{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JPD3RASUMLS7USEGQNWWM5USRS","short_pith_number":"pith:JPD3RASU","schema_version":"1.0","canonical_sha256":"4bc7b8825462e5fa4886836d6676928cb818a24f657e06563a9e64deed843946","source":{"kind":"arxiv","id":"2305.10309","version":1},"attestation_state":"computed","paper":{"title":"MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cees G.M. Snoek, Fan Wang, Ling Wang, Wenfang Sun, Xiantong Zhen, Yingjun Du","submitted_at":"2023-05-17T15:47:47Z","abstract_excerpt":"Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for few-shot learning with fewer tasks, which we call MetaModulation. The key idea is to use a neural network to increase the density of the meta-training tasks by modulating batch normalization parameters during meta-training. Additionally, we modify parameters at various network levels, rather than just a single layer, to increase task diversity. To account for the "},"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":"2305.10309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-17T15:47:47Z","cross_cats_sorted":[],"title_canon_sha256":"ad4183a2d1d9591549f071e58601f346e7f18fc143ce79688a55047441f6fc75","abstract_canon_sha256":"4684263dff772b1f3626b916bd2d50b7f428f1ce4860b3ddf5439d1287f4123f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:12.285029Z","signature_b64":"qrec/V7HDAYB+ROs0n6Za4OU2+erdnbsbQOHdD8AGb8gliPDBK1pKC3Vik/CDTg9fL3cNY6aw2o2sTprAA7ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc7b8825462e5fa4886836d6676928cb818a24f657e06563a9e64deed843946","last_reissued_at":"2026-07-05T06:11:12.284652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:12.284652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cees G.M. Snoek, Fan Wang, Ling Wang, Wenfang Sun, Xiantong Zhen, Yingjun Du","submitted_at":"2023-05-17T15:47:47Z","abstract_excerpt":"Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for few-shot learning with fewer tasks, which we call MetaModulation. The key idea is to use a neural network to increase the density of the meta-training tasks by modulating batch normalization parameters during meta-training. Additionally, we modify parameters at various network levels, rather than just a single layer, to increase task diversity. To account for the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10309","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/2305.10309/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":"2305.10309","created_at":"2026-07-05T06:11:12.284706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10309v1","created_at":"2026-07-05T06:11:12.284706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10309","created_at":"2026-07-05T06:11:12.284706+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPD3RASUMLS7","created_at":"2026-07-05T06:11:12.284706+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPD3RASUMLS7USEG","created_at":"2026-07-05T06:11:12.284706+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPD3RASU","created_at":"2026-07-05T06:11:12.284706+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/JPD3RASUMLS7USEGQNWWM5USRS","json":"https://pith.science/pith/JPD3RASUMLS7USEGQNWWM5USRS.json","graph_json":"https://pith.science/api/pith-number/JPD3RASUMLS7USEGQNWWM5USRS/graph.json","events_json":"https://pith.science/api/pith-number/JPD3RASUMLS7USEGQNWWM5USRS/events.json","paper":"https://pith.science/paper/JPD3RASU"},"agent_actions":{"view_html":"https://pith.science/pith/JPD3RASUMLS7USEGQNWWM5USRS","download_json":"https://pith.science/pith/JPD3RASUMLS7USEGQNWWM5USRS.json","view_paper":"https://pith.science/paper/JPD3RASU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10309&json=true","fetch_graph":"https://pith.science/api/pith-number/JPD3RASUMLS7USEGQNWWM5USRS/graph.json","fetch_events":"https://pith.science/api/pith-number/JPD3RASUMLS7USEGQNWWM5USRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPD3RASUMLS7USEGQNWWM5USRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPD3RASUMLS7USEGQNWWM5USRS/action/storage_attestation","attest_author":"https://pith.science/pith/JPD3RASUMLS7USEGQNWWM5USRS/action/author_attestation","sign_citation":"https://pith.science/pith/JPD3RASUMLS7USEGQNWWM5USRS/action/citation_signature","submit_replication":"https://pith.science/pith/JPD3RASUMLS7USEGQNWWM5USRS/action/replication_record"}},"created_at":"2026-07-05T06:11:12.284706+00:00","updated_at":"2026-07-05T06:11:12.284706+00:00"}