{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7DRD4IHSFGTMOF2LIA6GALVDYK","short_pith_number":"pith:7DRD4IHS","schema_version":"1.0","canonical_sha256":"f8e23e20f229a6c7174b403c602ea3c28006758e9f880ff32838eb4e41aec503","source":{"kind":"arxiv","id":"1803.07294","version":1},"attestation_state":"computed","paper":{"title":"GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Dit-Yan Yeung, Hao Ma, Irwin King, Jiani Zhang, Junyuan Xie, Xingjian Shi","submitted_at":"2018-03-20T08:33:20Z","abstract_excerpt":"We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head's importance. We demonstrate the effectiveness of GaAN on the inductive node classification problem. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting problem. Extensive experiments on three real-world datasets show that our GaAN framework achieves stat"},"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":"1803.07294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T08:33:20Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"e406e50a0484fa303a73db99731b80abb9b170055618b1c2814e83421495c577","abstract_canon_sha256":"a6cec209df914999cf5327b826b85f03c6586c4b8b44d842841ee3e972993720"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:33.717895Z","signature_b64":"5xILx2XmbbpBZv37fJVE2wfK6BEdD+HeTs8378T8unx1bvLBh8ExcQE7YlBFfHCbgZ9+fOiO3WPlfR4qWYawBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e23e20f229a6c7174b403c602ea3c28006758e9f880ff32838eb4e41aec503","last_reissued_at":"2026-05-18T00:20:33.717410Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:33.717410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Dit-Yan Yeung, Hao Ma, Irwin King, Jiani Zhang, Junyuan Xie, Xingjian Shi","submitted_at":"2018-03-20T08:33:20Z","abstract_excerpt":"We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head's importance. We demonstrate the effectiveness of GaAN on the inductive node classification problem. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting problem. Extensive experiments on three real-world datasets show that our GaAN framework achieves stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07294","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":"1803.07294","created_at":"2026-05-18T00:20:33.717484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.07294v1","created_at":"2026-05-18T00:20:33.717484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07294","created_at":"2026-05-18T00:20:33.717484+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DRD4IHSFGTM","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DRD4IHSFGTMOF2L","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DRD4IHS","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.12330","citing_title":"Graph Star Net for Generalized Multi-Task Learning","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23183","citing_title":"GMENet: Generative Mixture of Experts Network for Multi-Center Glioma Diagnosis with Incomplete Imaging Sequences","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16726","citing_title":"A Global-Local Graph Attention Network for Traffic Forecasting","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK","json":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK.json","graph_json":"https://pith.science/api/pith-number/7DRD4IHSFGTMOF2LIA6GALVDYK/graph.json","events_json":"https://pith.science/api/pith-number/7DRD4IHSFGTMOF2LIA6GALVDYK/events.json","paper":"https://pith.science/paper/7DRD4IHS"},"agent_actions":{"view_html":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK","download_json":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK.json","view_paper":"https://pith.science/paper/7DRD4IHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.07294&json=true","fetch_graph":"https://pith.science/api/pith-number/7DRD4IHSFGTMOF2LIA6GALVDYK/graph.json","fetch_events":"https://pith.science/api/pith-number/7DRD4IHSFGTMOF2LIA6GALVDYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK/action/storage_attestation","attest_author":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK/action/author_attestation","sign_citation":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK/action/citation_signature","submit_replication":"https://pith.science/pith/7DRD4IHSFGTMOF2LIA6GALVDYK/action/replication_record"}},"created_at":"2026-05-18T00:20:33.717484+00:00","updated_at":"2026-05-18T00:20:33.717484+00:00"}