报告题目：Delving into the Calibratability of Deep Neural Networks

报告人：张敏灵 教授（东南大学 计算机科学与工程学院）

主持人：孙仕亮 教授，赵静 副研究员

报告时间：2023年10月21日（星期六）09:00-09:40

报告地点：腾讯会议，会议号：830 424 730

报告摘要：

Reliable predictive models should be accurate when they are confident about their predictions and indicate high uncertainty when they are likely to be inaccurate. However, modern DNNs trained with cross-entropy (CE) loss, despite being highly accurate, have been recently found to predict poorly calibrated probabilities, unlike traditional models trained with the same objective. In recent years, many approaches have been proposed to improve DNNs’calibration performance while maintain their accuracy. Differing from prior researches, our recent studies focus on the calibratability, which refers to the extent to which a model can be calibrated during the post-calibration phase. Our studies show a disparity between models’ calibration performance and their calibratability. Specifically, we found that despite models trained with existing calibration methods are better calibrated, they suffer from not being as calibratable as regularly trained models, namely, it is harder to further calibrate these models with post-hoc calibration approaches. Taking Label Smoothing and Mixup as two illustrative cases, our recent work highlights some surprising phenomena concerning calibrability and offers potential avenues for this issue.

报告人简介：

       张敏灵，东南大学计算机科学与工程学院教授，经理。主要研究领域为机器学习、数据挖掘。现任中国人工智能学会机器学习专委会副主任、江苏省人工智能学会副理事长等。现任《中国科学：信息科学》、《IEEE Trans. PAMI》、《ACM Trans. IST》、《Frontiers of Computer Science》、《Machine Intelligence Research》等期刊编委。应邀担任ACML、PAKDD指导委员会委员，PRICAI/CCF-ICAI/CCFAI等国内外学术会议程序主席，以及KDD/IJCAI/AAAI/ICDM等国际会议领域主席或资深程序委员50余次。曾获CCF - IEEE CS青年科学家奖（2016）、国家杰出青年科学基金（2022）等。