Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

The success of artificial intelligence (AI) in multiple disciplines and vertical domains in recent
years has promoted the evolution of mobile networking and the future Internet toward an AI …

Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a
zero-shot classifier by discrete prompt design, eg, the confidence score of an image …

The goal of domain generalization (DG) is to enhance the generalization capability of the
model learned from a source domain to other unseen domains. The recently developed …

Abstract Federated Domain Generalization (FedDG) attempts to learn a global model in a
privacy-preserving manner that generalizes well to new clients possibly with domain shift …

Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

Shortcut Learning of Large Language Models in Natural Language Understanding Page 1 110
COMMUNICATIONS OF THE ACM | JANUARY 2024 | VOL. 67 | NO. 1 research IMA GE B Y …

Abstract Machine learning algorithms typically assume that training and test examples are
drawn from the same distribution. However, distribution shift is a common problem in real …

Deep neural networks often rely on spurious correlations to make predictions, which hinders
generalization beyond training environments. For instance, models that associate cats with …

Abstract Domain generalization (DG) aims to learn a generalized model to an unseen target
domain using only limited source domains. Previous attempts to DG fail to learn domain …