Domain generalization: A survey

K Zhou, Z Liu, Y Qiao, T **ang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
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 …

Edge-cloud polarization and collaboration: A comprehensive survey for ai

J Yao, S Zhang, Y Yao, F Wang, J Ma… - … on Knowledge and …, 2022 - ieeexplore.ieee.org
Influenced by the great success of deep learning via cloud computing and the rapid
development of edge chips, research in artificial intelligence (AI) has shifted to both of the …

Fishr: Invariant gradient variances for out-of-distribution generalization

A Rame, C Dancette, M Cord - International Conference on …, 2022 - proceedings.mlr.press
Learning robust models that generalize well under changes in the data distribution is critical
for real-world applications. To this end, there has been a growing surge of interest to learn …

On learning contrastive representations for learning with noisy labels

L Yi, S Liu, Q She, AI McLeod… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Deep neural networks are able to memorize noisy labels easily with a softmax cross entropy
(CE) loss. Previous studies attempted to address this issue focus on incorporating a noise …

Invariant information bottleneck for domain generalization

B Li, Y Shen, Y Wang, W Zhu, D Li, K Keutzer… - Proceedings of the …, 2022 - ojs.aaai.org
Invariant risk minimization (IRM) has recently emerged as a promising alternative for domain
generalization. Nevertheless, the loss function is difficult to optimize for nonlinear classifiers …

Environment-aware dynamic graph learning for out-of-distribution generalization

H Yuan, Q Sun, X Fu, Z Zhang, C Ji… - Advances in Neural …, 2024 - proceedings.neurips.cc
Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-
temporal patterns on dynamic graphs. However, existing works fail to generalize under …

Graph domain adaptation via theory-grounded spectral regularization

Y You, T Chen, Z Wang, Y Shen - The eleventh international conference …, 2023 - par.nsf.gov
Transfer learning on graphs drawn from varied distributions (domains) is in great demand
across many applications. Emerging methods attempt to learn domain-invariant …

Federated domain generalization: A survey

Y Li, X Wang, R Zeng, PK Donta, I Murturi… - arxiv preprint arxiv …, 2023 - arxiv.org
Machine learning typically relies on the assumption that training and testing distributions are
identical and that data is centrally stored for training and testing. However, in real-world …

Prior knowledge guided unsupervised domain adaptation

T Sun, C Lu, H Ling - European conference on computer vision, 2022 - Springer
The waive of labels in the target domain makes Unsupervised Domain Adaptation (UDA) an
attractive technique in many real-world applications, though it also brings great challenges …

Learning distinctive margin toward active domain adaptation

M **e, Y Li, Y Wang, Z Luo, Z Gan… - Proceedings of the …, 2022 - openaccess.thecvf.com
Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under
unsupervised or few-shot semi-supervised settings, recently the solution of active learning …