{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2TFHEYFFYG5THH5P22EFUCELWO","short_pith_number":"pith:2TFHEYFF","schema_version":"1.0","canonical_sha256":"d4ca7260a5c1bb339fafd6885a088bb39f3f7423b937114b9beb09b563ea1440","source":{"kind":"arxiv","id":"2406.12575","version":1},"attestation_state":"computed","paper":{"title":"Training Diffusion Models with Federated Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Bart Cox, J\\'er\\'emie Decouchant, Matthijs de Goede","submitted_at":"2024-06-18T13:02:48Z","abstract_excerpt":"The training of diffusion-based models for image generation is predominantly controlled by a select few Big Tech companies, raising concerns about privacy, copyright, and data authority due to their lack of transparency regarding training data. To ad-dress this issue, we propose a federated diffusion model scheme that enables the independent and collaborative training of diffusion models without exposing local data. Our approach adapts the Federated Averaging (FedAvg) algorithm to train a Denoising Diffusion Model (DDPM). Through a novel utilization of the underlying UNet backbone, we achieve "},"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":"2406.12575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T13:02:48Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"a3dcbe2c5cdd7832fb4b2c6503596c156b099d53d6ae3a99b302877c1607920d","abstract_canon_sha256":"c27acceb3c8942164d024d61d2cdca3cf5c836497ca820fe689d1a1a8e9e5f97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:48.358129Z","signature_b64":"jfLZtOglEsgibICYiwI/7PkhENvkDF18Hm3lI0ziAMyCrzPc6QHfNIjWT18PmJdHocLgQaE6CujTaih6DywEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4ca7260a5c1bb339fafd6885a088bb39f3f7423b937114b9beb09b563ea1440","last_reissued_at":"2026-07-05T08:33:48.357640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:48.357640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Diffusion Models with Federated Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Bart Cox, J\\'er\\'emie Decouchant, Matthijs de Goede","submitted_at":"2024-06-18T13:02:48Z","abstract_excerpt":"The training of diffusion-based models for image generation is predominantly controlled by a select few Big Tech companies, raising concerns about privacy, copyright, and data authority due to their lack of transparency regarding training data. To ad-dress this issue, we propose a federated diffusion model scheme that enables the independent and collaborative training of diffusion models without exposing local data. Our approach adapts the Federated Averaging (FedAvg) algorithm to train a Denoising Diffusion Model (DDPM). Through a novel utilization of the underlying UNet backbone, we achieve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12575","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/2406.12575/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":"2406.12575","created_at":"2026-07-05T08:33:48.357698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12575v1","created_at":"2026-07-05T08:33:48.357698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12575","created_at":"2026-07-05T08:33:48.357698+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TFHEYFFYG5T","created_at":"2026-07-05T08:33:48.357698+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TFHEYFFYG5THH5P","created_at":"2026-07-05T08:33:48.357698+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TFHEYFF","created_at":"2026-07-05T08:33:48.357698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10153","citing_title":"Compositional Generative Modeling from Decentralized Data","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14429","citing_title":"CollaFuse: Collaborative Diffusion Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08288","citing_title":"UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07860","citing_title":"On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO","json":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO.json","graph_json":"https://pith.science/api/pith-number/2TFHEYFFYG5THH5P22EFUCELWO/graph.json","events_json":"https://pith.science/api/pith-number/2TFHEYFFYG5THH5P22EFUCELWO/events.json","paper":"https://pith.science/paper/2TFHEYFF"},"agent_actions":{"view_html":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO","download_json":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO.json","view_paper":"https://pith.science/paper/2TFHEYFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12575&json=true","fetch_graph":"https://pith.science/api/pith-number/2TFHEYFFYG5THH5P22EFUCELWO/graph.json","fetch_events":"https://pith.science/api/pith-number/2TFHEYFFYG5THH5P22EFUCELWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO/action/storage_attestation","attest_author":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO/action/author_attestation","sign_citation":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO/action/citation_signature","submit_replication":"https://pith.science/pith/2TFHEYFFYG5THH5P22EFUCELWO/action/replication_record"}},"created_at":"2026-07-05T08:33:48.357698+00:00","updated_at":"2026-07-05T08:33:48.357698+00:00"}