637 citations · 642 across the 5 of their papers we have counts for
4 papers · 1 filter
Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting
Xiang Yuan, Kaiqing Lei, Zhenyu Jin +3
The performance of Large Language Models (LLMs) is fundamentally influenced by the distributional composition of multi-domain pre-training data. While manual heuristics were preval…
Feed Two Birds with One Scone: Exploiting Function-Space Regularization for Both OOD Robustness and ID Fine-Tuning Performance
Xiang Yuan, Jun Shu, Deyu meng +1
Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring…
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning
Jun Shu, Xiang Yuan, Deyu Meng +1
Meta learning recently has been heavily researched and helped advance the contemporary machine learning. However, achieving well-performing meta-learning model requires a large amo…
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning
Jun Shu, Xiang Yuan, Deyu Meng +1
Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate t…