{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZIROPHJDST3DECWXDFQ32XT2VJ","short_pith_number":"pith:ZIROPHJD","schema_version":"1.0","canonical_sha256":"ca22e79d2394f6320ad71961bd5e7aaa4c72043afe3dd2b2ea927ced31146b40","source":{"kind":"arxiv","id":"2010.01992","version":3},"attestation_state":"computed","paper":{"title":"Improving Few-Shot Learning through Multi-task Representation Learning Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amaury Habrard, Ang\\'elique Loesch, Ievgen Redko, Quentin Bouniot, Romaric Audigier","submitted_at":"2020-10-05T13:24:43Z","abstract_excerpt":"In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task. We start by reviewing recent advances in MTR theory and show that they can provide novel insights for popular meta-learning algorithms when analyzed within this framework. In particular, we highlight a fundamental difference between gradient-based and metric-based algorithms in practice and put forward a theoretical analysis to explain it. Finally, we use the derived insights to improve "},"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":"2010.01992","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T13:24:43Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"dcbb3fcfd6dc2ac136c0c13a727bee919c24f5a83e9863183bd3ba1ce4bbccde","abstract_canon_sha256":"34628c9948286a1def48155a3bfe9cd7d2fbb80600f964dbd74a0c1b755090c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:03.556271Z","signature_b64":"h7zUPb/V2TDbXuAwlms9L1DCiCvU+6LQhBDoq+15xv8lbRdKeY5X0MjWEj+Bft2sQc+RC/+1VUAhOrXut3nZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca22e79d2394f6320ad71961bd5e7aaa4c72043afe3dd2b2ea927ced31146b40","last_reissued_at":"2026-07-05T07:05:03.555708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:03.555708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Few-Shot Learning through Multi-task Representation Learning Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amaury Habrard, Ang\\'elique Loesch, Ievgen Redko, Quentin Bouniot, Romaric Audigier","submitted_at":"2020-10-05T13:24:43Z","abstract_excerpt":"In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task. We start by reviewing recent advances in MTR theory and show that they can provide novel insights for popular meta-learning algorithms when analyzed within this framework. In particular, we highlight a fundamental difference between gradient-based and metric-based algorithms in practice and put forward a theoretical analysis to explain it. Finally, we use the derived insights to improve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01992","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/2010.01992/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":"2010.01992","created_at":"2026-07-05T07:05:03.555776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01992v3","created_at":"2026-07-05T07:05:03.555776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01992","created_at":"2026-07-05T07:05:03.555776+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIROPHJDST3D","created_at":"2026-07-05T07:05:03.555776+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIROPHJDST3DECWX","created_at":"2026-07-05T07:05:03.555776+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIROPHJD","created_at":"2026-07-05T07:05:03.555776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.15241","citing_title":"Research on Graph-Retrieval Augmented Generation Based on Historical Text Knowledge Graphs","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ","json":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ.json","graph_json":"https://pith.science/api/pith-number/ZIROPHJDST3DECWXDFQ32XT2VJ/graph.json","events_json":"https://pith.science/api/pith-number/ZIROPHJDST3DECWXDFQ32XT2VJ/events.json","paper":"https://pith.science/paper/ZIROPHJD"},"agent_actions":{"view_html":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ","download_json":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ.json","view_paper":"https://pith.science/paper/ZIROPHJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01992&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIROPHJDST3DECWXDFQ32XT2VJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIROPHJDST3DECWXDFQ32XT2VJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZIROPHJDST3DECWXDFQ32XT2VJ/action/replication_record"}},"created_at":"2026-07-05T07:05:03.555776+00:00","updated_at":"2026-07-05T07:05:03.555776+00:00"}