Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
Liu, Jingren, Ji, Zhong, Yu, YunLong, Cao, Jiale, Pang, Yanwei, Han, Jungong, Li, Xuelong
–arXiv.org Artificial Intelligence
Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting problem. However, understanding the mechanisms that dictate continual performance in this paradigm remains elusive. To tackle this complexity, we undertake a rigorous analysis of PEFT-CL dynamics to derive relevant metrics for continual scenarios using Neural Tangent Kernel (NTK) theory. With the aid of NTK as a mathematical analysis tool, we recast the challenge of test-time forgetting into the quantifiable generalization gaps during training, identifying three key factors that influence these gaps and the performance of PEFT-CL: training sample size, task-level feature orthogonality, and regularization. To address these challenges, we introduce NTK-CL, a novel framework that eliminates task-specific parameter storage while adaptively generating task-relevant features. Aligning with theoretical guidance, NTK-CL triples the feature representation of each sample, theoretically and empirically reducing the magnitude of both task-interplay and task-specific generalization gaps. Grounded in NTK analysis, our approach imposes an adaptive exponential moving average mechanism and constraints on task-level feature orthogonality, maintaining intra-task NTK forms while attenuating inter-task NTK forms. Ultimately, by fine-tuning optimizable parameters with appropriate regularization, NTK-CL achieves state-of-the-art performance on established PEFT-CL benchmarks. This work provides a theoretical foundation for understanding and improving PEFT-CL models, offering insights into the interplay between feature representation, task orthogonality, and generalization, contributing to the development of more efficient continual learning systems.
arXiv.org Artificial Intelligence
Jul-24-2024
- Country:
- Europe
- Asia > China
- Tianjin Province > Tianjin (0.05)
- Zhejiang Province > Hangzhou (0.04)
- Shanghai > Shanghai (0.04)
- Jiangsu Province > Nanjing (0.04)
- Shaanxi Province > Xi'an (0.04)
- Beijing > Beijing (0.04)
- Anhui Province > Hefei (0.04)
- Genre:
- Research Report (1.00)
- Industry:
- Education > Educational Setting > Online (0.45)
- Technology: