AI Paper Atlas

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

Theoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning Solution

Haixu Liao, Yating Zhou, Songyang Zhang, Meng Wang, Shuai Zhang

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 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
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR10-LT (rho=10)linear probe accuracy (%): 79.25 ± 1.03 -> 84.92 ± 0.67Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR10-LT (rho=50)linear probe accuracy (%): 75.58 ± 0.84 -> 83.60 ± 1.02Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR10-LT (rho=100)linear probe accuracy (%): 74.24 ± 0.82 -> 81.31 ± 0.94Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR100-LT (rho=10)linear probe accuracy (%): 51.21± 1.21 -> 56.33±1.51Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR100-LT (rho=50)linear probe accuracy (%): 49.32± 0.45 -> 56.12± 0.32Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR100-LT (rho=100)linear probe accuracy (%): 47.12±0.51 -> 54.93±0.50Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · ImageNet-LT (rho=256)linear probe accuracy (%): 63.21 -> 65.12Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR10-LT (rho=10)head-tail accuracy gap Delta20: 3.42±1.02 -> 2.99±0.92Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR10-LT (rho=50)head-tail accuracy gap Delta20: 3.92±1.21 -> 3.35± 0.76Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR10-LT (rho=100)head-tail accuracy gap Delta20: 5.69±1.35 -> 5.62±0.99Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR100-LT (rho=10)head-tail accuracy gap Delta20: 2.45±0.57 -> 1.37±0.46Improved
add magnitude-based neuron pruning to contrastive pretrainingcontrastive learning · CIFAR100-LT (rho=50)head-tail accuracy gap Delta20: 4.95±1.02 -> 2.57±0.92Improved

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