AI Paper Atlas

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

Sum of Ranked Range Loss for Supervised Learning

Shu Hu, Yiming Ying, Xin Wang, Siwei Lyu

JMLR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data

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 average aggregate loss (logistic)linear classifier · Monkerror rate (%): 20.46 -> 12.69Improved
use AoRR instead of AT_k aggregate loss (logistic)linear classifier · Monkerror rate (%): 16.76 -> 12.69Improved
use AoRR instead of AT_k aggregate loss (hinge)linear classifier · Monkerror rate (%): 17.04 -> 13.17Improved
use AoRR instead of AT_k aggregate loss (logistic)linear classifier · Phonemeerror rate (%): 24.17 -> 21.95Improved
use AoRR instead of AT_k aggregate loss (logistic)linear classifier · Titanicerror rate (%): 22.44 -> 21.69Improved
use AoRR instead of AT_k aggregate loss (logistic)linear classifier · Australianerror rate (%): 11.7 -> 11.42Improved
use AoRR instead of AT_k aggregate loss (hinge)linear classifier · Australianerror rate (%): 12.51 -> 12.5Improved
exclude the m largest individual losses (increase m) in AoRRAoRR logistic · four real data setserror rateMixed
use AoRR instead of AT_k on MNIST noise 0.2softmax loss · MNIST symmetric noise 0.2accuracy (%): 89.71 -> 92.42Improved
use AoRR instead of AT_k on MNIST noise 0.3softmax loss · MNIST symmetric noise 0.3accuracy (%): 88.73 -> 92.26Improved
use AoRR instead of AT_k on MNIST noise 0.4softmax loss · MNIST symmetric noise 0.4accuracy (%): 87.62 -> 91.87Improved
use AT_k instead of average loss on MNIST noisy labelssoftmax loss · MNIST symmetric noise 0.2accuracy (%): 89.69 -> 89.71No clear effect

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