{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R45UJYHURFD656RTOHZM4BREQN","short_pith_number":"pith:R45UJYHU","schema_version":"1.0","canonical_sha256":"8f3b44e0f48947eefa3371f2ce0624836ed202a8b4266c06f92559fc26d6fd62","source":{"kind":"arxiv","id":"1811.11479","version":2},"attestation_state":"computed","paper":{"title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eunjeong Jeong, Hyesung Kim, Jihong Park, Mehdi Bennis, Seong-Lyun Kim, Seungeun Oh","submitted_at":"2018-11-28T10:16:18Z","abstract_excerpt":"On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose federated distillation (FD), a distributed model training algorithm whose communication payload size is much smaller than a benchmark scheme, federated learning (FL), particularly when the model size is large. Moreover, user-generated data samples are likely to become non-IID across devices, which commonly degrades the performance compared to the case with an IID"},"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":"1811.11479","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-28T10:16:18Z","cross_cats_sorted":["cs.NI","stat.ML"],"title_canon_sha256":"ffe23062e22b9e3d0261894941b3d875eef805c5a1321647fa8e7d0f720f3787","abstract_canon_sha256":"bb73b2c29201dbb710683643a0b7d0670f26d26c63d475c7f4e4d13ee1250476"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:23.405052Z","signature_b64":"PNj/o+TSyk6voep2yCtLb6+i5Rx9K9lMd5nCWPPtykxwwTJemQyV2lphhTl9MG8/gqC5AvL9MHgV9ndy44fvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f3b44e0f48947eefa3371f2ce0624836ed202a8b4266c06f92559fc26d6fd62","last_reissued_at":"2026-07-05T07:02:23.404574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:23.404574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eunjeong Jeong, Hyesung Kim, Jihong Park, Mehdi Bennis, Seong-Lyun Kim, Seungeun Oh","submitted_at":"2018-11-28T10:16:18Z","abstract_excerpt":"On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose federated distillation (FD), a distributed model training algorithm whose communication payload size is much smaller than a benchmark scheme, federated learning (FL), particularly when the model size is large. Moreover, user-generated data samples are likely to become non-IID across devices, which commonly degrades the performance compared to the case with an IID"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11479","kind":"arxiv","version":2},"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/1811.11479/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":"1811.11479","created_at":"2026-07-05T07:02:23.404634+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11479v2","created_at":"2026-07-05T07:02:23.404634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11479","created_at":"2026-07-05T07:02:23.404634+00:00"},{"alias_kind":"pith_short_12","alias_value":"R45UJYHURFD6","created_at":"2026-07-05T07:02:23.404634+00:00"},{"alias_kind":"pith_short_16","alias_value":"R45UJYHURFD656RT","created_at":"2026-07-05T07:02:23.404634+00:00"},{"alias_kind":"pith_short_8","alias_value":"R45UJYHU","created_at":"2026-07-05T07:02:23.404634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08013","citing_title":"Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08252","citing_title":"Quantifying and Defending against the Privacy Risk in Logit-based Federated Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00173","citing_title":"TallyTrain: Communication-Efficient Federated Distillation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"1907.06426","citing_title":"Multi-hop Federated Private Data Augmentation with Sample Compression","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2406.10861","citing_title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13543","citing_title":"Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2508.14769","citing_title":"Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21322","citing_title":"Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14886","citing_title":"BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09356","citing_title":"Function-Space ADMM for Decentralized Federated Learning: A Control Theoretic Perspective","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25018","citing_title":"Internet of Everything in the 6G Era: Paradigms, Enablers, Potentials and Future Directions","ref_index":254,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05959","citing_title":"From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12160","citing_title":"PubSwap: Public-Data Off-Policy Coordination for Federated RLVR","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN","json":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN.json","graph_json":"https://pith.science/api/pith-number/R45UJYHURFD656RTOHZM4BREQN/graph.json","events_json":"https://pith.science/api/pith-number/R45UJYHURFD656RTOHZM4BREQN/events.json","paper":"https://pith.science/paper/R45UJYHU"},"agent_actions":{"view_html":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN","download_json":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN.json","view_paper":"https://pith.science/paper/R45UJYHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11479&json=true","fetch_graph":"https://pith.science/api/pith-number/R45UJYHURFD656RTOHZM4BREQN/graph.json","fetch_events":"https://pith.science/api/pith-number/R45UJYHURFD656RTOHZM4BREQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN/action/storage_attestation","attest_author":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN/action/author_attestation","sign_citation":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN/action/citation_signature","submit_replication":"https://pith.science/pith/R45UJYHURFD656RTOHZM4BREQN/action/replication_record"}},"created_at":"2026-07-05T07:02:23.404634+00:00","updated_at":"2026-07-05T07:02:23.404634+00:00"}