{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3XYIJU3NIZY3YBSLA5SLZ3NH7W","short_pith_number":"pith:3XYIJU3N","schema_version":"1.0","canonical_sha256":"ddf084d36d4671bc064b0764bceda7fdb4b9214e4cc6081920f52e5820f7fce5","source":{"kind":"arxiv","id":"1910.11945","version":1},"attestation_state":"computed","paper":{"title":"Improving Graph Attention Networks with Large Margin-based Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guangtao Wang, Jing Huang, Jure Leskovec, Rex Ying","submitted_at":"2019-10-25T21:24:00Z","abstract_excerpt":"Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the feature aggregation steps. In practice, however, induced attention functions are prone to over-fitting due to the increasing number of parameters and the lack of direct supervision on attention weights. GATs also suffer from over-smoothing at the decision boundary of nodes. Here we propose a framework to address their weaknesses via margin-based constraints on at"},"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":"1910.11945","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-25T21:24:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c1e4de9129c13df006d487d17508495a2bc590bfe95be61b1ba4321206f83e11","abstract_canon_sha256":"306c9b50820da67f1c41316094a4527ccd5989947802fac11227dec81b0aa060"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:11.260786Z","signature_b64":"Sv+LVpCEQ6v7q5M7gFo4QX9wUNyN+6+K6GHOgRfp1lmT2pTAoJus1540/VxOUdGtiXLhaW6swmEuSqt6p6x7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddf084d36d4671bc064b0764bceda7fdb4b9214e4cc6081920f52e5820f7fce5","last_reissued_at":"2026-07-05T00:15:11.260328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:11.260328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Graph Attention Networks with Large Margin-based Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guangtao Wang, Jing Huang, Jure Leskovec, Rex Ying","submitted_at":"2019-10-25T21:24:00Z","abstract_excerpt":"Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the feature aggregation steps. In practice, however, induced attention functions are prone to over-fitting due to the increasing number of parameters and the lack of direct supervision on attention weights. GATs also suffer from over-smoothing at the decision boundary of nodes. Here we propose a framework to address their weaknesses via margin-based constraints on at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.11945","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/1910.11945/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":"1910.11945","created_at":"2026-07-05T00:15:11.260383+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.11945v1","created_at":"2026-07-05T00:15:11.260383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.11945","created_at":"2026-07-05T00:15:11.260383+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XYIJU3NIZY3","created_at":"2026-07-05T00:15:11.260383+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XYIJU3NIZY3YBSL","created_at":"2026-07-05T00:15:11.260383+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XYIJU3N","created_at":"2026-07-05T00:15:11.260383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2105.14491","citing_title":"How Attentive are Graph Attention Networks?","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08679","citing_title":"Attention-based graph neural networks: a survey","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W","json":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W.json","graph_json":"https://pith.science/api/pith-number/3XYIJU3NIZY3YBSLA5SLZ3NH7W/graph.json","events_json":"https://pith.science/api/pith-number/3XYIJU3NIZY3YBSLA5SLZ3NH7W/events.json","paper":"https://pith.science/paper/3XYIJU3N"},"agent_actions":{"view_html":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W","download_json":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W.json","view_paper":"https://pith.science/paper/3XYIJU3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.11945&json=true","fetch_graph":"https://pith.science/api/pith-number/3XYIJU3NIZY3YBSLA5SLZ3NH7W/graph.json","fetch_events":"https://pith.science/api/pith-number/3XYIJU3NIZY3YBSLA5SLZ3NH7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W/action/storage_attestation","attest_author":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W/action/author_attestation","sign_citation":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W/action/citation_signature","submit_replication":"https://pith.science/pith/3XYIJU3NIZY3YBSLA5SLZ3NH7W/action/replication_record"}},"created_at":"2026-07-05T00:15:11.260383+00:00","updated_at":"2026-07-05T00:15:11.260383+00:00"}