8 citations · 15 across the 8 of their papers we have counts for
4 papers · 1 filter
LoRA Dropout as a Sparsity Regularizer for Overfitting Control
Yang Lin, Xinyu Ma, Xu Chu +4
Parameter-efficient fine-tuning methods, represented by LoRA, play an essential role in adapting large-scale pre-trained models to downstream tasks. However, fine-tuning LoRA-serie…
Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation
Xinyu Ma, Xu Chu, Zhibang Yang +3
With the increasingly powerful performances and enormous scales of pretrained models, promoting parameter efficiency in fine-tuning has become a crucial need for effective and effi…
Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications
Xinyu Ma, Xu Chu, Yasha Wang +4
Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the…
Multi-Label Robust Factorization Autoencoder and its Application in Predicting Drug-Drug Interactions
Xu Chu, Yang Lin, Jingyue Gao +3
Drug-drug interactions (DDIs) are a major cause of preventable hospitalizations and deaths. Predicting the occurrence of DDIs helps drug safety professionals allocate investigative…