Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (26) · 22191-22199
DOI: 10.1609/aaai.v40i26.39375 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Kangye Ji und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Sample selection is a straightforward technique to combat noisy labels, aiming to prevent mislabeled samples from degrading the robustness of neural networks. However, existing methods mitigate compounding selection bias either by leveraging dual-network disagreement or additional forward propagations, leading to multiplied training overhead. To address this challenge, we introduce Jump-teaching, an efficient sample selection framework for debiased model update and simplified selection criterion. Based on a key observation that a neural network exhibits significant disagreement across different training iterations, Jump-teaching proposes a jump-manner model update strategy to enable self-correction of selection bias by harnessing temporal disagreement, eliminating the need for multi-network or multi-round training. Furthermore, we employ a sample-wise selection criterion building on the intra variance of a decomposed single loss for a fine-grained selection without relying on batch-wise ranking or dataset-wise modeling. Extensive experiments demonstrate that Jump-teaching outperforms state-of-the-art counterparts while achieving a nearly overhead-free selection procedure, which boosts training speed by up to 4.47× and reduces peak memory footprint by 54%.
Zitieren
APA
Ji, K., Cheng, F., Wang, Z., Zhang, Q., & Huang, B. (2026). Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement. Proceedings of the AAAI Conference on Artificial Intelligence, 40(26), 22191-22199. https://doi.org/10.1609/aaai.v40i26.39375
Vancouver
Ji K, Cheng F, Wang Z, Zhang Q, Huang B. Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(26):22191-22199. doi:10.1609/aaai.v40i26.39375
BibTeX
@article{Ji2026,
author = {Ji, Kangye and Cheng, Fei and Wang, Zeqing and Zhang, Qichang and Huang, Bohu},
title = {Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {26},
pages = {22191--22199},
doi = {10.1609/aaai.v40i26.39375}
}
EUVIMED