DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models

Abstract

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the pre-trained models grow bigger (e.g., 175B parameters for GPT-3), even the fine-tuning process can be time-consuming and computationally expensive; (b) the fine-tuned model has the same size as its starting point by default, which is neither sensible due to its more specialized functionality, nor practical since many fine-tuned models will be deployed in resource-constrained environments. To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning - by enforcing sparsity-aware low-rank updates on top of the pre-trained weights; and (ii) resource-efficient inference - by encouraging a sparse weight structure towards the final fine-tuned model. We leverage sparsity in these two directions by exploiting both unstructured and structured sparse patterns in pre-trained language models via a unified approach. Extensive experiments and in-depth investigations, with diverse network backbones (i.e., BERT, RoBERTa, and GPT-2) on dozens of datasets, consistently demonstrate impressive parameter-/inference-efficiency, while maintaining competitive downstream performance. For instance, DSEE saves about 25% inference FLOPs while achieving comparable performance, with 0.5% trainable parameters on BERT. Codes are available in https://github.com/VITA-Group/DSEE.

Accepted by ACL 2023

References in corpus (11)

• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Language Models are Few-Shot Learners
• LoRA: Low-Rank Adaptation of Large Language Models
• ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
• Learning Structured Sparsity in Deep Neural Networks
• DeBERTa: Decoding-enhanced BERT with Disentangled Attention
• Prefix-Tuning: Optimizing Continuous Prompts for Generation
• Picking Winning Tickets Before Training by Preserving Gradient Flow
• Structured Pruning of a BERT-based Question Answering Model
• Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian
• Parameter-Efficient Transfer Learning with Diff Pruning