{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:I2FWNRCYMQ4UBHLA4EWD5HUUJR","short_pith_number":"pith:I2FWNRCY","schema_version":"1.0","canonical_sha256":"468b66c4586439409d60e12c3e9e944c49ed72153ae3988855ae20d04c25e691","source":{"kind":"arxiv","id":"1803.10071","version":1},"attestation_state":"computed","paper":{"title":"Tensor graph convolutional neural network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"2), 2) ((1) the Department of Information Science, China), China (2) the Key Laboratory of Child Development, China (3) the School of Computer Science, Engineering, Learning Science of Ministry of Education, Nanjing, Nanjing University of science, Research Center for Learning Science, Southeast University, Technology, Tong Zhang (1, Wenming Zheng (2), Yang Li (1, Zhen Cui (3)","submitted_at":"2018-03-27T13:34:05Z","abstract_excerpt":"In this paper, we propose a novel tensor graph convolutional neural network (TGCNN) to conduct convolution on factorizable graphs, for which here two types of problems are focused, one is sequential dynamic graphs and the other is cross-attribute graphs. Especially, we propose a graph preserving layer to memorize salient nodes of those factorized subgraphs, i.e. cross graph convolution and graph pooling. For cross graph convolution, a parameterized Kronecker sum operation is proposed to generate a conjunctive adjacency matrix characterizing the relationship between every pair of nodes across t"},"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":"1803.10071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T13:34:05Z","cross_cats_sorted":[],"title_canon_sha256":"8024f9755e39afef49ec066016ccc2d286c1a69bbec985f7e63df5662c75db6d","abstract_canon_sha256":"68197e6f127ed04433aa101c42ac7d44b97f3c02287d9354a6dee6bca1be36b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:00.541298Z","signature_b64":"4Rto7S5b8HJ4kWUEhSPCPBpeBoHbjDte9okzz2Yn2hLXAuSJWcihUcRowWJ+UydSSu4UBuw80jnDzGXE+xYzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"468b66c4586439409d60e12c3e9e944c49ed72153ae3988855ae20d04c25e691","last_reissued_at":"2026-05-18T00:20:00.540761Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:00.540761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tensor graph convolutional neural network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"2), 2) ((1) the Department of Information Science, China), China (2) the Key Laboratory of Child Development, China (3) the School of Computer Science, Engineering, Learning Science of Ministry of Education, Nanjing, Nanjing University of science, Research Center for Learning Science, Southeast University, Technology, Tong Zhang (1, Wenming Zheng (2), Yang Li (1, Zhen Cui (3)","submitted_at":"2018-03-27T13:34:05Z","abstract_excerpt":"In this paper, we propose a novel tensor graph convolutional neural network (TGCNN) to conduct convolution on factorizable graphs, for which here two types of problems are focused, one is sequential dynamic graphs and the other is cross-attribute graphs. Especially, we propose a graph preserving layer to memorize salient nodes of those factorized subgraphs, i.e. cross graph convolution and graph pooling. For cross graph convolution, a parameterized Kronecker sum operation is proposed to generate a conjunctive adjacency matrix characterizing the relationship between every pair of nodes across t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10071","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":"1803.10071","created_at":"2026-05-18T00:20:00.540852+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10071v1","created_at":"2026-05-18T00:20:00.540852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10071","created_at":"2026-05-18T00:20:00.540852+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2FWNRCYMQ4U","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2FWNRCYMQ4UBHLA","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2FWNRCY","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13312","citing_title":"Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysis","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR","json":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR.json","graph_json":"https://pith.science/api/pith-number/I2FWNRCYMQ4UBHLA4EWD5HUUJR/graph.json","events_json":"https://pith.science/api/pith-number/I2FWNRCYMQ4UBHLA4EWD5HUUJR/events.json","paper":"https://pith.science/paper/I2FWNRCY"},"agent_actions":{"view_html":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR","download_json":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR.json","view_paper":"https://pith.science/paper/I2FWNRCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10071&json=true","fetch_graph":"https://pith.science/api/pith-number/I2FWNRCYMQ4UBHLA4EWD5HUUJR/graph.json","fetch_events":"https://pith.science/api/pith-number/I2FWNRCYMQ4UBHLA4EWD5HUUJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR/action/storage_attestation","attest_author":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR/action/author_attestation","sign_citation":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR/action/citation_signature","submit_replication":"https://pith.science/pith/I2FWNRCYMQ4UBHLA4EWD5HUUJR/action/replication_record"}},"created_at":"2026-05-18T00:20:00.540852+00:00","updated_at":"2026-05-18T00:20:00.540852+00:00"}