{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:E5K3DVSVM4URWZCQJONLLOQHUG","short_pith_number":"pith:E5K3DVSV","schema_version":"1.0","canonical_sha256":"2755b1d65567291b64504b9ab5ba07a1b794b8f7ed27186cc2c5e9569b9ba47a","source":{"kind":"arxiv","id":"1910.07796","version":1},"attestation_state":"computed","paper":{"title":"Overcoming Forgetting in Federated Learning on Non-IID Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Keren (Edgify), Daniel Benditkis (Edgify), Itai Zeitak (Edgify), Liron Mor-Yosef (Edgify), Nadav Israel (Edgify), Neta Shoham (Edgify), Tomer Avidor (Edgify)","submitted_at":"2019-10-17T09:53:16Z","abstract_excerpt":"We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt a solution for catastrophic forgetting to Federated Learning. We add a penalty term to the loss function, compelling all local models to converge to a shared optimum. We show that this can be done efficiently for communication (adding no further privacy risks), scaling with the number of nodes in the distributed setting. Our experiments show that this method is superior to competing ones for image recognition on the "},"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":"1910.07796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-17T09:53:16Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"8839508bbde3fac7ee1c695a0c15ceaa32b2da60a7dbb99efd36eb582bd24a7c","abstract_canon_sha256":"86f68384df24c7dfb53f7b6c2fc945ab17e14797f428c3e59f1629b05b81d7c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:56.055390Z","signature_b64":"IEPIJHMfciEb3PTqyRpFevrUmUBjKR+MTiszOIbo2qOv2XN0+ShrFY1GNQ6JuvUb8fYSMEnGkc2QSGTUGzQTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2755b1d65567291b64504b9ab5ba07a1b794b8f7ed27186cc2c5e9569b9ba47a","last_reissued_at":"2026-07-05T00:12:56.054981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:56.054981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Forgetting in Federated Learning on Non-IID Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviv Keren (Edgify), Daniel Benditkis (Edgify), Itai Zeitak (Edgify), Liron Mor-Yosef (Edgify), Nadav Israel (Edgify), Neta Shoham (Edgify), Tomer Avidor (Edgify)","submitted_at":"2019-10-17T09:53:16Z","abstract_excerpt":"We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt a solution for catastrophic forgetting to Federated Learning. We add a penalty term to the loss function, compelling all local models to converge to a shared optimum. We show that this can be done efficiently for communication (adding no further privacy risks), scaling with the number of nodes in the distributed setting. Our experiments show that this method is superior to competing ones for image recognition on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07796","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/1910.07796/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":"1910.07796","created_at":"2026-07-05T00:12:56.055043+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.07796v1","created_at":"2026-07-05T00:12:56.055043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07796","created_at":"2026-07-05T00:12:56.055043+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5K3DVSVM4UR","created_at":"2026-07-05T00:12:56.055043+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5K3DVSVM4URWZCQ","created_at":"2026-07-05T00:12:56.055043+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5K3DVSV","created_at":"2026-07-05T00:12:56.055043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08219","citing_title":"Benchmark Evaluation of Federated Learning on Multi-organ Images","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28024","citing_title":"FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00698","citing_title":"FedKPer: Tackling Generalization and Personalization in Medical Federated Learning via Knowledge Personalization","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG","json":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG.json","graph_json":"https://pith.science/api/pith-number/E5K3DVSVM4URWZCQJONLLOQHUG/graph.json","events_json":"https://pith.science/api/pith-number/E5K3DVSVM4URWZCQJONLLOQHUG/events.json","paper":"https://pith.science/paper/E5K3DVSV"},"agent_actions":{"view_html":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG","download_json":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG.json","view_paper":"https://pith.science/paper/E5K3DVSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.07796&json=true","fetch_graph":"https://pith.science/api/pith-number/E5K3DVSVM4URWZCQJONLLOQHUG/graph.json","fetch_events":"https://pith.science/api/pith-number/E5K3DVSVM4URWZCQJONLLOQHUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG/action/storage_attestation","attest_author":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG/action/author_attestation","sign_citation":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG/action/citation_signature","submit_replication":"https://pith.science/pith/E5K3DVSVM4URWZCQJONLLOQHUG/action/replication_record"}},"created_at":"2026-07-05T00:12:56.055043+00:00","updated_at":"2026-07-05T00:12:56.055043+00:00"}