← Search

Weichen Lin

2 accepted papers

2025

To Tackle Adversarial Transferability: A Novel Ensemble Training Method with Fourier Transformation

ICLR 2025poster

Ensemble methods are commonly used for enhancing robustness in machine learning. However, due to the ''transferability'' of adversarial examples, the performance of an ensemble model can be seriously affected even it contains a set of independently trained sub-models. To address this issue, we prop…

Cited by 0SourcePDFScholar
2024

An Effective Dynamic Gradient Calibration Method for Continual Learning

ICML 2024poster

Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the ``catastrophic forgetting'' problem, i.e., the performance on…

Cited by 3SourcePDFScholar