{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FJ3ZRU2EBARYQYLKN6QRF7FH6Y","short_pith_number":"pith:FJ3ZRU2E","schema_version":"1.0","canonical_sha256":"2a7798d344082388616a6fa112fca7f61d6cf6f3f40f7f849a09bcaa63bd3bbd","source":{"kind":"arxiv","id":"2010.08982","version":1},"attestation_state":"computed","paper":{"title":"Federated Unsupervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Wu, Fengda Zhang, Jun Xiao, Kun Kuang, Tao Shen, Xiaolin Li, Yin Zhang, Yueting Zhuang, Zhaoyang You","submitted_at":"2020-10-18T13:28:30Z","abstract_excerpt":"To leverage enormous unlabeled data on distributed edge devices, we formulate a new problem in federated learning called Federated Unsupervised Representation Learning (FURL) to learn a common representation model without supervision while preserving data privacy. FURL poses two new challenges: (1) data distribution shift (Non-IID distribution) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces. (2) without the unified information among clients in FURL, the representations across clients would be misaligned. To address the"},"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":"2010.08982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T13:28:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18f240e933df401bcf25b164f64888a4e0c04c8a0c07757cbff585acd088fb7c","abstract_canon_sha256":"61d49d55382a90d8ab5d0b987c2b02454e1a953eff8fe0a777cf81c67cbb6a05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:47.284274Z","signature_b64":"M7jsFlV4rTvAy0zTZoXo1SyZeXakm1qZuVxt8iI7KrK6tUP1IX7mJjfcnClsT2LArtxaZls9RoFvw3MFPKMsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a7798d344082388616a6fa112fca7f61d6cf6f3f40f7f849a09bcaa63bd3bbd","last_reissued_at":"2026-07-05T01:43:47.283912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:47.283912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Unsupervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Wu, Fengda Zhang, Jun Xiao, Kun Kuang, Tao Shen, Xiaolin Li, Yin Zhang, Yueting Zhuang, Zhaoyang You","submitted_at":"2020-10-18T13:28:30Z","abstract_excerpt":"To leverage enormous unlabeled data on distributed edge devices, we formulate a new problem in federated learning called Federated Unsupervised Representation Learning (FURL) to learn a common representation model without supervision while preserving data privacy. FURL poses two new challenges: (1) data distribution shift (Non-IID distribution) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces. (2) without the unified information among clients in FURL, the representations across clients would be misaligned. To address the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08982","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/2010.08982/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":"2010.08982","created_at":"2026-07-05T01:43:47.283970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08982v1","created_at":"2026-07-05T01:43:47.283970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08982","created_at":"2026-07-05T01:43:47.283970+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJ3ZRU2EBARY","created_at":"2026-07-05T01:43:47.283970+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJ3ZRU2EBARYQYLK","created_at":"2026-07-05T01:43:47.283970+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJ3ZRU2E","created_at":"2026-07-05T01:43:47.283970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26243","citing_title":"Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y","json":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y.json","graph_json":"https://pith.science/api/pith-number/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/graph.json","events_json":"https://pith.science/api/pith-number/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/events.json","paper":"https://pith.science/paper/FJ3ZRU2E"},"agent_actions":{"view_html":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y","download_json":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y.json","view_paper":"https://pith.science/paper/FJ3ZRU2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08982&json=true","fetch_graph":"https://pith.science/api/pith-number/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/action/storage_attestation","attest_author":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/action/author_attestation","sign_citation":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/action/citation_signature","submit_replication":"https://pith.science/pith/FJ3ZRU2EBARYQYLKN6QRF7FH6Y/action/replication_record"}},"created_at":"2026-07-05T01:43:47.283970+00:00","updated_at":"2026-07-05T01:43:47.283970+00:00"}