S1 firsts gives some of the formal definitions and interpretations omitted from the main paper due to space limitations.

This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing methods severely suffer from catastrophic forgetting, awell-known problem in incremental learning, which is aggravated due to data scarcity andimbalance inthefew-shot setting.

However,itsextension tosolvingstochastic min-max problems withstrong convexity and strong concavity still remains open, and itisstill unclear whether a fast rate ofO(1/T) for the duality gapis achievable for stochastic min-max optimization under strong convexity and strong concavity.

Here, by contrast, we propose to explicitly model thehuman-scenecontacts.