Justin and Dan discuss “non-robust features” as a special case of models being non-robust because they latch on to superficial correlations, a view often found in the distributional robustness literature. As an example, they discuss recent analysis of how neural networks behave in frequency space. They emphasize we should think about a broader notion of robustness. Read Full Article
The demonstration of models that learn from only high-frequency components of the data is an interesting finding that provides us with another way our models can learn from data that appears “meaningless” to humans. The authors fully agree that studying a wider notion of robustness will become increasingly important in ML, and will help us get a better grasp of features we actually want our models to rely on.