{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZFTXR3MMP727RD562J7NZDQBHW","short_pith_number":"pith:ZFTXR3MM","schema_version":"1.0","canonical_sha256":"c96778ed8c7ff5f88fbed27edc8e013dbf79bdb7345940673f9d8372b3b2ec01","source":{"kind":"arxiv","id":"2209.14851","version":1},"attestation_state":"computed","paper":{"title":"Meta Knowledge Condensation for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Joey Tianyi Zhou, Ping Liu, Xin Yu","submitted_at":"2022-09-29T15:07:37Z","abstract_excerpt":"Existing federated learning paradigms usually extensively exchange distributed models at a central solver to achieve a more powerful model. However, this would incur severe communication burden between a server and multiple clients especially when data distributions are heterogeneous. As a result, current federated learning methods often require a large number of communication rounds in training. Unlike existing paradigms, we introduce an alternative perspective to significantly decrease the communication cost in federate learning. In this work, we first introduce a meta knowledge representati"},"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":"2209.14851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T15:07:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7ddf7d14bda510caf6c44b0649ef253011ec27fd6542724a3f5ee2432e90d9b4","abstract_canon_sha256":"33803931ffcf0d49448c81cdd94c2639b0ffcb3a335cf5ae79832f64287933d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:06.327767Z","signature_b64":"I5VXbgRuFj6UCWE4TzoxfTr6RJts9/F9ZL+MNvTFBQe37aUrkk3zhE5rsBOJY8fBVf6Aa73B/1Yap3FsLnRwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c96778ed8c7ff5f88fbed27edc8e013dbf79bdb7345940673f9d8372b3b2ec01","last_reissued_at":"2026-07-05T05:02:06.327354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:06.327354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta Knowledge Condensation for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Joey Tianyi Zhou, Ping Liu, Xin Yu","submitted_at":"2022-09-29T15:07:37Z","abstract_excerpt":"Existing federated learning paradigms usually extensively exchange distributed models at a central solver to achieve a more powerful model. However, this would incur severe communication burden between a server and multiple clients especially when data distributions are heterogeneous. As a result, current federated learning methods often require a large number of communication rounds in training. Unlike existing paradigms, we introduce an alternative perspective to significantly decrease the communication cost in federate learning. In this work, we first introduce a meta knowledge representati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14851","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/2209.14851/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":"2209.14851","created_at":"2026-07-05T05:02:06.327410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.14851v1","created_at":"2026-07-05T05:02:06.327410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14851","created_at":"2026-07-05T05:02:06.327410+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFTXR3MMP727","created_at":"2026-07-05T05:02:06.327410+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFTXR3MMP727RD56","created_at":"2026-07-05T05:02:06.327410+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFTXR3MM","created_at":"2026-07-05T05:02:06.327410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02854","citing_title":"TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW","json":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW.json","graph_json":"https://pith.science/api/pith-number/ZFTXR3MMP727RD562J7NZDQBHW/graph.json","events_json":"https://pith.science/api/pith-number/ZFTXR3MMP727RD562J7NZDQBHW/events.json","paper":"https://pith.science/paper/ZFTXR3MM"},"agent_actions":{"view_html":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW","download_json":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW.json","view_paper":"https://pith.science/paper/ZFTXR3MM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.14851&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFTXR3MMP727RD562J7NZDQBHW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFTXR3MMP727RD562J7NZDQBHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW/action/storage_attestation","attest_author":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW/action/author_attestation","sign_citation":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW/action/citation_signature","submit_replication":"https://pith.science/pith/ZFTXR3MMP727RD562J7NZDQBHW/action/replication_record"}},"created_at":"2026-07-05T05:02:06.327410+00:00","updated_at":"2026-07-05T05:02:06.327410+00:00"}