5B5FQV34QJM","created_at":"2026-07-05T03:00:36.071579+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5B5FQV34QJM4KPO","created_at":"2026-07-05T03:00:36.071579+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5B5FQV3","created_at":"2026-07-05T03:00:36.071579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07731","citing_title":"HyperQuery: Beyond Binary Link Prediction","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR","json":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR.json","graph_json":"https://pith.science/api/pith-number/S5B5FQV34QJM4KPOQJJHMRLCHR/graph.json","events_json":"https://pith.science/api/pith-number/S5B5FQV34QJM4KPOQJJHMRLCHR/events.json","paper":"https://pith.science/paper/S5B5FQV3"},"agent_actions":{"view_html":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR","download_json":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR.json","view_paper":"https://pith.science/paper/S5B5FQV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.11666&json=true","fetch_graph":"https://pith.science/api/pith-number/S5B5FQV34QJM4KPOQJJHMRLCHR/graph.json","fetch_events":"https://pith.science/api/pith-number/S5B5FQV34QJM4KPOQJJHMRLCHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR/action/storage_attestation","attest_author":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR/action/author_attestation","sign_citation":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR/action/citation_signature","submit_replication":"https://pith.science/pith/S5B5FQV34QJM4KPOQJJHMRLCHR/action/replication_record"}},"created_at":"2026-07-05T03:00:36.071579+00:00","updated_at":"2026-07-05T03:00:36.071579+00:00"}