Learning to double-check model prediction from a causal perspective

• Main Authors: Deng, Xun, Feng, Fuli, Wang, Xiang, He, Xiangnan, Zhang, Hanwang, Chua, Tat-Seng
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Causality; Classification
• Online Access: https://hdl.handle.net/10356/170568
• Institution: Nanyang Technological University

The present machine learning schema typically uses a one-pass model inference (e.g., forward propagation) to make predictions in the testing phase. It is inherently different from human students who double-check the answer during examinations especially when the confidence is low. To bridge this gap...