{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2HR5IRXANK7W7DB2NABCHKV2AA","short_pith_number":"pith:2HR5IRXA","schema_version":"1.0","canonical_sha256":"d1e3d446e06abf6f8c3a680223aaba001ac67bcbc059f808f7ac04c4c1e20eeb","source":{"kind":"arxiv","id":"1812.07210","version":2},"attestation_state":"computed","paper":{"title":"Expanding the Reach of Federated Learning by Reducing Client Resource Requirements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, H. Brendan McMahan, Jakub Kone\\v{c}n\\`y, Sebastian Caldas","submitted_at":"2018-12-18T07:31:18Z","abstract_excerpt":"Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue, we introduce two novel strategies to reduce communication costs: (1) the use of lossy compression on the global model sent server-to-client; and (2) Federated Dropout, which allows users to efficiently train locally on smaller subsets of the global model and also provides a reduction in both client-to-server communication and local computation. We empirically show that these strategies, combined with existing compres"},"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":"1812.07210","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-18T07:31:18Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"fa4260abfa792d43a096a1f097464b08b82cabf2e0b1c24129f6a2f4e3ae5a8c","abstract_canon_sha256":"518dc540c0e65c5c73b3afc55a8412c8dc6f0a7a407853d27f73e068ba9b1df2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:44.510920Z","signature_b64":"ch2UAmIDmA0qNW3j/80q/PY77PT1RgfvnApNfPYpFQRN+lMpcTLmoNJgBJ4I+ocjLrEJWO42hsy6dL9GVrw5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1e3d446e06abf6f8c3a680223aaba001ac67bcbc059f808f7ac04c4c1e20eeb","last_reissued_at":"2026-05-17T23:56:44.510557Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:44.510557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expanding the Reach of Federated Learning by Reducing Client Resource Requirements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameet Talwalkar, H. Brendan McMahan, Jakub Kone\\v{c}n\\`y, Sebastian Caldas","submitted_at":"2018-12-18T07:31:18Z","abstract_excerpt":"Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue, we introduce two novel strategies to reduce communication costs: (1) the use of lossy compression on the global model sent server-to-client; and (2) Federated Dropout, which allows users to efficiently train locally on smaller subsets of the global model and also provides a reduction in both client-to-server communication and local computation. We empirically show that these strategies, combined with existing compres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07210","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":"1812.07210","created_at":"2026-05-17T23:56:44.510614+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07210v2","created_at":"2026-05-17T23:56:44.510614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07210","created_at":"2026-05-17T23:56:44.510614+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HR5IRXANK7W","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HR5IRXANK7W7DB2","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HR5IRXA","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.12022","citing_title":"DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23426","citing_title":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06014","citing_title":"Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11278","citing_title":"Representation-Aligned Multi-Scale Personalization for Federated Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA","json":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA.json","graph_json":"https://pith.science/api/pith-number/2HR5IRXANK7W7DB2NABCHKV2AA/graph.json","events_json":"https://pith.science/api/pith-number/2HR5IRXANK7W7DB2NABCHKV2AA/events.json","paper":"https://pith.science/paper/2HR5IRXA"},"agent_actions":{"view_html":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA","download_json":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA.json","view_paper":"https://pith.science/paper/2HR5IRXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07210&json=true","fetch_graph":"https://pith.science/api/pith-number/2HR5IRXANK7W7DB2NABCHKV2AA/graph.json","fetch_events":"https://pith.science/api/pith-number/2HR5IRXANK7W7DB2NABCHKV2AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA/action/storage_attestation","attest_author":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA/action/author_attestation","sign_citation":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA/action/citation_signature","submit_replication":"https://pith.science/pith/2HR5IRXANK7W7DB2NABCHKV2AA/action/replication_record"}},"created_at":"2026-05-17T23:56:44.510614+00:00","updated_at":"2026-05-17T23:56:44.510614+00:00"}