通过层间权重与激活的交互分析，量化神经网络对分布偏移的鲁棒性。
A New Framework to Analyse the Distributional Robustness of Deep Neural Networks
- 用伯努利分布建模层间权重与激活的交互，以类别分离度为鲁棒性指标。
- 在CIFAR-10和ImageNet上验证，能区分记忆训练数据与泛化模型。
- 适用于诊断模型表示结构，尤其适合关注模型鲁棒性的研究者。
深度神经网络在多种任务中表现优异，但其对分布偏移的脆弱性仍是实际部署的主要障碍。本文提出一种分析与量化神经网络分布鲁棒性的框架，通过研究层间权重与激活的交互实现。我们使用伯努利分布建模这些交互，并以类别间的分离度作为鲁棒性的诊断代理。在CIFAR-10和ImageNet上训练的模型验证了该框架的有效性。结果表明，所提指标能够区分记忆训练数据的网络与未记忆的网络。我们在激活空间也进行了类似实验，发现相同性质不成立。此外，我们研究了各类分布偏移下的指标行为，发现这些偏移会降低路径基准诊断中的分离度。结果表明，该框架可提供有价值的模型级诊断，揭示表示结构与鲁棒性之间的关系。
原文摘要 · Abstract (English)
Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant barrier to real-world deployment. In this paper, we propose a framework to analyse and quantify the distributional robustness of neural networks by studying the interactions between layer weights and activations. We model these interactions using Bernoulli distributions, using the separation between classes as a diagnostic proxy for robustness. We demonstrate the usefulness of this framework through models trained on CIFAR-10 and ImageNet. We show that our proposed metrics can distinguish between networks that have memorised their training data and those that have not. We also perform analogous experiments in the activation space and find that the same properties do not hold up. Additionally, we investigate the behaviour of our metrics under various distribution shifts and show that these shifts reduce separation under our path-based diagnostics. Our results suggest that this framework provides useful model-level diagnostics of representation structure and robustness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。