How fine can fine-tuning be? Learning efficient language models

• URL: http://arxiv.org/abs/2004.14129v1
• Date: Fri, 24 Apr 2020 20:31:28 GMT
• Title: How fine can fine-tuning be? Learning efficient language models
• Authors: Evani Radiya-Dixit and Xin Wang
• Abstract summary: Given a language model pre-trained on massive unlabeled text corpora, only very light supervised fine-tuning is needed to learn a task. We show that it suffices to fine-tune only the most critical layers. As a result, fine-tuning of huge language models can be achieved by simply setting a certain number of entries in certain layers of the pre-trained parameters to zero.
• Score: 8.25186900320093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only very light supervised fine-tuning is needed to learn a task: the number of fine-tuning steps is typically five orders of magnitude lower than the total parameter count. Does this mean that fine-tuning only introduces small differences from the pre-trained model in the parameter space? If so, can one avoid storing and computing an entire model for each task? In this work, we address these questions by using Bidirectional Encoder Representations from Transformers (BERT) as an example. As expected, we find that the fine-tuned models are close in parameter space to the pre-trained one, with the closeness varying from layer to layer. We show that it suffices to fine-tune only the most critical layers. Further, we find that there are surprisingly many good solutions in the set of sparsified versions of the pre-trained model. As a result, fine-tuning of huge language models can be achieved by simply setting a certain number of entries in certain layers of the pre-trained parameters to zero, saving both task-specific parameter storage and computational cost.

Related papers

• Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning [60.26952378997713]
  Contrastive vision-language models (e.g. CLIP) are created by updating all the parameters of a vision model and language model through contrastive training. We show that a minimal set of parameter updates ($$7%) can achieve the same performance as full-model training. We describe a series of experiments: we show that existing knowledge is conserved more strongly in parameter-efficient training.
  arXiv  Detail & Related papers  (2023-03-21T14:12:08Z)
• Task-Specific Skill Localization in Fine-tuned Language Models [36.53572616441048]
  This paper introduces the term skill localization for this problem. A simple optimization is used to identify a very small subset of parameters. grafting the fine-tuned values for just this tiny subset onto the pre-trained model gives performance almost as well as the fine-tuned model.
  arXiv  Detail & Related papers  (2023-02-13T18:55:52Z)
• Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective [26.41585967095811]
  Zero-shot learning aims to train a model on a given task such that it can address new learning tasks without any additional training. Our approach converts zero-shot learning into multiple-choice tasks, avoiding problems in commonly used large-scale generative models such as FLAN. Our approach shows state-of-the-art performance on several benchmarks and produces satisfactory results on tasks such as natural language inference and text classification.
  arXiv  Detail & Related papers  (2022-10-16T17:24:06Z)
• Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency [62.0887259003594]
  This work investigates three aspects of structured pruning on multilingual pre-trained language models: settings, algorithms, and efficiency. Experiments on nine downstream tasks show several counter-intuitive phenomena. We present Dynamic Sparsification, a simple approach that allows training the model once and adapting to different model sizes at inference.
  arXiv  Detail & Related papers  (2022-04-06T06:29:52Z)
• PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models [67.3725459417758]
  PERFECT is a simple and efficient method for few-shot fine-tuning of PLMs without relying on any such handcrafting. We show that manually engineered task prompts can be replaced with task-specific adapters that enable sample-efficient fine-tuning. Experiments on a wide range of few-shot NLP tasks demonstrate that PERFECT, while being simple and efficient, also outperforms existing state-of-the-art few-shot learning methods.
  arXiv  Detail & Related papers  (2022-04-03T22:31:25Z)
• Prefix-Tuning: Optimizing Continuous Prompts for Generation [85.6357778621526]
  Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks. We propose prefix-tuning, a lightweight alternative to fine-tuning for natural language generation tasks. We find that by learning only 0.1% of the parameters, prefix-tuning obtains comparable performance in the full data setting.
  arXiv  Detail & Related papers  (2021-01-01T08:00:36Z)
• WARP: Word-level Adversarial ReProgramming [13.08689221166729]
  In many applications it is preferable to tune much smaller sets of parameters, so that the majority of parameters can be shared across multiple tasks. We present an alternative approach based on adversarial reprogramming, which extends earlier work on automatic prompt generation. We show that this approach outperforms other methods with a similar number of trainable parameters on SST-2 and MNLI datasets.
  arXiv  Detail & Related papers  (2021-01-01T00:41:03Z)
• Parameter-Efficient Transfer Learning with Diff Pruning [108.03864629388404]
  diff pruning is a simple approach to enable parameter-efficient transfer learning within the pretrain-finetune framework. We find that models finetuned with diff pruning can match the performance of fully finetuned baselines on the GLUE benchmark.
  arXiv  Detail & Related papers  (2020-12-14T12:34:01Z)
• Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning [70.81910984985683]
  We propose an effective way to fine-tune multiple down-stream generation tasks simultaneously using a single, large pre-trained model. The experiments on five diverse language generation tasks show that by just using an additional 2-3% parameters for each task, our model can maintain or even improve the performance of fine-tuning the whole model.
  arXiv  Detail & Related papers  (2020-04-08T06:18:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.