{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2HRRVVZ7TG4F7FR7VDTJTCOQU5","short_pith_number":"pith:2HRRVVZ7","schema_version":"1.0","canonical_sha256":"d1e31ad73f99b85f963fa8e69989d0a77a63df927a2ae4bf9dadb080a58eb726","source":{"kind":"arxiv","id":"2110.14057","version":1},"attestation_state":"computed","paper":{"title":"Meta-learning with an Adaptive Task Scheduler","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Defu Lian, Huaxiu Yao, Mehrdad Mahdavi, Peilin Zhao, Ying Wei, Yu Wang","submitted_at":"2021-10-26T22:16:35Z","abstract_excerpt":"To benefit the learning of a new task, meta-learning has been proposed to transfer a well-generalized meta-model learned from various meta-training tasks. Existing meta-learning algorithms randomly sample meta-training tasks with a uniform probability, under the assumption that tasks are of equal importance. However, it is likely that tasks are detrimental with noise or imbalanced given a limited number of meta-training tasks. To prevent the meta-model from being corrupted by such detrimental tasks or dominated by tasks in the majority, in this paper, we propose an adaptive task scheduler (ATS"},"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":"2110.14057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T22:16:35Z","cross_cats_sorted":[],"title_canon_sha256":"5fc7b1d31bbf34ca2f4dea0e39f8ff6c4ed259f4e22722387a1ac495755b9dd3","abstract_canon_sha256":"23d3a7a843035fb6ee33524c1d319f1822241fb941ae6702489ea124c06a554a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:23.345214Z","signature_b64":"gxk53CmHLSEpBR2xPUAO2EZZSfmKitBuobFhL7BD2/hFb2u/P9MtOnyCeWB84tY2yj4sGU88o+rA3E8SsFSeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1e31ad73f99b85f963fa8e69989d0a77a63df927a2ae4bf9dadb080a58eb726","last_reissued_at":"2026-07-05T03:26:23.344747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:23.344747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-learning with an Adaptive Task Scheduler","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Defu Lian, Huaxiu Yao, Mehrdad Mahdavi, Peilin Zhao, Ying Wei, Yu Wang","submitted_at":"2021-10-26T22:16:35Z","abstract_excerpt":"To benefit the learning of a new task, meta-learning has been proposed to transfer a well-generalized meta-model learned from various meta-training tasks. Existing meta-learning algorithms randomly sample meta-training tasks with a uniform probability, under the assumption that tasks are of equal importance. However, it is likely that tasks are detrimental with noise or imbalanced given a limited number of meta-training tasks. To prevent the meta-model from being corrupted by such detrimental tasks or dominated by tasks in the majority, in this paper, we propose an adaptive task scheduler (ATS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14057","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/2110.14057/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":"2110.14057","created_at":"2026-07-05T03:26:23.344806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14057v1","created_at":"2026-07-05T03:26:23.344806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14057","created_at":"2026-07-05T03:26:23.344806+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HRRVVZ7TG4F","created_at":"2026-07-05T03:26:23.344806+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HRRVVZ7TG4F7FR7","created_at":"2026-07-05T03:26:23.344806+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HRRVVZ7","created_at":"2026-07-05T03:26:23.344806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11878","citing_title":"AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5","json":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5.json","graph_json":"https://pith.science/api/pith-number/2HRRVVZ7TG4F7FR7VDTJTCOQU5/graph.json","events_json":"https://pith.science/api/pith-number/2HRRVVZ7TG4F7FR7VDTJTCOQU5/events.json","paper":"https://pith.science/paper/2HRRVVZ7"},"agent_actions":{"view_html":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5","download_json":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5.json","view_paper":"https://pith.science/paper/2HRRVVZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14057&json=true","fetch_graph":"https://pith.science/api/pith-number/2HRRVVZ7TG4F7FR7VDTJTCOQU5/graph.json","fetch_events":"https://pith.science/api/pith-number/2HRRVVZ7TG4F7FR7VDTJTCOQU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5/action/storage_attestation","attest_author":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5/action/author_attestation","sign_citation":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5/action/citation_signature","submit_replication":"https://pith.science/pith/2HRRVVZ7TG4F7FR7VDTJTCOQU5/action/replication_record"}},"created_at":"2026-07-05T03:26:23.344806+00:00","updated_at":"2026-07-05T03:26:23.344806+00:00"}