Timezone: »

A Causal View on Robustness of Neural Networks
Cheng Zhang · Kun Zhang · Yingzhen Li

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #805

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.

Author Information

Cheng Zhang (Microsoft Research, Cambridge, UK)
Kun Zhang (CMU)
Yingzhen Li (Microsoft Research Cambridge)

More from the Same Authors