Guiding Attention for Self-Supervised Learning with Transformers

• URL: http://arxiv.org/abs/2010.02399v1
• Date: Tue, 6 Oct 2020 00:04:08 GMT
• Title: Guiding Attention for Self-Supervised Learning with Transformers
• Authors: Ameet Deshpande, Karthik Narasimhan
• Abstract summary: We propose a technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained models contain a majority of non-linguistic regularities.
• Score: 24.785500242464646
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained models contain a majority of non-linguistic regularities. We propose a computationally efficient auxiliary loss function to guide attention heads to conform to such patterns. Our method is agnostic to the actual pre-training objective and results in faster convergence of models as well as better performance on downstream tasks compared to the baselines, achieving state of the art results in low-resource settings. Surprisingly, we also find that linguistic properties of attention heads are not necessarily correlated with language modeling performance.

Related papers

• LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging [10.33844295243509]
  We propose a unified framework for model merging based on low-rank estimation of task vectors without the need for access to the base model, named textscLoRE-Merging. Our approach is motivated by the observation that task vectors from fine-tuned models frequently exhibit a limited number of dominant singular values, making low-rank estimations less prone to interference.
  arXiv  Detail & Related papers  (2025-02-15T10:18:46Z)
• Leveraging counterfactual concepts for debugging and improving CNN model performance [1.1049608786515839]
  We propose to leverage counterfactual concepts aiming to enhance the performance of CNN models in image classification tasks. Our proposed approach utilizes counterfactual reasoning to identify crucial filters used in the decision-making process. By incorporating counterfactual explanations, we validate unseen model predictions and identify misclassifications.
  arXiv  Detail & Related papers  (2025-01-19T15:50:33Z)
• Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models [4.737806982257592]
  This study proposes a knowledge distillation algorithm based on large language models and feature alignment. The proposed model performs very close to the state-of-the-art GPT-4 model in terms of evaluation indicators such as perplexity, BLEU, ROUGE, and CER.
  arXiv  Detail & Related papers  (2024-12-27T04:37:06Z)
• DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning [75.68193159293425]
  In-context learning (ICL) allows transformer-based language models to learn a specific task with a few "task demonstrations" without updating their parameters. We propose an influence function-based attribution technique, DETAIL, that addresses the specific characteristics of ICL. We experimentally prove the wide applicability of DETAIL by showing our attribution scores obtained on white-box models are transferable to black-box models in improving model performance.
  arXiv  Detail & Related papers  (2024-05-22T15:52:52Z)
• Entailment as Robust Self-Learner [14.86757876218415]
  We design a prompting strategy that formulates a number of different NLU tasks as contextual entailment. We propose the Simple Pseudo-Label Editing (SimPLE) algorithm for better pseudo-labeling quality in self-training.
  arXiv  Detail & Related papers  (2023-05-26T18:41:23Z)
• Towards Compute-Optimal Transfer Learning [82.88829463290041]
  We argue that zero-shot structured pruning of pretrained models allows them to increase compute efficiency with minimal reduction in performance. Our results show that pruning convolutional filters of pretrained models can lead to more than 20% performance improvement in low computational regimes.
  arXiv  Detail & Related papers  (2023-04-25T21:49:09Z)
• Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
  We propose self-distillation as a regularization for a further pre-training stage. We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
  arXiv  Detail & Related papers  (2022-09-30T02:25:12Z)
• Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles [60.97922557957857]
  We provide a framework to perform self-supervised model ensembling via a novel method of learning representations directly through gradient descent at inference time. This technique improves representation quality, as measured by k-nearest neighbors, both on the in-domain dataset and in the transfer setting.
  arXiv  Detail & Related papers  (2021-10-19T22:24:57Z)
• Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training [66.80558875393565]
  We study the problem of training named entity recognition (NER) models using only distantly-labeled data. We propose a noise-robust learning scheme comprised of a new loss function and a noisy label removal step. Our method achieves superior performance, outperforming existing distantly-supervised NER models by significant margins.
  arXiv  Detail & Related papers  (2021-09-10T17:19:56Z)
• On Learning Text Style Transfer with Direct Rewards [101.97136885111037]
  Lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task. We leverage semantic similarity metrics originally used for fine-tuning neural machine translation models. Our model provides significant gains in both automatic and human evaluation over strong baselines.
  arXiv  Detail & Related papers  (2020-10-24T04:30:02Z)

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.