2022年4月24日
Do We Need Zero Training Loss After Achieving Zero Training Error?
摘要： Ishida T., Yamane I., Sakai T., Niu G. and Sugiyama M. Do we need zero training loss after achieving zero training error? In International Conference 阅读全文
posted @ 2022-04-24 21:59 馒头and花卷 阅读(384) 评论(0) 推荐(1)
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning
摘要： Flooding-X: improving bert’s resistance to adversarial attacks via loss-restricted fine-tuning. 概 作者认为通过 flooding 能够使得 loss landscape 平滑, 这有利于抵抗对抗攻击. 阅读全文
posted @ 2022-04-24 21:56 馒头and花卷 阅读(398) 评论(0) 推荐(1)
Fake News Detection on Social Media Using Geometric Deep Learning
摘要： [1] Monti F., Frasca F., Eynard D., Mannion D. and Bronstein M. M. Fake news detection on social media using geometric deep learning. In International 阅读全文
posted @ 2022-04-24 12:28 馒头and花卷 阅读(250) 评论(0) 推荐(1)