{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ECEW5MYGE3AH6SAWBVYCD5KEXK","short_pith_number":"pith:ECEW5MYG","schema_version":"1.0","canonical_sha256":"20896eb30626c07f48160d7021f544baa06c46f76598e0b2dd324f0a791e1599","source":{"kind":"arxiv","id":"1807.02872","version":2},"attestation_state":"computed","paper":{"title":"Large Margin Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiatao Gu, Lei Zhang, Qimai Li, Victor O.K. Li, Wangmeng Xiang, Xiao-Ming Wu, Yong Wang","submitted_at":"2018-07-08T19:44:31Z","abstract_excerpt":"The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the classification loss function with a large margin distance loss function for training. Extensive experiments on two state-of-the-art few-shot learning methods, graph neural networks and prototypical networks, show that our method can improve the performance of existing models substantially with very"},"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":"1807.02872","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-08T19:44:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fac78aa668d72f59eaf3e476153fae4c4a11a27ffa607c016fb77898ce1bdf5a","abstract_canon_sha256":"4d464f9b1801f83b8a5c8c8f2febe3693c3f5269861c65d94efb78038aa55282"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:13.866500Z","signature_b64":"IQevnX+6ssDFdqetEfo42ZIelpRbOLz+qVlzWKKo47ctVr4hv5p0AZbr5fQLb6Uu3P6ke4YhBL8xOpV0qY5NBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20896eb30626c07f48160d7021f544baa06c46f76598e0b2dd324f0a791e1599","last_reissued_at":"2026-05-18T00:05:13.865984Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:13.865984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Margin Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiatao Gu, Lei Zhang, Qimai Li, Victor O.K. Li, Wangmeng Xiang, Xiao-Ming Wu, Yong Wang","submitted_at":"2018-07-08T19:44:31Z","abstract_excerpt":"The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the classification loss function with a large margin distance loss function for training. Extensive experiments on two state-of-the-art few-shot learning methods, graph neural networks and prototypical networks, show that our method can improve the performance of existing models substantially with very"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02872","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":""},"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":"1807.02872","created_at":"2026-05-18T00:05:13.866064+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.02872v2","created_at":"2026-05-18T00:05:13.866064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02872","created_at":"2026-05-18T00:05:13.866064+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECEW5MYGE3AH","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECEW5MYGE3AH6SAW","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECEW5MYG","created_at":"2026-05-18T12:32:22.470017+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/ECEW5MYGE3AH6SAWBVYCD5KEXK","json":"https://pith.science/pith/ECEW5MYGE3AH6SAWBVYCD5KEXK.json","graph_json":"https://pith.science/api/pith-number/ECEW5MYGE3AH6SAWBVYCD5KEXK/graph.json","events_json":"https://pith.science/api/pith-number/ECEW5MYGE3AH6SAWBVYCD5KEXK/events.json","paper":"https://pith.science/paper/ECEW5MYG"},"agent_actions":{"view_html":"https://pith.science/pith/ECEW5MYGE3AH6SAWBVYCD5KEXK","download_json":"https://pith.science/pith/ECEW5MYGE3AH6SAWBVYCD5KEXK.json","view_paper":"https://pith.science/paper/ECEW5MYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.02872&json=true","fetch_graph":"https://pith.science/api/pith-number/ECEW5MYGE3AH6SAWBVYCD5KEXK/graph.json","fetch_events":"https://pith.science/api/pith-number/ECEW5MYGE3AH6SAWBVYCD5KEXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECEW5MYGE3AH6SAWBVYCD5KEXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECEW5MYGE3AH6SAWBVYCD5KEXK/action/storage_attestation","attest_author":"https://pith.science/pith/ECEW5MYGE3AH6SAWBVYCD5KEXK/action/author_attestation","sign_citation":"https://pith.science/pith/ECEW5MYGE3AH6SAWBVYCD5KEXK/action/citation_signature","submit_replication":"https://pith.science/pith/ECEW5MYGE3AH6SAWBVYCD5KEXK/action/replication_record"}},"created_at":"2026-05-18T00:05:13.866064+00:00","updated_at":"2026-05-18T00:05:13.866064+00:00"}