{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:57WE2XVKNFQXTUSFIY2627QKHG","short_pith_number":"pith:57WE2XVK","schema_version":"1.0","canonical_sha256":"efec4d5eaa696179d2454635ed7e0a39aa0477ba4170eae5382a45cb146c5035","source":{"kind":"arxiv","id":"2403.14737","version":1},"attestation_state":"computed","paper":{"title":"FedMef: Towards Memory-efficient Federated Dynamic Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Hong Huang, Lingjuan Lyu, Weiming Zhuang","submitted_at":"2024-03-21T13:54:36Z","abstract_excerpt":"Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However, its application on resource-constrained devices is challenging due to the high demand for computation and memory resources to train deep learning models. Neural network pruning techniques, such as dynamic pruning, could enhance model efficiency, but directly adopting them in FL still poses substantial challenges, including post-pruning performance degradation, high activation memory usage, etc. To address these challenges, we propose FedMef, a novel and memory-efficient federated dynamic p"},"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":"2403.14737","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T13:54:36Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"fccd8d200f4a47f0c5c2e74170256005724c2924e66c2d3edcd7e806039561dd","abstract_canon_sha256":"43f01ca7668b33fe307ffbb2501d713de71176d0db1ed2640a3c3f7affa09195"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:25.384265Z","signature_b64":"uV3vQcqg5XCiPL3Sw8y6iObEfSuT1ogDoL0P6+L43CyN4qmRBzYEtN/roIXSZMetJXyT+vf5e4xqjHrfG7Z/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efec4d5eaa696179d2454635ed7e0a39aa0477ba4170eae5382a45cb146c5035","last_reissued_at":"2026-07-05T07:59:25.383809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:25.383809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedMef: Towards Memory-efficient Federated Dynamic Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Hong Huang, Lingjuan Lyu, Weiming Zhuang","submitted_at":"2024-03-21T13:54:36Z","abstract_excerpt":"Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However, its application on resource-constrained devices is challenging due to the high demand for computation and memory resources to train deep learning models. Neural network pruning techniques, such as dynamic pruning, could enhance model efficiency, but directly adopting them in FL still poses substantial challenges, including post-pruning performance degradation, high activation memory usage, etc. To address these challenges, we propose FedMef, a novel and memory-efficient federated dynamic p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14737","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/2403.14737/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":"2403.14737","created_at":"2026-07-05T07:59:25.383873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14737v1","created_at":"2026-07-05T07:59:25.383873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14737","created_at":"2026-07-05T07:59:25.383873+00:00"},{"alias_kind":"pith_short_12","alias_value":"57WE2XVKNFQX","created_at":"2026-07-05T07:59:25.383873+00:00"},{"alias_kind":"pith_short_16","alias_value":"57WE2XVKNFQXTUSF","created_at":"2026-07-05T07:59:25.383873+00:00"},{"alias_kind":"pith_short_8","alias_value":"57WE2XVK","created_at":"2026-07-05T07:59:25.383873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18563","citing_title":"PacTrain: Pruning and Adaptive Sparse Gradient Compression for Efficient Collective Communication in Distributed Deep Learning","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG","json":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG.json","graph_json":"https://pith.science/api/pith-number/57WE2XVKNFQXTUSFIY2627QKHG/graph.json","events_json":"https://pith.science/api/pith-number/57WE2XVKNFQXTUSFIY2627QKHG/events.json","paper":"https://pith.science/paper/57WE2XVK"},"agent_actions":{"view_html":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG","download_json":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG.json","view_paper":"https://pith.science/paper/57WE2XVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14737&json=true","fetch_graph":"https://pith.science/api/pith-number/57WE2XVKNFQXTUSFIY2627QKHG/graph.json","fetch_events":"https://pith.science/api/pith-number/57WE2XVKNFQXTUSFIY2627QKHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG/action/storage_attestation","attest_author":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG/action/author_attestation","sign_citation":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG/action/citation_signature","submit_replication":"https://pith.science/pith/57WE2XVKNFQXTUSFIY2627QKHG/action/replication_record"}},"created_at":"2026-07-05T07:59:25.383873+00:00","updated_at":"2026-07-05T07:59:25.383873+00:00"}