{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IOUX3QBK6DGT6VHQTOJ3FVV3NW","short_pith_number":"pith:IOUX3QBK","schema_version":"1.0","canonical_sha256":"43a97dc02af0cd3f54f09b93b2d6bb6d92360abc48aaa43e465de37c6e0a4cf5","source":{"kind":"arxiv","id":"2104.15092","version":1},"attestation_state":"computed","paper":{"title":"Faster Meta Update Strategy for Noise-Robust Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Linchao Zhu, Lu Jiang, Yi Yang, Youjiang Xu","submitted_at":"2021-04-30T16:19:07Z","abstract_excerpt":"It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow training is currently the bottleneck in the meta learning approaches. In this paper, we introduce a novel Faster Meta Update Strategy (FaMUS) to replace the most expensive step in the meta gradient computation with a faster layer-wise approximation. We empirically find that FaMUS yields not only a reasonably accurate but also a low-variance approximation of"},"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":"2104.15092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-30T16:19:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"47dc3e0dc80b3a67f815b6fa69eff27e8d719ea547de99d44b750b970c9d35f2","abstract_canon_sha256":"73d455008da1fb605b0074cb2b9384faba8124eb0b81548bbfb12b0f4433293a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:29.826119Z","signature_b64":"Ut6epcwUb1+SHFkTk7H536EMUBUITxv6BgTkGHMNjc7+K94jh2J1ejXLNa6HPjnuS7rUpSUddyoGD0acFIYCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43a97dc02af0cd3f54f09b93b2d6bb6d92360abc48aaa43e465de37c6e0a4cf5","last_reissued_at":"2026-07-05T02:36:29.825475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:29.825475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster Meta Update Strategy for Noise-Robust Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Linchao Zhu, Lu Jiang, Yi Yang, Youjiang Xu","submitted_at":"2021-04-30T16:19:07Z","abstract_excerpt":"It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow training is currently the bottleneck in the meta learning approaches. In this paper, we introduce a novel Faster Meta Update Strategy (FaMUS) to replace the most expensive step in the meta gradient computation with a faster layer-wise approximation. We empirically find that FaMUS yields not only a reasonably accurate but also a low-variance approximation of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.15092","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/2104.15092/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":"2104.15092","created_at":"2026-07-05T02:36:29.825542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.15092v1","created_at":"2026-07-05T02:36:29.825542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.15092","created_at":"2026-07-05T02:36:29.825542+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOUX3QBK6DGT","created_at":"2026-07-05T02:36:29.825542+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOUX3QBK6DGT6VHQ","created_at":"2026-07-05T02:36:29.825542+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOUX3QBK","created_at":"2026-07-05T02:36:29.825542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW","json":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW.json","graph_json":"https://pith.science/api/pith-number/IOUX3QBK6DGT6VHQTOJ3FVV3NW/graph.json","events_json":"https://pith.science/api/pith-number/IOUX3QBK6DGT6VHQTOJ3FVV3NW/events.json","paper":"https://pith.science/paper/IOUX3QBK"},"agent_actions":{"view_html":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW","download_json":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW.json","view_paper":"https://pith.science/paper/IOUX3QBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.15092&json=true","fetch_graph":"https://pith.science/api/pith-number/IOUX3QBK6DGT6VHQTOJ3FVV3NW/graph.json","fetch_events":"https://pith.science/api/pith-number/IOUX3QBK6DGT6VHQTOJ3FVV3NW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW/action/storage_attestation","attest_author":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW/action/author_attestation","sign_citation":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW/action/citation_signature","submit_replication":"https://pith.science/pith/IOUX3QBK6DGT6VHQTOJ3FVV3NW/action/replication_record"}},"created_at":"2026-07-05T02:36:29.825542+00:00","updated_at":"2026-07-05T02:36:29.825542+00:00"}