M Xie, S Li, L Yuan, C Liu, Z Dai - Advances in Neural …, 2024 - proceedings.neurips.cc
The capability of generalizing to out-of-distribution data is crucial for the deployment of machine learning models in the real world. Existing domain generalization (DG) mainly …
X Li, S Wang, J Sun, Z Xu - Pattern Recognition, 2023 - Elsevier
Deep neural networks suffer from the catastrophic forgetting phenomenon when trained on sequential tasks in continual learning, especially when data from previous tasks are …
G Saha, K Roy - Machine Vision and Applications, 2023 - Springer
Artificial learning systems aspire to mimic human intelligence by continually learning from a stream of tasks without forgetting past knowledge. One way to enable such learning is to …
Y Ding, B Guo, Y Liu, Y Jing, M Yin, N Li… - Information Processing …, 2025 - Elsevier
The prevalence of fake news on social media poses devastating and wide-ranging threats to political beliefs, economic activities, and public health. Due to the continuous emergence of …
Training at the edge utilizes continuously evolving data generated at different locations. Privacy concerns prohibit the co-location of this spatially as well as temporally distributed …
Y Luo, R Cong, X Liu, HHS Ip… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Existing continual image classification methods demonstrate that samples from all sequences of continual classification tasks contain common (task-invariant) features and …
Y Yang, J Huang, D Hu - Applied Soft Computing, 2024 - Elsevier
This paper develops a new method for lifelong learning referred to as Sparsify Dynamically Expandable Network (SDEN) via Variational Dropout, which explores a sparse model while …
Machine {\em unlearning} has emerged as a prominent and challenging area of interest, driven in large part by the rising regulatory demands for industries to delete user data upon …
In online continual learning, a neural network incrementally learns from a non-iid data stream. Nearly all online continual learning methods employ experience replay to …