{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ASU2IVFM6JTBTKTXNOAOM6XRB2","short_pith_number":"pith:ASU2IVFM","schema_version":"1.0","canonical_sha256":"04a9a454acf26619aa776b80e67af10ebac68528c868223ae62ae70824b786e7","source":{"kind":"arxiv","id":"2208.02951","version":1},"attestation_state":"computed","paper":{"title":"Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dandan Guo, He Zhao, Hongyuan Zha, Meixi Zheng, Mingyuan Zhou, Zhuo Li","submitted_at":"2022-08-05T01:23:54Z","abstract_excerpt":"Imbalanced data pose challenges for deep learning based classification models. One of the most widely-used approaches for tackling imbalanced data is re-weighting, where training samples are associated with different weights in the loss function. Most of existing re-weighting approaches treat the example weights as the learnable parameter and optimize the weights on the meta set, entailing expensive bilevel optimization. In this paper, we propose a novel re-weighting method based on optimal transport (OT) from a distributional point of view. Specifically, we view the training set as an imbalan"},"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":"2208.02951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-05T01:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"6d6f9e3a4710c6c1c69ceb2731187bfc1149556aae4e42446e381ba958ef622a","abstract_canon_sha256":"fcf105dc40411389015386608f0ff93599b2f6118b959dfc42ae3bdfa470ae03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:17.923459Z","signature_b64":"PhYq+dylI1UlzCz9JYlxyvkdRa6PEW9QJtBUlBaLm+pHf/GhxdgoSbfhOMMGE7kt+wOmqFwhRGz2fWzPkneVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04a9a454acf26619aa776b80e67af10ebac68528c868223ae62ae70824b786e7","last_reissued_at":"2026-07-05T04:46:17.923051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:17.923051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dandan Guo, He Zhao, Hongyuan Zha, Meixi Zheng, Mingyuan Zhou, Zhuo Li","submitted_at":"2022-08-05T01:23:54Z","abstract_excerpt":"Imbalanced data pose challenges for deep learning based classification models. One of the most widely-used approaches for tackling imbalanced data is re-weighting, where training samples are associated with different weights in the loss function. Most of existing re-weighting approaches treat the example weights as the learnable parameter and optimize the weights on the meta set, entailing expensive bilevel optimization. In this paper, we propose a novel re-weighting method based on optimal transport (OT) from a distributional point of view. Specifically, we view the training set as an imbalan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.02951","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/2208.02951/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":"2208.02951","created_at":"2026-07-05T04:46:17.923107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.02951v1","created_at":"2026-07-05T04:46:17.923107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.02951","created_at":"2026-07-05T04:46:17.923107+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASU2IVFM6JTB","created_at":"2026-07-05T04:46:17.923107+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASU2IVFM6JTBTKTX","created_at":"2026-07-05T04:46:17.923107+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASU2IVFM","created_at":"2026-07-05T04:46:17.923107+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/ASU2IVFM6JTBTKTXNOAOM6XRB2","json":"https://pith.science/pith/ASU2IVFM6JTBTKTXNOAOM6XRB2.json","graph_json":"https://pith.science/api/pith-number/ASU2IVFM6JTBTKTXNOAOM6XRB2/graph.json","events_json":"https://pith.science/api/pith-number/ASU2IVFM6JTBTKTXNOAOM6XRB2/events.json","paper":"https://pith.science/paper/ASU2IVFM"},"agent_actions":{"view_html":"https://pith.science/pith/ASU2IVFM6JTBTKTXNOAOM6XRB2","download_json":"https://pith.science/pith/ASU2IVFM6JTBTKTXNOAOM6XRB2.json","view_paper":"https://pith.science/paper/ASU2IVFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.02951&json=true","fetch_graph":"https://pith.science/api/pith-number/ASU2IVFM6JTBTKTXNOAOM6XRB2/graph.json","fetch_events":"https://pith.science/api/pith-number/ASU2IVFM6JTBTKTXNOAOM6XRB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASU2IVFM6JTBTKTXNOAOM6XRB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASU2IVFM6JTBTKTXNOAOM6XRB2/action/storage_attestation","attest_author":"https://pith.science/pith/ASU2IVFM6JTBTKTXNOAOM6XRB2/action/author_attestation","sign_citation":"https://pith.science/pith/ASU2IVFM6JTBTKTXNOAOM6XRB2/action/citation_signature","submit_replication":"https://pith.science/pith/ASU2IVFM6JTBTKTXNOAOM6XRB2/action/replication_record"}},"created_at":"2026-07-05T04:46:17.923107+00:00","updated_at":"2026-07-05T04:46:17.923107+00:00"}