{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PAX3MUIUVS232QTAQE4U5EHLGG","short_pith_number":"pith:PAX3MUIU","schema_version":"1.0","canonical_sha256":"782fb65114acb5bd426081394e90eb31b26c800adea0c5889f034c8727a708ee","source":{"kind":"arxiv","id":"2303.02278","version":3},"attestation_state":"computed","paper":{"title":"Federated Learning on Virtual Heterogeneous Data with Local-global Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Can Zhao, Chun-Yin Huang, Daguang Xu, Ruinan Jin, Xiaoxiao Li","submitted_at":"2023-03-04T00:35:29Z","abstract_excerpt":"While Federated Learning (FL) is gaining popularity for training machine learning models in a decentralized fashion, numerous challenges persist, such as asynchronization, computational expenses, data heterogeneity, and gradient and membership privacy attacks. Lately, dataset distillation has emerged as a promising solution for addressing the aforementioned challenges by generating a compact synthetic dataset that preserves a model's training efficacy. However, we discover that using distilled local datasets can amplify the heterogeneity issue in FL. To address this, we propose Federated Learn"},"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":"2303.02278","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-04T00:35:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02bedabbd6c1418a494747c2aef7b8aeab9203e149f98688648a9726b6fd5937","abstract_canon_sha256":"64041fa3837c57921ff4f5113782513e9fb753b1d5beb7599d138ccbd91bb455"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:12.082397Z","signature_b64":"lOfOf5P8341dpbH4gQ3qNlKtWSl33xxLw5rYJZfOrfZgCj43Bm1ro/755L4LNpvZ7IVhCSlei2tIdOzdl9AiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"782fb65114acb5bd426081394e90eb31b26c800adea0c5889f034c8727a708ee","last_reissued_at":"2026-07-05T10:29:12.081888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:12.081888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning on Virtual Heterogeneous Data with Local-global Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Can Zhao, Chun-Yin Huang, Daguang Xu, Ruinan Jin, Xiaoxiao Li","submitted_at":"2023-03-04T00:35:29Z","abstract_excerpt":"While Federated Learning (FL) is gaining popularity for training machine learning models in a decentralized fashion, numerous challenges persist, such as asynchronization, computational expenses, data heterogeneity, and gradient and membership privacy attacks. Lately, dataset distillation has emerged as a promising solution for addressing the aforementioned challenges by generating a compact synthetic dataset that preserves a model's training efficacy. However, we discover that using distilled local datasets can amplify the heterogeneity issue in FL. To address this, we propose Federated Learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02278","kind":"arxiv","version":3},"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/2303.02278/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":"2303.02278","created_at":"2026-07-05T10:29:12.081948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02278v3","created_at":"2026-07-05T10:29:12.081948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02278","created_at":"2026-07-05T10:29:12.081948+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAX3MUIUVS23","created_at":"2026-07-05T10:29:12.081948+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAX3MUIUVS232QTA","created_at":"2026-07-05T10:29:12.081948+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAX3MUIU","created_at":"2026-07-05T10:29:12.081948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG","json":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG.json","graph_json":"https://pith.science/api/pith-number/PAX3MUIUVS232QTAQE4U5EHLGG/graph.json","events_json":"https://pith.science/api/pith-number/PAX3MUIUVS232QTAQE4U5EHLGG/events.json","paper":"https://pith.science/paper/PAX3MUIU"},"agent_actions":{"view_html":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG","download_json":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG.json","view_paper":"https://pith.science/paper/PAX3MUIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02278&json=true","fetch_graph":"https://pith.science/api/pith-number/PAX3MUIUVS232QTAQE4U5EHLGG/graph.json","fetch_events":"https://pith.science/api/pith-number/PAX3MUIUVS232QTAQE4U5EHLGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG/action/storage_attestation","attest_author":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG/action/author_attestation","sign_citation":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG/action/citation_signature","submit_replication":"https://pith.science/pith/PAX3MUIUVS232QTAQE4U5EHLGG/action/replication_record"}},"created_at":"2026-07-05T10:29:12.081948+00:00","updated_at":"2026-07-05T10:29:12.081948+00:00"}