{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3QKJ7JWVPC42WX4KRLFXZ7KNF2","short_pith_number":"pith:3QKJ7JWV","schema_version":"1.0","canonical_sha256":"dc149fa6d578b9ab5f8a8acb7cfd4d2e96f314c433c6230045bb0e41ff137663","source":{"kind":"arxiv","id":"1710.09599","version":2},"attestation_state":"computed","paper":{"title":"Watch Your Step: Learning Node Embeddings via Graph Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Alemi, Bryan Perozzi, Rami Al-Rfou, Sami Abu-el-haija","submitted_at":"2017-10-26T09:10:01Z","abstract_excerpt":"Graph embedding methods represent nodes in a continuous vector space, preserving information from the graph (e.g. by sampling random walks). There are many hyper-parameters to these methods (such as random walk length) which have to be manually tuned for every graph. In this paper, we replace random walk hyper-parameters with trainable parameters that we automatically learn via backpropagation. In particular, we learn a novel attention model on the power series of the transition matrix, which guides the random walk to optimize an upstream objective. Unlike previous approaches to attention mode"},"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":"1710.09599","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-26T09:10:01Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"4b5daa9a12dd32a0f12acff00acf0b548eb2722da1134f53c8015f955fb2e258","abstract_canon_sha256":"f07817cb2ba7fbd8ca814fd5b903b0a48854a655d8e610785b26751f59ed4125"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:32.521690Z","signature_b64":"u5gisQD2taf+6HMd0p6ddQSAvezjcyJbJiklTHFa2ByCOez1urYdxQlY1Yixvm3SpeCOyAuRgfVVakp9NejYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc149fa6d578b9ab5f8a8acb7cfd4d2e96f314c433c6230045bb0e41ff137663","last_reissued_at":"2026-05-17T23:57:32.521192Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:32.521192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watch Your Step: Learning Node Embeddings via Graph Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Alemi, Bryan Perozzi, Rami Al-Rfou, Sami Abu-el-haija","submitted_at":"2017-10-26T09:10:01Z","abstract_excerpt":"Graph embedding methods represent nodes in a continuous vector space, preserving information from the graph (e.g. by sampling random walks). There are many hyper-parameters to these methods (such as random walk length) which have to be manually tuned for every graph. In this paper, we replace random walk hyper-parameters with trainable parameters that we automatically learn via backpropagation. In particular, we learn a novel attention model on the power series of the transition matrix, which guides the random walk to optimize an upstream objective. Unlike previous approaches to attention mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.09599","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":"1710.09599","created_at":"2026-05-17T23:57:32.521259+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.09599v2","created_at":"2026-05-17T23:57:32.521259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.09599","created_at":"2026-05-17T23:57:32.521259+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QKJ7JWVPC42","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QKJ7JWVPC42WX4K","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QKJ7JWV","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2","json":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2.json","graph_json":"https://pith.science/api/pith-number/3QKJ7JWVPC42WX4KRLFXZ7KNF2/graph.json","events_json":"https://pith.science/api/pith-number/3QKJ7JWVPC42WX4KRLFXZ7KNF2/events.json","paper":"https://pith.science/paper/3QKJ7JWV"},"agent_actions":{"view_html":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2","download_json":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2.json","view_paper":"https://pith.science/paper/3QKJ7JWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.09599&json=true","fetch_graph":"https://pith.science/api/pith-number/3QKJ7JWVPC42WX4KRLFXZ7KNF2/graph.json","fetch_events":"https://pith.science/api/pith-number/3QKJ7JWVPC42WX4KRLFXZ7KNF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2/action/storage_attestation","attest_author":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2/action/author_attestation","sign_citation":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2/action/citation_signature","submit_replication":"https://pith.science/pith/3QKJ7JWVPC42WX4KRLFXZ7KNF2/action/replication_record"}},"created_at":"2026-05-17T23:57:32.521259+00:00","updated_at":"2026-05-17T23:57:32.521259+00:00"}