{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VKQFMK3X3IWMITF7DULEW563MO","short_pith_number":"pith:VKQFMK3X","schema_version":"1.0","canonical_sha256":"aaa0562b77da2cc44cbf1d164b77db63b93da293be48f5b32eca246a1914fd4a","source":{"kind":"arxiv","id":"2111.11204","version":1},"attestation_state":"computed","paper":{"title":"Client Selection in Federated Learning based on Gradients Importance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"El houcine Bergou, Hajar El Hammouti, Ouiame Marnissi","submitted_at":"2021-11-19T11:53:23Z","abstract_excerpt":"Federated learning (FL) enables multiple devices to collaboratively learn a global model without sharing their personal data. In real-world applications, the different parties are likely to have heterogeneous data distribution and limited communication bandwidth. In this paper, we are interested in improving the communication efficiency of FL systems. We investigate and design a device selection strategy based on the importance of the gradient norms. In particular, our approach consists of selecting devices with the highest norms of gradient values at each communication round. We study the con"},"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":"2111.11204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T11:53:23Z","cross_cats_sorted":[],"title_canon_sha256":"10ea6edd0f6149e668f0c96d945774457791786dc38ebe94d836fe6df6d02035","abstract_canon_sha256":"0fd36aafff5072d04524adaef07d693a2ec0a5cc16cb5160c9c7a94f409ab829"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:00.932928Z","signature_b64":"VxDqhuFxJvqFypNX3Hn9NxIwDrnjS8ikOYkiZ+y7jXdAVuBojL2diaWZFkhbJqJNGB8IvU7PMfsVNpXCFBJPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aaa0562b77da2cc44cbf1d164b77db63b93da293be48f5b32eca246a1914fd4a","last_reissued_at":"2026-07-05T03:34:00.932529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:00.932529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Client Selection in Federated Learning based on Gradients Importance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"El houcine Bergou, Hajar El Hammouti, Ouiame Marnissi","submitted_at":"2021-11-19T11:53:23Z","abstract_excerpt":"Federated learning (FL) enables multiple devices to collaboratively learn a global model without sharing their personal data. In real-world applications, the different parties are likely to have heterogeneous data distribution and limited communication bandwidth. In this paper, we are interested in improving the communication efficiency of FL systems. We investigate and design a device selection strategy based on the importance of the gradient norms. In particular, our approach consists of selecting devices with the highest norms of gradient values at each communication round. We study the con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11204","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/2111.11204/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":"2111.11204","created_at":"2026-07-05T03:34:00.932584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11204v1","created_at":"2026-07-05T03:34:00.932584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11204","created_at":"2026-07-05T03:34:00.932584+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKQFMK3X3IWM","created_at":"2026-07-05T03:34:00.932584+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKQFMK3X3IWMITF7","created_at":"2026-07-05T03:34:00.932584+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKQFMK3X","created_at":"2026-07-05T03:34:00.932584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07157","citing_title":"Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO","json":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO.json","graph_json":"https://pith.science/api/pith-number/VKQFMK3X3IWMITF7DULEW563MO/graph.json","events_json":"https://pith.science/api/pith-number/VKQFMK3X3IWMITF7DULEW563MO/events.json","paper":"https://pith.science/paper/VKQFMK3X"},"agent_actions":{"view_html":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO","download_json":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO.json","view_paper":"https://pith.science/paper/VKQFMK3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11204&json=true","fetch_graph":"https://pith.science/api/pith-number/VKQFMK3X3IWMITF7DULEW563MO/graph.json","fetch_events":"https://pith.science/api/pith-number/VKQFMK3X3IWMITF7DULEW563MO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO/action/storage_attestation","attest_author":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO/action/author_attestation","sign_citation":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO/action/citation_signature","submit_replication":"https://pith.science/pith/VKQFMK3X3IWMITF7DULEW563MO/action/replication_record"}},"created_at":"2026-07-05T03:34:00.932584+00:00","updated_at":"2026-07-05T03:34:00.932584+00:00"}