{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ETVEAYNVZKMZM5ZAKXJILIJFF4","short_pith_number":"pith:ETVEAYNV","schema_version":"1.0","canonical_sha256":"24ea4061b5ca9996772055d285a1252f1872947d2c1eedd10329e1fce4ec8e1c","source":{"kind":"arxiv","id":"2405.02081","version":1},"attestation_state":"computed","paper":{"title":"A Mutual Information Perspective on Federated Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christos Louizos, Denis Korzhenkov, Matthias Reisser","submitted_at":"2024-05-03T13:15:29Z","abstract_excerpt":"We investigate contrastive learning in the federated setting through the lens of SimCLR and multi-view mutual information maximization. In doing so, we uncover a connection between contrastive representation learning and user verification; by adding a user verification loss to each client's local SimCLR loss we recover a lower bound to the global multi-view mutual information. To accommodate for the case of when some labelled data are available at the clients, we extend our SimCLR variant to the federated semi-supervised setting. We see that a supervised SimCLR objective can be obtained with t"},"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":"2405.02081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-03T13:15:29Z","cross_cats_sorted":[],"title_canon_sha256":"8f6ebe0b0c5dfdd2fabd283c1846ec576f6a5b1584abf03d10395c33967232bb","abstract_canon_sha256":"00ceb472e55a44f569bbeee9ea67378ef14056d62a421c62ebeaabbfefefc8f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:06.531591Z","signature_b64":"gLheyLsq0uqshx8U+fh5r7U4M5Guz4DwXKH1I3eZTo1O531z1Y+6MDxxQXCaRTmTcYc0qJFLgnLiI1a17mlNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24ea4061b5ca9996772055d285a1252f1872947d2c1eedd10329e1fce4ec8e1c","last_reissued_at":"2026-07-05T08:15:06.531195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:06.531195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mutual Information Perspective on Federated Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christos Louizos, Denis Korzhenkov, Matthias Reisser","submitted_at":"2024-05-03T13:15:29Z","abstract_excerpt":"We investigate contrastive learning in the federated setting through the lens of SimCLR and multi-view mutual information maximization. In doing so, we uncover a connection between contrastive representation learning and user verification; by adding a user verification loss to each client's local SimCLR loss we recover a lower bound to the global multi-view mutual information. To accommodate for the case of when some labelled data are available at the clients, we extend our SimCLR variant to the federated semi-supervised setting. We see that a supervised SimCLR objective can be obtained with t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02081","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/2405.02081/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":"2405.02081","created_at":"2026-07-05T08:15:06.531251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02081v1","created_at":"2026-07-05T08:15:06.531251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02081","created_at":"2026-07-05T08:15:06.531251+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETVEAYNVZKMZ","created_at":"2026-07-05T08:15:06.531251+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETVEAYNVZKMZM5ZA","created_at":"2026-07-05T08:15:06.531251+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETVEAYNV","created_at":"2026-07-05T08:15:06.531251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07888","citing_title":"Enhancing Federated Quadruplet Learning: Stochastic Client Selection and Embedding Stability Analysis","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4","json":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4.json","graph_json":"https://pith.science/api/pith-number/ETVEAYNVZKMZM5ZAKXJILIJFF4/graph.json","events_json":"https://pith.science/api/pith-number/ETVEAYNVZKMZM5ZAKXJILIJFF4/events.json","paper":"https://pith.science/paper/ETVEAYNV"},"agent_actions":{"view_html":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4","download_json":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4.json","view_paper":"https://pith.science/paper/ETVEAYNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02081&json=true","fetch_graph":"https://pith.science/api/pith-number/ETVEAYNVZKMZM5ZAKXJILIJFF4/graph.json","fetch_events":"https://pith.science/api/pith-number/ETVEAYNVZKMZM5ZAKXJILIJFF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4/action/storage_attestation","attest_author":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4/action/author_attestation","sign_citation":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4/action/citation_signature","submit_replication":"https://pith.science/pith/ETVEAYNVZKMZM5ZAKXJILIJFF4/action/replication_record"}},"created_at":"2026-07-05T08:15:06.531251+00:00","updated_at":"2026-07-05T08:15:06.531251+00:00"}