{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YW7VZQKWUIHJO4LL7L52IPZHKP","short_pith_number":"pith:YW7VZQKW","schema_version":"1.0","canonical_sha256":"c5bf5cc156a20e97716bfafba43f2753e8168c1a789622a0b49586c3f704e5f6","source":{"kind":"arxiv","id":"2405.13365","version":2},"attestation_state":"computed","paper":{"title":"Communication-Efficient Federated Learning via Clipped Uniform Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA","eess.SP"],"primary_cat":"cs.LG","authors_text":"Hao Chen, Zavareh Bozorgasl","submitted_at":"2024-05-22T05:48:25Z","abstract_excerpt":"This paper presents a novel approach to enhance communication efficiency in federated learning through clipped uniform quantization. By leveraging optimal clipping thresholds and client-specific adaptive quantization schemes, the proposed method significantly reduces bandwidth and memory requirements for model weight transmission between clients and the server while maintaining competitive accuracy. We investigate the effects of symmetric clipping and uniform quantization on model performance, emphasizing the role of stochastic quantization in mitigating artifacts and improving robustness. Ext"},"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":"2405.13365","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T05:48:25Z","cross_cats_sorted":["cs.MA","eess.SP"],"title_canon_sha256":"aebab11fbfcbe244a86b984411d453b69b2ecfd140fd70c4396327e87ed7d920","abstract_canon_sha256":"c1e293d9d85f5300925cd59f613b5d3fce68a6bd712919360cc89f79dbe05ed1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:05.181028Z","signature_b64":"fOzFWUBU4Yc9Qo+bCDhxg8Y6Iai6mlq3ou9rtjOKZMskuvnAx3e/pZ82GM+MzWLUnM9HPGNAenVlwTNLpmEUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5bf5cc156a20e97716bfafba43f2753e8168c1a789622a0b49586c3f704e5f6","last_reissued_at":"2026-07-05T09:49:05.180554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:05.180554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Efficient Federated Learning via Clipped Uniform Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA","eess.SP"],"primary_cat":"cs.LG","authors_text":"Hao Chen, Zavareh Bozorgasl","submitted_at":"2024-05-22T05:48:25Z","abstract_excerpt":"This paper presents a novel approach to enhance communication efficiency in federated learning through clipped uniform quantization. By leveraging optimal clipping thresholds and client-specific adaptive quantization schemes, the proposed method significantly reduces bandwidth and memory requirements for model weight transmission between clients and the server while maintaining competitive accuracy. We investigate the effects of symmetric clipping and uniform quantization on model performance, emphasizing the role of stochastic quantization in mitigating artifacts and improving robustness. Ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13365","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.13365/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":"2405.13365","created_at":"2026-07-05T09:49:05.180616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13365v2","created_at":"2026-07-05T09:49:05.180616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13365","created_at":"2026-07-05T09:49:05.180616+00:00"},{"alias_kind":"pith_short_12","alias_value":"YW7VZQKWUIHJ","created_at":"2026-07-05T09:49:05.180616+00:00"},{"alias_kind":"pith_short_16","alias_value":"YW7VZQKWUIHJO4LL","created_at":"2026-07-05T09:49:05.180616+00:00"},{"alias_kind":"pith_short_8","alias_value":"YW7VZQKW","created_at":"2026-07-05T09:49:05.180616+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04244","citing_title":"Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP","json":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP.json","graph_json":"https://pith.science/api/pith-number/YW7VZQKWUIHJO4LL7L52IPZHKP/graph.json","events_json":"https://pith.science/api/pith-number/YW7VZQKWUIHJO4LL7L52IPZHKP/events.json","paper":"https://pith.science/paper/YW7VZQKW"},"agent_actions":{"view_html":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP","download_json":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP.json","view_paper":"https://pith.science/paper/YW7VZQKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13365&json=true","fetch_graph":"https://pith.science/api/pith-number/YW7VZQKWUIHJO4LL7L52IPZHKP/graph.json","fetch_events":"https://pith.science/api/pith-number/YW7VZQKWUIHJO4LL7L52IPZHKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP/action/storage_attestation","attest_author":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP/action/author_attestation","sign_citation":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP/action/citation_signature","submit_replication":"https://pith.science/pith/YW7VZQKWUIHJO4LL7L52IPZHKP/action/replication_record"}},"created_at":"2026-07-05T09:49:05.180616+00:00","updated_at":"2026-07-05T09:49:05.180616+00:00"}