Research map / Label-efficient and robust learning / Recognition and long-tail
Multilabel reductions: what is my loss optimising?
Aditya K Menon, Ankit Singh Rawat, Sashank Reddi, Sanjiv Kumar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use unnormalised pick-all-labels (PAL) reduction instead of normalised PAL-N (ablation) | PAL multilabel reduction, linear scorer · Synthetic two-Gaussian multilabel data, L=10 | precision@k | Improved |
| Use normalised PAL-N reduction instead of unnormalised PAL (ablation) | PAL multilabel reduction, linear scorer · Synthetic two-Gaussian multilabel data, L=10 | recall@k | Improved |
Closest papers by meaning
- Multi-label classification: do Hamming loss and subset accuracy really conflict with each other? (NeurIPS 2020 · similarity 0.90)
- Two-Way Multi-Label Loss (CVPR 2023 · similarity 0.88)
- Large Loss Matters in Weakly Supervised Multi-Label Classification (CVPR 2022 · similarity 0.88)
- Multi-Label Learning with Stronger Consistency Guarantees (NeurIPS 2024 · similarity 0.88)
- Regret Bounds for Multilabel Classification in Sparse Label Regimes (NeurIPS 2022 · similarity 0.87)
- Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization (NeurIPS 2021 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
