7 papers
Contrastive Learning on Multimodal Analysis of Electronic Health Records
Tianxi Cai, Feiqing Huang, Ryumei Nakada +2
Electronic health record (EHR) systems capture a wealth of multimodal clinical data, encompassing both structured clinical codes and unstructured clinical notes. Yet, many EHR-focu…
Residual Feature Integration is Sufficient to Prevent Negative Transfer
Yichen Xu, Ryumei Nakada, Linjun Zhang +1
Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative transfer, where leveraging source representati…
Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance
Ryumei Nakada, Yichen Xu, Lexin Li +1
Imbalanced classification and spurious correlation are common challenges in data science and machine learning. Both issues are linked to data imbalance, with certain groups of data…
PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers
Yibo Zhong, Haoxiang Jiang, Lincan Li +5
Fine-tuning large pre-trained foundation models often yields excellent downstream performance but is prohibitively expensive when updating all parameters. Parameter-efficient fine-…
Contrastive Network Representation Learning
Zihan Dong, Xin Zhou, Ryumei Nakada +2
Network representation learning seeks to embed networks into a low-dimensional space while preserving the structural and semantic properties, thereby facilitating downstream tasks…
A Theoretical Framework for Prompt Engineering: Approximating Smooth Functions with Transformer Prompts
Ryumei Nakada, Wenlong Ji, Tianxi Cai +2
Prompt engineering has emerged as a powerful technique for guiding large language models (LLMs) toward desired responses, significantly enhancing their performance across diverse t…