{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JTQBIRFV6Z3QS7SJW653NNTD2N","short_pith_number":"pith:JTQBIRFV","schema_version":"1.0","canonical_sha256":"4ce01444b5f677097e49b7bbb6b663d35f3732e4cee38636e895ac303c5491cf","source":{"kind":"arxiv","id":"1904.04849","version":2},"attestation_state":"computed","paper":{"title":"Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthias Fey","submitted_at":"2019-04-09T18:02:54Z","abstract_excerpt":"We propose a dynamic neighborhood aggregation (DNA) procedure guided by (multi-head) attention for representation learning on graphs. In contrast to current graph neural networks which follow a simple neighborhood aggregation scheme, our DNA procedure allows for a selective and node-adaptive aggregation of neighboring embeddings of potentially differing locality. In order to avoid overfitting, we propose to control the channel-wise connections between input and output by making use of grouped linear projections. In a number of transductive node-classification experiments, we demonstrate the ef"},"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":"1904.04849","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-09T18:02:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8986446439cad3864f20526bdee183a9d4c4d9059628fff38d4629af2f6407db","abstract_canon_sha256":"0f70f78c0a63b1d18d087622ff70b3256b79465208206c124e068bec99d747cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:39.173734Z","signature_b64":"GQq/naw5OVQq0N+pHVF/VTD3dJWZwpAFVLRmJjrU4K5WRQui+n80i4mX24qylYLR3VsbJg2z9U8O2Aueq4THDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ce01444b5f677097e49b7bbb6b663d35f3732e4cee38636e895ac303c5491cf","last_reissued_at":"2026-05-17T23:48:39.173275Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:39.173275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthias Fey","submitted_at":"2019-04-09T18:02:54Z","abstract_excerpt":"We propose a dynamic neighborhood aggregation (DNA) procedure guided by (multi-head) attention for representation learning on graphs. In contrast to current graph neural networks which follow a simple neighborhood aggregation scheme, our DNA procedure allows for a selective and node-adaptive aggregation of neighboring embeddings of potentially differing locality. In order to avoid overfitting, we propose to control the channel-wise connections between input and output by making use of grouped linear projections. In a number of transductive node-classification experiments, we demonstrate the ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04849","kind":"arxiv","version":2},"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":"1904.04849","created_at":"2026-05-17T23:48:39.173356+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.04849v2","created_at":"2026-05-17T23:48:39.173356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04849","created_at":"2026-05-17T23:48:39.173356+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTQBIRFV6Z3Q","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTQBIRFV6Z3QS7SJ","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTQBIRFV","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10467","citing_title":"MGM: Global Understanding of Audience Overlap Graphs for Predicting the Factuality and the Bias of News Media","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N","json":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N.json","graph_json":"https://pith.science/api/pith-number/JTQBIRFV6Z3QS7SJW653NNTD2N/graph.json","events_json":"https://pith.science/api/pith-number/JTQBIRFV6Z3QS7SJW653NNTD2N/events.json","paper":"https://pith.science/paper/JTQBIRFV"},"agent_actions":{"view_html":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N","download_json":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N.json","view_paper":"https://pith.science/paper/JTQBIRFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.04849&json=true","fetch_graph":"https://pith.science/api/pith-number/JTQBIRFV6Z3QS7SJW653NNTD2N/graph.json","fetch_events":"https://pith.science/api/pith-number/JTQBIRFV6Z3QS7SJW653NNTD2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N/action/storage_attestation","attest_author":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N/action/author_attestation","sign_citation":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N/action/citation_signature","submit_replication":"https://pith.science/pith/JTQBIRFV6Z3QS7SJW653NNTD2N/action/replication_record"}},"created_at":"2026-05-17T23:48:39.173356+00:00","updated_at":"2026-05-17T23:48:39.173356+00:00"}