{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N7MRZV3BBHC5WERLM6WT573Z7T","short_pith_number":"pith:N7MRZV3B","schema_version":"1.0","canonical_sha256":"6fd91cd76109c5db122b67ad3eff79fccdc9129c88dddc6d3b6730ecb86ddefc","source":{"kind":"arxiv","id":"2006.07242","version":3},"attestation_state":"computed","paper":{"title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lingjing Kong, Martin Jaggi, Sebastian U. Stich, Tao Lin","submitted_at":"2020-06-12T14:49:47Z","abstract_excerpt":"Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. However, directly averaging model parameters is only possible if all models have the same structure and size, which could be a restrictive constraint in many scenarios.\n  In this work we investigate more powerful and more flexible aggregation schemes for FL. Specific"},"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":"2006.07242","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:49:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4fad72b15272ac8727fdcf12fd0ea6a32af076d408c5ca164660743c819cfb47","abstract_canon_sha256":"f768a258531620776385eebbdbbaa7c7cfeabf4dd27c3fc811e95905dbe2d315"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:48.449185Z","signature_b64":"TPK/z9CvJHn/MHWVtvL1SYg1uHFsggVyqFX4jHvzsJAxFbO/AAV9FEQC8iIoKwPxlilcoxtYhGm+KcJX5JCRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fd91cd76109c5db122b67ad3eff79fccdc9129c88dddc6d3b6730ecb86ddefc","last_reissued_at":"2026-07-05T02:26:48.448731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:48.448731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lingjing Kong, Martin Jaggi, Sebastian U. Stich, Tao Lin","submitted_at":"2020-06-12T14:49:47Z","abstract_excerpt":"Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. However, directly averaging model parameters is only possible if all models have the same structure and size, which could be a restrictive constraint in many scenarios.\n  In this work we investigate more powerful and more flexible aggregation schemes for FL. Specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07242","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/2006.07242/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":"2006.07242","created_at":"2026-07-05T02:26:48.448787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07242v3","created_at":"2026-07-05T02:26:48.448787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07242","created_at":"2026-07-05T02:26:48.448787+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7MRZV3BBHC5","created_at":"2026-07-05T02:26:48.448787+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7MRZV3BBHC5WERL","created_at":"2026-07-05T02:26:48.448787+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7MRZV3B","created_at":"2026-07-05T02:26:48.448787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00173","citing_title":"TallyTrain: Communication-Efficient Federated Distillation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29002","citing_title":"FedQHD: Closed-Form Function-Space Federated Reinforcement Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07621","citing_title":"HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T","json":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T.json","graph_json":"https://pith.science/api/pith-number/N7MRZV3BBHC5WERLM6WT573Z7T/graph.json","events_json":"https://pith.science/api/pith-number/N7MRZV3BBHC5WERLM6WT573Z7T/events.json","paper":"https://pith.science/paper/N7MRZV3B"},"agent_actions":{"view_html":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T","download_json":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T.json","view_paper":"https://pith.science/paper/N7MRZV3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07242&json=true","fetch_graph":"https://pith.science/api/pith-number/N7MRZV3BBHC5WERLM6WT573Z7T/graph.json","fetch_events":"https://pith.science/api/pith-number/N7MRZV3BBHC5WERLM6WT573Z7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T/action/storage_attestation","attest_author":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T/action/author_attestation","sign_citation":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T/action/citation_signature","submit_replication":"https://pith.science/pith/N7MRZV3BBHC5WERLM6WT573Z7T/action/replication_record"}},"created_at":"2026-07-05T02:26:48.448787+00:00","updated_at":"2026-07-05T02:26:48.448787+00:00"}