Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively
Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by overfitting and representation degradation. In this paper, we propose a Dynamic Parameter Selection (DPS) algorithm for the large-scale pre-trained models during fine-tuning, which adaptively selects a more promising subnetwork to perform staging updates based on gradients of back-propagation. Experiments on the GLUE benchmark show that DPS outperforms previous fine-tuning methods in terms of overall performance and stability, and consistently achieves better results with variable pre-trained language models. In addition, DPS brings a large magnitude of improvement in out-of-domain transferring experiments and low-resource scenarios, which shows that it can maintain stable general contextual features and reduce the representation collapse. We release our code at https://github.com/ZhangHaojie077/DPS
Code (1)
Tasks
Language ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and semantic generalization. …
Action GenerationChunkingImitation LearningVision-Language-ActionOptimizing Multi-Modality Trackers via Significance-Regularized Tuning
This paper tackles the critical challenge of optimizing multi-modality trackers by effectively adapting pre-trained models for RGB data. Existing fine-tuning paradigms oscillate between excessive flexibility and over-res…
Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as harmful fine-tuning attacks. In this wor…
Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
Recent large-scale generative models enable high-quality 3D synthesis. However, the public accessibility of pre-trained weights introduces a critical vulnerability. Adversaries can fine-tune these models to steal special…
Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs
Large Language Models (LLMs) for public use require continuous pre-training to remain up-to-date with the latest data. The models also need to be fine-tuned with specific instructions to maintain their ability to follow …
Instruction Following