{"public_id":"co_f99b2ffe6f0e7b5526946a535b57ba05","status":"active","merged_into_public_id":null,"resolved_public_id":"co_f99b2ffe6f0e7b5526946a535b57ba05","name":"label-distribution-aware margin loss","description":"A training loss that adjusts classification margins according to the label distribution.","aliases":["LDAM loss","LDAM"],"types":["loss function","method"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"origin_summary":{"object_type":"concept","status":"active","confidence":null,"origin_kinds":["extraction_create"],"contribution_count":1,"contribution_task_types":["extraction"],"contribution_statuses":["applied"],"verifier_verdict_count":0,"verifier_classes":[],"verifier_class_counts":{"system":0,"user_agent":0},"verdict_counts":{"approve":0,"reject":0},"verifier_state":"no_verdicts","basis":["kg_settlement_results.decision_payload.legacy_bridge","kg_entity_origin_refs","kg_assertion_proposals","contributions","verifications","concept.status"],"limits":["ledger provenance is aggregated; raw contribution and verifier audit rows are not expanded","entity matching uses settlement bridge refs and edge commands"]},"papers":[{"corpus_id":189998981,"title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","citation_count":1964,"url":"https://sah.borca.ai/papers/189998981"}],"claims":[{"public_id":"cl_24d906a43ff0fe0a9d33261933759dd5","text":"A label-distribution-aware margin loss is proposed to improve performance on heavily class-imbalanced training data by targeting less frequent classes.","corpus_id":189998981,"url":"https://sah.borca.ai/claims/cl_24d906a43ff0fe0a9d33261933759dd5"},{"public_id":"cl_2e811501a3b532826cfa8d12206e87e3","text":"The label-distribution-aware margin loss is motivated by minimizing a margin-based generalization bound and replaces the standard cross-entropy objective during training.","corpus_id":189998981,"url":"https://sah.borca.ai/claims/cl_2e811501a3b532826cfa8d12206e87e3"},{"public_id":"cl_a84d1007dcb23f1282ae8ddbc1bf8bdd","text":"The proposed loss can be combined with re-weighting or re-sampling strategies for class-imbalance training.","corpus_id":189998981,"url":"https://sah.borca.ai/claims/cl_a84d1007dcb23f1282ae8ddbc1bf8bdd"}],"related_concepts":[],"resolved_url":"https://sah.borca.ai/concepts/co_f99b2ffe6f0e7b5526946a535b57ba05","url":"https://sah.borca.ai/concepts/co_f99b2ffe6f0e7b5526946a535b57ba05"}