{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W6JAVUUGLI6ZQUYFPIH6PS4FK2","short_pith_number":"pith:W6JAVUUG","schema_version":"1.0","canonical_sha256":"b7920ad2865a3d9853057a0fe7cb85569712d870a3d468a7f7aae41c35901a1a","source":{"kind":"arxiv","id":"2304.04326","version":2},"attestation_state":"computed","paper":{"title":"Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Deepak Ravikumar, Gobinda Saha, Kaushik Roy, Sai Aparna Aketi","submitted_at":"2023-04-09T23:26:24Z","abstract_excerpt":"Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as the ability to train with a wide variety of data sources. However, one of the key challenges with decentralized learning is heterogeneity in the data distribution across the nodes. In this paper, we propose In-Distribution Knowledge Distillation (IDKD) to address the challenge of heterogeneous data distribution. The goal of IDKD is to homogenize the data distribution across the nodes. While such data homogenization ca"},"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":"2304.04326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-09T23:26:24Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"e887ceedfcfb97c24f5d6392fe045ec9b9da9dd43c65c1891870952df4eb7b47","abstract_canon_sha256":"ba222dc98bb5cb4d48377b3db57e1705eb891ad9d22cbf7d99c2635c24f608be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:45.928039Z","signature_b64":"RUx7vKL/XACB6M+TjrRjCnFj2SsafqLFiFboRJyuWYMll941hYIDkUww6QFgi1TJnsZjT4WveAXRGypeQbWMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7920ad2865a3d9853057a0fe7cb85569712d870a3d468a7f7aae41c35901a1a","last_reissued_at":"2026-07-05T07:48:45.927615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:45.927615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Deepak Ravikumar, Gobinda Saha, Kaushik Roy, Sai Aparna Aketi","submitted_at":"2023-04-09T23:26:24Z","abstract_excerpt":"Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as the ability to train with a wide variety of data sources. However, one of the key challenges with decentralized learning is heterogeneity in the data distribution across the nodes. In this paper, we propose In-Distribution Knowledge Distillation (IDKD) to address the challenge of heterogeneous data distribution. The goal of IDKD is to homogenize the data distribution across the nodes. While such data homogenization ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04326","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/2304.04326/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":"2304.04326","created_at":"2026-07-05T07:48:45.927674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04326v2","created_at":"2026-07-05T07:48:45.927674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04326","created_at":"2026-07-05T07:48:45.927674+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6JAVUUGLI6Z","created_at":"2026-07-05T07:48:45.927674+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6JAVUUGLI6ZQUYF","created_at":"2026-07-05T07:48:45.927674+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6JAVUUG","created_at":"2026-07-05T07:48:45.927674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11760","citing_title":"Topology-Aware Knowledge Propagation in Decentralized Learning","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2","json":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2.json","graph_json":"https://pith.science/api/pith-number/W6JAVUUGLI6ZQUYFPIH6PS4FK2/graph.json","events_json":"https://pith.science/api/pith-number/W6JAVUUGLI6ZQUYFPIH6PS4FK2/events.json","paper":"https://pith.science/paper/W6JAVUUG"},"agent_actions":{"view_html":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2","download_json":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2.json","view_paper":"https://pith.science/paper/W6JAVUUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04326&json=true","fetch_graph":"https://pith.science/api/pith-number/W6JAVUUGLI6ZQUYFPIH6PS4FK2/graph.json","fetch_events":"https://pith.science/api/pith-number/W6JAVUUGLI6ZQUYFPIH6PS4FK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2/action/storage_attestation","attest_author":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2/action/author_attestation","sign_citation":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2/action/citation_signature","submit_replication":"https://pith.science/pith/W6JAVUUGLI6ZQUYFPIH6PS4FK2/action/replication_record"}},"created_at":"2026-07-05T07:48:45.927674+00:00","updated_at":"2026-07-05T07:48:45.927674+00:00"}