{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZRNS6RBY4FFH6WRIICOYFEGZFL","short_pith_number":"pith:ZRNS6RBY","schema_version":"1.0","canonical_sha256":"cc5b2f4438e14a7f5a28409d8290d92afb2dba80b249b75db09c5d70032d1a26","source":{"kind":"arxiv","id":"1711.05697","version":4},"attestation_state":"computed","paper":{"title":"Motif-based Convolutional Neural Network on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Aravind Sankar, Kevin Chen-Chuan Chang, Xinyang Zhang","submitted_at":"2017-11-15T17:48:35Z","abstract_excerpt":"This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to model the key properties of local connectivity and translation invariance, using high-order connection patterns or motifs. We develop a novel deep architecture Motif-CNN that employs an attention model to combine the features extracted from multiple patterns, thus effectively capturing high-order structural and feature information. Our experiments on semi-supe"},"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":"1711.05697","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-15T17:48:35Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"b8fbcf5604b62482b1e61817074e5cbd7273a40c3a65c8585996c991eb754921","abstract_canon_sha256":"ee15537dc814b6750507bbb55a18cbb5397c4d73d22139de0e8e791c47fead37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:04.703724Z","signature_b64":"iA5M7GZkGHKhaXilk/vrBA1MaiWPhu2JnR7zVCo4WaSpCKHh7DtGQbYw+oTBI9RoPDXgcDvFb/Y2La7IKO49Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc5b2f4438e14a7f5a28409d8290d92afb2dba80b249b75db09c5d70032d1a26","last_reissued_at":"2026-05-17T23:40:04.703105Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:04.703105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motif-based Convolutional Neural Network on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Aravind Sankar, Kevin Chen-Chuan Chang, Xinyang Zhang","submitted_at":"2017-11-15T17:48:35Z","abstract_excerpt":"This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to model the key properties of local connectivity and translation invariance, using high-order connection patterns or motifs. We develop a novel deep architecture Motif-CNN that employs an attention model to combine the features extracted from multiple patterns, thus effectively capturing high-order structural and feature information. Our experiments on semi-supe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05697","kind":"arxiv","version":4},"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":"1711.05697","created_at":"2026-05-17T23:40:04.703199+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.05697v4","created_at":"2026-05-17T23:40:04.703199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05697","created_at":"2026-05-17T23:40:04.703199+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRNS6RBY4FFH","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRNS6RBY4FFH6WRI","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRNS6RBY","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.05387","citing_title":"HONEM: Learning Embedding for Higher Order Networks","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL","json":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL.json","graph_json":"https://pith.science/api/pith-number/ZRNS6RBY4FFH6WRIICOYFEGZFL/graph.json","events_json":"https://pith.science/api/pith-number/ZRNS6RBY4FFH6WRIICOYFEGZFL/events.json","paper":"https://pith.science/paper/ZRNS6RBY"},"agent_actions":{"view_html":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL","download_json":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL.json","view_paper":"https://pith.science/paper/ZRNS6RBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.05697&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRNS6RBY4FFH6WRIICOYFEGZFL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRNS6RBY4FFH6WRIICOYFEGZFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL/action/storage_attestation","attest_author":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL/action/author_attestation","sign_citation":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL/action/citation_signature","submit_replication":"https://pith.science/pith/ZRNS6RBY4FFH6WRIICOYFEGZFL/action/replication_record"}},"created_at":"2026-05-17T23:40:04.703199+00:00","updated_at":"2026-05-17T23:40:04.703199+00:00"}