← Search

Yiqin Dai

2 accepted papers

2023

“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors

ACL 2023findings

Deep neural networks (DNNs) are often used for text classification due to their high accuracy. However, DNNs can be computationally intensive, requiring millions of parameters and large amounts of labeled data, which can make them expensive to use, to optimize, and to transfer to out-of-distribution…

2022

Few-Shot Non-Parametric Learning with Deep Latent Variable Model

NeurIPS 2022accept

Most real-world problems that machine learning algorithms are expected to solve face the situation with (1) unknown data distribution; (2) little domain-specific knowledge; and (3) datasets with limited annotation. We propose Non-Parametric learning by Compression with Latent Variables (NPC-LV), a l…

Cited by 14SourcePDFScholar