2 papers
cs.LG2025
MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCIL
Jinhui Pang, Changqing Lin, Hao Lin +4
Graph Few-Shot Class-Incremental Learning (GFSCIL) enables models to continually learn from limited samples of novel tasks after initial training on a large base dataset. Existing…
cs.CL2024
Enhancing Source Code Classification Effectiveness via Prompt Learning Incorporating Knowledge Features
Yong Ma, Senlin Luo, Yu-Ming Shang +2
Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on…