Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting
and enhance their generalization and performance, various methods have been suggested …

Data augmentation (DA) is indispensable in modern machine learning and deep neural
networks. The basic idea of DA is to construct new training data to improve the model's …

Abstract Model heterogeneous federated learning is a realistic and challenging problem.
However, due to the limitations of data collection, storage, and transmission conditions, as …

Graph classification is a fundamental problem with diverse applications in bioinformatics
and chemistry. Due to the intricate procedures of manual annotations in graphical domains …

Abstract Generalization of Neural Networks is crucial for deploying them safely in the real
world. Common training strategies to improve generalization involve the use of data …

Federated learning is a distributed paradigm that allows multiple parties to collaboratively
train deep models without exchanging the raw data. However, the data distribution among …

Recently non-transferable learning (NTL) was proposed to restrict models' generalization
toward the target domain (s) which serves as state-of-the-art solutions for intellectual …

For many real-world applications, obtaining stable and robust statistical performance is more
important than simply achieving state-of-the-art predictive test accuracy, and thus robustness …

Abstract Supervised Person Re-identification (Person ReID) methods have achieved
excellent performance when training and testing within one camera network. However, they …

The robustness of neural networks has become increasingly important in real-world
applications where stable and reliable performance is valued over simply achieving high …