Investigating Transferability in Pretrained Language Models

• URL: http://arxiv.org/abs/2004.14975v2
• Date: Tue, 10 Nov 2020 00:56:31 GMT
• Title: Investigating Transferability in Pretrained Language Models
• Authors: Alex Tamkin, Trisha Singh, Davide Giovanardi, Noah Goodman
• Abstract summary: We consider a simple ablation technique for determining the impact of each pretrained layer on transfer task performance. This technique reveals that in BERT, layers with high probing performance on downstream GLUE tasks are neither necessary nor sufficient for high accuracy on those tasks.
• Score: 8.83046338075119
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: How does language model pretraining help transfer learning? We consider a simple ablation technique for determining the impact of each pretrained layer on transfer task performance. This method, partial reinitialization, involves replacing different layers of a pretrained model with random weights, then finetuning the entire model on the transfer task and observing the change in performance. This technique reveals that in BERT, layers with high probing performance on downstream GLUE tasks are neither necessary nor sufficient for high accuracy on those tasks. Furthermore, the benefit of using pretrained parameters for a layer varies dramatically with finetuning dataset size: parameters that provide tremendous performance improvement when data is plentiful may provide negligible benefits in data-scarce settings. These results reveal the complexity of the transfer learning process, highlighting the limitations of methods that operate on frozen models or single data samples.

Related papers

• Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach [87.8330887605381]
  We show how to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. We synthesize a task-specific query with a learnable and lightweight module, which is independent of the pre-trained model. Our method achieves state-of-the-art performance under memory constraints, showcasing its applicability in real-world situations.
  arXiv  Detail & Related papers  (2024-07-09T15:45:04Z)
• Improvement of Applicability in Student Performance Prediction Based on Transfer Learning [2.3290007848431955]
  This study proposes a method to improve prediction accuracy by employing transfer learning techniques on the dataset with varying distributions. The model was trained and evaluated to enhance its generalization ability and prediction accuracy. Experiments demonstrated that this approach excels in reducing Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) The results demonstrate that freezing more layers improves performance for complex and noisy data, whereas freezing fewer layers is more effective for simpler and larger datasets.
  arXiv  Detail & Related papers  (2024-06-01T13:09:05Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)
• TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models [32.83440439290383]
  We introduce TAIL (Task-specific Adapters for Learning), a framework for efficient adaptation to new control tasks. Inspired by recent advancements in parameter-efficient fine-tuning in language domains, we explore efficient fine-tuning techniques. Our experiments in large-scale language-conditioned manipulation tasks suggest that TAIL with LoRA can achieve the best post-adaptation performance.
  arXiv  Detail & Related papers  (2023-10-09T17:49:50Z)
• Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning [16.60284838029852]
  We investigate whether one could make a task-specific selection on which subset of the layers to adapt. We propose to select layers based on the variability of their hidden states given a task-specific corpus.
  arXiv  Detail & Related papers  (2022-10-18T17:58:43Z)
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning [81.3514358542452]
  Few-shot in-context learning (ICL) incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made. parameter-efficient fine-tuning offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task. In this paper, we rigorously compare few-shot ICL and parameter-efficient fine-tuning and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs.
  arXiv  Detail & Related papers  (2022-05-11T17:10:41Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Dynamic Scale Training for Object Detection [111.33112051962514]
  We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Experimental results demonstrate the efficacy of our proposed DST towards scale variation handling. It does not introduce inference overhead and could serve as a free lunch for general detection configurations.
  arXiv  Detail & Related papers  (2020-04-26T16:48:17Z)
• Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation [111.44445634272235]
  In this paper, we develop a parameter efficient transfer learning architecture, termed as PeterRec. PeterRec allows the pre-trained parameters to remain unaltered during fine-tuning by injecting a series of re-learned neural networks. We perform extensive experimental ablation to show the effectiveness of the learned user representation in five downstream tasks.
  arXiv  Detail & Related papers  (2020-01-13T14:09:54Z)

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.