{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MI47VKV6IHWLGIUX34EAQRY7JZ","short_pith_number":"pith:MI47VKV6","schema_version":"1.0","canonical_sha256":"6239faaabe41ecb32297df0808471f4e5214bb333458ac9b9a4fc5464477ba0f","source":{"kind":"arxiv","id":"2001.01523","version":3},"attestation_state":"computed","paper":{"title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Brent, Liu Ziyin, Louis-Philippe Morency, Nicholas B. Allen, Paul Pu Liang, Randy P. Auerbach, Ruslan Salakhutdinov, Terrance Liu","submitted_at":"2020-01-06T12:40:21Z","abstract_excerpt":"Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges for large models. To this end, we propose a new federated learning algorithm that jointly learns compact local representations on each device and a global model across all devices. As a result, the global model can be smaller since it only operates on local representations, reducing the number of communicated parameters. Theoretically, we provide a generalizat"},"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":"2001.01523","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-06T12:40:21Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"e3355f293a5e993916cec27a218e6983868ebea7d267766f688c272e734763d3","abstract_canon_sha256":"b18448c49fd98ce893ed55470a4aa948a6d12cfcc06b8291a6bdc388bf294750"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:17.256841Z","signature_b64":"5YITq8oDdlYbN/3whJuqr9OqX0zPMxPmBBRC8m8McEmRdEDefw+QWIfGhl/U1UF8Z8dRz+GyZNt7Ms1+i2gUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6239faaabe41ecb32297df0808471f4e5214bb333458ac9b9a4fc5464477ba0f","last_reissued_at":"2026-07-05T01:18:17.256400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:17.256400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Brent, Liu Ziyin, Louis-Philippe Morency, Nicholas B. Allen, Paul Pu Liang, Randy P. Auerbach, Ruslan Salakhutdinov, Terrance Liu","submitted_at":"2020-01-06T12:40:21Z","abstract_excerpt":"Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges for large models. To this end, we propose a new federated learning algorithm that jointly learns compact local representations on each device and a global model across all devices. As a result, the global model can be smaller since it only operates on local representations, reducing the number of communicated parameters. Theoretically, we provide a generalizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.01523","kind":"arxiv","version":3},"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/2001.01523/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":"2001.01523","created_at":"2026-07-05T01:18:17.256461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.01523v3","created_at":"2026-07-05T01:18:17.256461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.01523","created_at":"2026-07-05T01:18:17.256461+00:00"},{"alias_kind":"pith_short_12","alias_value":"MI47VKV6IHWL","created_at":"2026-07-05T01:18:17.256461+00:00"},{"alias_kind":"pith_short_16","alias_value":"MI47VKV6IHWLGIUX","created_at":"2026-07-05T01:18:17.256461+00:00"},{"alias_kind":"pith_short_8","alias_value":"MI47VKV6","created_at":"2026-07-05T01:18:17.256461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10595","citing_title":"From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30615","citing_title":"Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22898","citing_title":"FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13543","citing_title":"Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21264","citing_title":"FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05959","citing_title":"From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07860","citing_title":"On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16574","citing_title":"FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ","json":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ.json","graph_json":"https://pith.science/api/pith-number/MI47VKV6IHWLGIUX34EAQRY7JZ/graph.json","events_json":"https://pith.science/api/pith-number/MI47VKV6IHWLGIUX34EAQRY7JZ/events.json","paper":"https://pith.science/paper/MI47VKV6"},"agent_actions":{"view_html":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ","download_json":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ.json","view_paper":"https://pith.science/paper/MI47VKV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.01523&json=true","fetch_graph":"https://pith.science/api/pith-number/MI47VKV6IHWLGIUX34EAQRY7JZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MI47VKV6IHWLGIUX34EAQRY7JZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ/action/storage_attestation","attest_author":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ/action/author_attestation","sign_citation":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ/action/citation_signature","submit_replication":"https://pith.science/pith/MI47VKV6IHWLGIUX34EAQRY7JZ/action/replication_record"}},"created_at":"2026-07-05T01:18:17.256461+00:00","updated_at":"2026-07-05T01:18:17.256461+00:00"}