A Causal View on Robustness of Neural Networks
This work addresses robustness issues in neural networks for general measurement data, offering a novel causal approach that is incremental in improving existing methods.
The authors tackled the problem of neural network robustness against input manipulations by proposing a causal view and a deep causal manipulation augmented model (deep CAMA), which showed superior robustness against unseen manipulations compared to discriminative deep neural networks.
We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data. Based on this view, we design a deep causal manipulation augmented model (deep CAMA) which explicitly models possible manipulations on certain causes leading to changes in the observed effect. We further develop data augmentation and test-time fine-tuning methods to improve deep CAMA's robustness. When compared with discriminative deep neural networks, our proposed model shows superior robustness against unseen manipulations. As a by-product, our model achieves disentangled representation which separates the representation of manipulations from those of other latent causes.