Kezhi Kong

Data Augmentation for Meta-Learning

2020 · arXiv (Cornell University)

Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for sampling. In contrast, meta-learning algorithms …

Robust Optimization as Data Augmentation for Large-scale Graphs

2020 · arXiv (Cornell University)

Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). While most …

OpenTab: Advancing Large Language Models as Open-domain Table Reasoners

2024 · arXiv (Cornell University)

Large Language Models (LLMs) trained on large volumes of data excel at various natural language tasks, but they cannot handle tasks requiring knowledge that has not been trained on previously. One solution is to use …