{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U5S667BGS7PVV6WCJ7WOGU7S6U","short_pith_number":"pith:U5S667BG","schema_version":"1.0","canonical_sha256":"a765ef7c2697df5afac24fece353f2f523957ccadb4315ee9f2d8c504d37bd36","source":{"kind":"arxiv","id":"2407.01607","version":1},"attestation_state":"computed","paper":{"title":"Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongying Kong, Han Li, Jian Liang, Kun Gai, Peng Jiang, Shuang Li, Zhaocheng Liu, Zhongxiang Fan","submitted_at":"2024-06-27T04:00:15Z","abstract_excerpt":"This paper investigates the one-epoch overfitting phenomenon in Click-Through Rate (CTR) models, where performance notably declines at the start of the second epoch. Despite extensive research, the efficacy of multi-epoch training over the conventional one-epoch approach remains unclear. We identify the overfitting of the embedding layer, caused by high-dimensional data sparsity, as the primary issue. To address this, we introduce a novel and simple Multi-Epoch learning with Data Augmentation (MEDA) framework, suitable for both non-continual and continual learning scenarios, which can be seaml"},"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":"2407.01607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-27T04:00:15Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"7f24c883834915aec65c12f37b17528e934cd180358a24c6fec68965f16d0189","abstract_canon_sha256":"561ee45c5a005460c35582e1a41ed58d4d468fa981e0117a00c5266161e5a0df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:02.729554Z","signature_b64":"C0zJRdhsqurYHV/zS5lcO3L+jH08rSG3CUK7bzSq5p5pw6a2asWeMz4HSthit4hzUfIc98hUTZrzpw0//6caBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a765ef7c2697df5afac24fece353f2f523957ccadb4315ee9f2d8c504d37bd36","last_reissued_at":"2026-07-05T08:39:02.729065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:02.729065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongying Kong, Han Li, Jian Liang, Kun Gai, Peng Jiang, Shuang Li, Zhaocheng Liu, Zhongxiang Fan","submitted_at":"2024-06-27T04:00:15Z","abstract_excerpt":"This paper investigates the one-epoch overfitting phenomenon in Click-Through Rate (CTR) models, where performance notably declines at the start of the second epoch. Despite extensive research, the efficacy of multi-epoch training over the conventional one-epoch approach remains unclear. We identify the overfitting of the embedding layer, caused by high-dimensional data sparsity, as the primary issue. To address this, we introduce a novel and simple Multi-Epoch learning with Data Augmentation (MEDA) framework, suitable for both non-continual and continual learning scenarios, which can be seaml"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01607","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/2407.01607/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":"2407.01607","created_at":"2026-07-05T08:39:02.729125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01607v1","created_at":"2026-07-05T08:39:02.729125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01607","created_at":"2026-07-05T08:39:02.729125+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5S667BGS7PV","created_at":"2026-07-05T08:39:02.729125+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5S667BGS7PVV6WC","created_at":"2026-07-05T08:39:02.729125+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5S667BG","created_at":"2026-07-05T08:39:02.729125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24051","citing_title":"Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U","json":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U.json","graph_json":"https://pith.science/api/pith-number/U5S667BGS7PVV6WCJ7WOGU7S6U/graph.json","events_json":"https://pith.science/api/pith-number/U5S667BGS7PVV6WCJ7WOGU7S6U/events.json","paper":"https://pith.science/paper/U5S667BG"},"agent_actions":{"view_html":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U","download_json":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U.json","view_paper":"https://pith.science/paper/U5S667BG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01607&json=true","fetch_graph":"https://pith.science/api/pith-number/U5S667BGS7PVV6WCJ7WOGU7S6U/graph.json","fetch_events":"https://pith.science/api/pith-number/U5S667BGS7PVV6WCJ7WOGU7S6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U/action/storage_attestation","attest_author":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U/action/author_attestation","sign_citation":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U/action/citation_signature","submit_replication":"https://pith.science/pith/U5S667BGS7PVV6WCJ7WOGU7S6U/action/replication_record"}},"created_at":"2026-07-05T08:39:02.729125+00:00","updated_at":"2026-07-05T08:39:02.729125+00:00"}