AI Paper Atlas

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

Discriminative Complementary-Label Learning with Weighted Loss

Yi Gao, Min-Ling Zhang

ICML 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning

Read the paper

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
Add weighted loss (L-W vs L-UW) to discriminative CLL model (ablation)discriminative CLL model · unbiased complementary labels, 6 dataset/model combostest accuracy: +0.24 MNIST linear, -0.37 MNIST MLP, +0.25 Fashion linear, +0.25 Fashion MLP, +0.42 Kuzushiji linear, +1.81 Kuzushiji MLMixed
Add weighted loss to discriminative CLL model (ablation)discriminative CLL model · biased complementary labels (Table 4, sets 1-3)test accuracy: L-W below L-UW on MNIST linear set 3 (79.72 vs 81.16) and MNIST MLP set 3 (85.91 vs 84.98 is above; set 3 Kuzushiji MLP Mixed
Discriminative complementary-loss model (L-UW) without weighting vs PC, NN, GA baselinesdiscriminative CLL model · unbiased complementary labels, MNIST/Fashion/Kuzushijitest accuracy: L-UW best or near-best in most cases, e.g. Kuzushiji linear 60.87 vs Forward 60.57Improved
Full L-W vs strongest baseline (Forward) on linear modelsdiscriminative CLL model · MNIST linear unbiasedtest accuracy: L-W 90.22 vs Forward 90.42 (below Forward)Mixed
Use MLP instead of linear model with GA baselineGA baseline · Kuzushiji unbiasedtest accuracy: GA 69.56 MLP vs 52.52 linear, yet L-W leads on linearMixed
Discriminative model (L-W) vs Forward on biased labels with linear modeldiscriminative CLL model · biased complementary labels, Kuzushiji linear set 3test accuracy: +3.44 (57.85 vs 54.41)Improved
Empirical risk of URE methods (PC, NN) with MLP goes to zero or negative, while GA stays stableURE-based CLL losses · MLP training, unbiasedtest accuracyHurt

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