{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GALHY4QY4LVUTZXAUH5DHAIFSL","short_pith_number":"pith:GALHY4QY","schema_version":"1.0","canonical_sha256":"30167c7218e2eb49e6e0a1fa33810592d03a6b16821b01132c19d32b73ee3271","source":{"kind":"arxiv","id":"2404.07532","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Federated Model Compression for Communication and Computation Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chengyu Xia, Danny H. K. Tsang, Vincent K. N. Lau","submitted_at":"2024-04-11T07:51:30Z","abstract_excerpt":"In this paper, we investigate Bayesian model compression in federated learning (FL) to construct sparse models that can achieve both communication and computation efficiencies. We propose a decentralized Turbo variational Bayesian inference (D-Turbo-VBI) FL framework where we firstly propose a hierarchical sparse prior to promote a clustered sparse structure in the weight matrix. Then, by carefully integrating message passing and VBI with a decentralized turbo framework, we propose the D-Turbo-VBI algorithm which can (i) reduce both upstream and downstream communication overhead during federat"},"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":"2404.07532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-11T07:51:30Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"2b04e5eeccfb7c7070e8eca8be3e5d447b13a30167a3a106b08560d6902ff751","abstract_canon_sha256":"e0075ecb9168f5e4290dfe03c0095799a382ed1d2dac7fab4f28325e289dd52e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:54.424125Z","signature_b64":"XXCMYQApGZlS+IaMAxNGFpdEa2uvDMN+TUoItF4Kyj4feYFApYUPeEztBIxowP28+BIZwtL90E3zMoqEWFouAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30167c7218e2eb49e6e0a1fa33810592d03a6b16821b01132c19d32b73ee3271","last_reissued_at":"2026-07-05T08:06:54.423725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:54.423725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Federated Model Compression for Communication and Computation Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chengyu Xia, Danny H. K. Tsang, Vincent K. N. Lau","submitted_at":"2024-04-11T07:51:30Z","abstract_excerpt":"In this paper, we investigate Bayesian model compression in federated learning (FL) to construct sparse models that can achieve both communication and computation efficiencies. We propose a decentralized Turbo variational Bayesian inference (D-Turbo-VBI) FL framework where we firstly propose a hierarchical sparse prior to promote a clustered sparse structure in the weight matrix. Then, by carefully integrating message passing and VBI with a decentralized turbo framework, we propose the D-Turbo-VBI algorithm which can (i) reduce both upstream and downstream communication overhead during federat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07532","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/2404.07532/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":"2404.07532","created_at":"2026-07-05T08:06:54.423788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07532v1","created_at":"2026-07-05T08:06:54.423788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07532","created_at":"2026-07-05T08:06:54.423788+00:00"},{"alias_kind":"pith_short_12","alias_value":"GALHY4QY4LVU","created_at":"2026-07-05T08:06:54.423788+00:00"},{"alias_kind":"pith_short_16","alias_value":"GALHY4QY4LVUTZXA","created_at":"2026-07-05T08:06:54.423788+00:00"},{"alias_kind":"pith_short_8","alias_value":"GALHY4QY","created_at":"2026-07-05T08:06:54.423788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20644","citing_title":"Efficient Federated Learning with Encrypted Data Sharing for Data-Heterogeneous Edge Devices","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL","json":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL.json","graph_json":"https://pith.science/api/pith-number/GALHY4QY4LVUTZXAUH5DHAIFSL/graph.json","events_json":"https://pith.science/api/pith-number/GALHY4QY4LVUTZXAUH5DHAIFSL/events.json","paper":"https://pith.science/paper/GALHY4QY"},"agent_actions":{"view_html":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL","download_json":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL.json","view_paper":"https://pith.science/paper/GALHY4QY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07532&json=true","fetch_graph":"https://pith.science/api/pith-number/GALHY4QY4LVUTZXAUH5DHAIFSL/graph.json","fetch_events":"https://pith.science/api/pith-number/GALHY4QY4LVUTZXAUH5DHAIFSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL/action/storage_attestation","attest_author":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL/action/author_attestation","sign_citation":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL/action/citation_signature","submit_replication":"https://pith.science/pith/GALHY4QY4LVUTZXAUH5DHAIFSL/action/replication_record"}},"created_at":"2026-07-05T08:06:54.423788+00:00","updated_at":"2026-07-05T08:06:54.423788+00:00"}