Monitoring Shortcut Learning using Mutual Information
浏览论文内容
英文摘要
The failure of deep neural networks to generalize to out-of-distribution data is a well-known problem and raises concerns about the deployment of trained networks in safety-critical domains such as healthcare, finance and autonomous vehicles. We study a particular kind of distribution shift $\unicode{x2013}$ shortcuts or spurious correlations in the training data. Shortcut learning is often only exposed when models are evaluated on real-world data that does not contain the same spurious correlations, posing a serious dilemma for AI practitioners to properly assess the effectiveness of a trained model for real-world applications. In this work, we propose to use the mutual information (MI) between the learned representation and the input as a metric to find where in training, the network latches onto shortcuts. Experiments demonstrate that MI can be used as a domain-agnostic metric for monitoring shortcut learning.
发表机构
- University of Guelph（圭尔夫大学）
- Vector Institute（向量研究所）
- University of Calgary（卡尔加里大学）
- Mayo Clinic（梅奥诊所）
- University of Waterloo（滑铁卢大学）
机构由 AI 辅助整理，请以论文原文为准。
