A Study on Transformer Configuration and Training Objective

• URL: http://arxiv.org/abs/2205.10505v3
• Date: Thu, 18 May 2023 16:08:10 GMT
• Title: A Study on Transformer Configuration and Training Objective
• Authors: Fuzhao Xue, Jianghai Chen, Aixin Sun, Xiaozhe Ren, Zangwei Zheng, Xiaoxin He, Yongming Chen, Xin Jiang, Yang You
• Abstract summary: We propose Bamboo, an idea of using deeper and narrower transformer configurations for masked autoencoder training. On ImageNet, with such a simple change in configuration, re-designed model achieves 87.1% top-1 accuracy. On language tasks, re-designed model outperforms BERT with default setting by 1.1 points on average.
• Score: 33.7272660870026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer-based models have delivered impressive results on many tasks, particularly vision and language tasks. In many model training situations, conventional configurations are typically adopted. For example, we often set the base model with hidden dimensions (i.e. model width) to be 768 and the number of transformer layers (i.e. model depth) to be 12. In this paper, we revisit these conventional configurations. Through theoretical analysis and experimental evaluation, we show that the masked autoencoder is effective in alleviating the over-smoothing issue in deep transformer training. Based on this finding, we propose Bamboo, an idea of using deeper and narrower transformer configurations, for masked autoencoder training. On ImageNet, with such a simple change in configuration, re-designed model achieves 87.1% top-1 accuracy and outperforms SoTA models like MAE and BEiT. On language tasks, re-designed model outperforms BERT with default setting by 1.1 points on average, on GLUE datasets.

Related papers

• MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining [73.81862342673894]
  Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. We conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. Our models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection.
  arXiv  Detail & Related papers  (2024-03-20T09:17:22Z)
• Fisher Mask Nodes for Language Model Merging [0.0]
  We introduce a novel model merging method for Transformers, combining insights from previous work in Fisher-weighted averaging and the use of Fisher information in model pruning. Our method exhibits a regular and significant performance increase across various models in the BERT family, outperforming full-scale Fisher-weighted averaging in a fraction of the computational cost.
  arXiv  Detail & Related papers  (2024-03-14T21:52:26Z)
• Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models [6.809572275782338]
  We develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the transformer model. Our framework can be used to understand and mitigate vanishing/exploding gradients, rank collapse, and instability associated with high attention scores.
  arXiv  Detail & Related papers  (2024-03-14T17:59:14Z)
• DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging [34.643717080240584]
  We propose DenseFormer, a simple modification to the standard architecture that improves the perplexity of the model without increasing its size. Our approach relies on an additional averaging step after each transformer block, which computes a weighted average of current and past representations. Experiments demonstrate that DenseFormer is more data efficient, reaching the same perplexity of much deeper transformer models.
  arXiv  Detail & Related papers  (2024-02-04T21:44:09Z)
• MatFormer: Nested Transformer for Elastic Inference [94.1789252941718]
  MatFormer is a nested Transformer architecture designed to offer elasticity in a variety of deployment constraints. We show that a 2.6B decoder-only MatFormer language model (MatLM) allows us to extract smaller models spanning from 1.5B to 2.6B. We also observe that smaller encoders extracted from a universal MatFormer-based ViT (MatViT) encoder preserve the metric-space structure for adaptive large-scale retrieval.
  arXiv  Detail & Related papers  (2023-10-11T17:57:14Z)
• Efficient GPT Model Pre-training using Tensor Train Matrix Representation [65.96485282393361]
  Large-scale transformer models feature billions of parameters, leading to difficulties in their deployment and prohibitive training costs from scratch. To reduce the number of parameters in the GPT-2 architecture, we replace the matrices of fully-connected layers with the corresponding Train Matrix(TTM) structure. The resulting GPT-based model stores up to 40% fewer parameters, showing the perplexity comparable to the original model.
  arXiv  Detail & Related papers  (2023-06-05T08:38:25Z)
• Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model [97.9548609175831]
  We resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models customized for remote sensing tasks. Specifically, to handle the large image size and objects of various orientations in RS images, we propose a new rotated varied-size window attention. Experiments on detection tasks demonstrate the superiority of our model over all state-of-the-art models, achieving 81.16% mAP on the DOTA-V1.0 dataset.
  arXiv  Detail & Related papers  (2022-08-08T09:08:40Z)
• Visformer: The Vision-friendly Transformer [105.52122194322592]
  We propose a new architecture named Visformer, which is abbreviated from the Vision-friendly Transformer' With the same computational complexity, Visformer outperforms both the Transformer-based and convolution-based models in terms of ImageNet classification accuracy.
  arXiv  Detail & Related papers  (2021-04-26T13:13:03Z)
• AutoTrans: Automating Transformer Design via Reinforced Architecture Search [52.48985245743108]
  This paper empirically explore how to set layer-norm, whether to scale, number of layers, number of heads, activation function, etc, so that one can obtain a transformer architecture that better suits the tasks at hand. Experiments on the CoNLL03, Multi-30k, IWSLT14 and WMT-14 shows that the searched transformer model can outperform the standard transformers.
  arXiv  Detail & Related papers  (2020-09-04T08:46:22Z)
• XD at SemEval-2020 Task 12: Ensemble Approach to Offensive Language Identification in Social Media Using Transformer Encoders [17.14709845342071]
  This paper presents six document classification models using the latest transformer encoders and a high-performing ensemble model for a task of offensive language identification in social media. Our analysis shows that although the ensemble model significantly improves the accuracy on the development set, the improvement is not as evident on the test set.
  arXiv  Detail & Related papers  (2020-07-21T17:03:00Z)

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.