AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning by Minimizing the Sum of Ranked Range

Shu Hu, Yiming Ying, xin wang, Siwei Lyu

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 14 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use AoRR instead of AT_k aggregation with logistic lossLinear binary classifier · Monkerror rate (%): 16.76 -> 12.69Improved
Use AoRR instead of AT_k aggregation with hinge lossLinear binary classifier · Monkerror rate (%): 17.04 -> 13.17Improved
Use AoRR rather than AT_k aggregationLinear binary classifier · Australian, Phoneme, Titanic, and Spliceerror rate (%)Improved
Increase the excluded top-loss count m from zero while keeping k fixed (ablation)AoRR binary classifier · Four real-world datasetsmisclassification error rateMixed
Use TKML rather than LRMulti-label classifier · Emotions, k=2top-k multi-label accuracy (%): 57.48(3.35) -> 62.11(2.85)Improved
Use TKML rather than LRMulti-label classifier · Scene, k=3 to k=5top-k multi-label accuracy (%)Hurt
Choose TKML k near the average number of true labels (ablation)TKML multi-label classifier · Emotions and Yeasttop-k multi-label accuracyImproved
Use TKML instead of SVM_alpha under asymmetric label noiseMulti-class classifier · MNIST, noise level 0.4, Top-1accuracy (%): 68.32(0.32) -> 75(1.15)Improved
Use TKML rather than LSEPMulti-label classifier · Emotionsaverage precision (%): 82.66 -> 84.82Improved
Use TKML rather than LSEPMulti-label classifier · Scene and Yeastaverage precision (%)Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy