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 …

When Machine Learning technologies are used in contexts that affect citizens, companies as
well as researchers need to be confident that there will not be any unexpected social …

Test-time training adapts to a new test distribution on the fly by optimizing a model for each
test input using self-supervision. In this paper, we use masked autoencoders for this one …

Federated Learning (FL) is a machine learning paradigm that allows decentralized clients to
learn collaboratively without sharing their private data. However, excessive computation and …

Federated learning has emerged as a promising paradigm for privacy-preserving
collaboration among different parties. Recently, with the popularity of federated learning, an …

The emerging paradigm of federated learning (FL) strives to enable collaborative training of
deep models on the network edge without centrally aggregating raw data and hence …

Classical machine learning assumes that the training and test sets come from the same
distributions. Therefore, a model learned from the labeled training data is expected to …

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a
labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA …

We propose a simple but effective source-free domain adaptation (SFDA) method. Treating
SFDA as an unsupervised clustering problem and following the intuition that local neighbors …

Federated learning shows a bright promise as a privacy-preserving collaborative learning
technique. However, prevalent solutions mainly focus on all private data sampled from the …