BranchNorm: Robustly Scaling Extremely Deep Transformers

• URL: http://arxiv.org/abs/2305.02790v1
• Date: Thu, 4 May 2023 12:46:12 GMT
• Title: BranchNorm: Robustly Scaling Extremely Deep Transformers
• Authors: Yijin Liu, Xianfeng Zeng, Fandong Meng and Jie Zhou
• Abstract summary: BranchNorm dynamically rescales the non-residual branch of Transformer in accordance with the training period. Experiment results on multiple translation tasks demonstrate that BranchNorm achieves a better trade-off between training stability and converge performance.
• Score: 55.92852268168816
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, DeepNorm scales Transformers into extremely deep (i.e., 1000 layers) and reveals the promising potential of deep scaling. To stabilize the training of deep models, DeepNorm (Wang et al., 2022) attempts to constrain the model update to a constant value. Although applying such a constraint can benefit the early stage of model training, it may lead to undertrained models during the whole training procedure. In this paper, we propose BranchNorm, which dynamically rescales the non-residual branch of Transformer in accordance with the training period. BranchNorm not only theoretically stabilizes the training with smooth gradient norms at the early stage, but also encourages better convergence in the subsequent training stage. Experiment results on multiple translation tasks demonstrate that BranchNorm achieves a better trade-off between training stability and converge performance.

Related papers

• Maestro: Uncovering Low-Rank Structures via Trainable Decomposition [15.254107731735553]
  Deep Neural Networks (DNNs) have been a large driver for AI breakthroughs in recent years. They have been getting increasingly large as they become more accurate and safe. This means that their training becomes increasingly costly and time-consuming. We propose Maestro, a framework for trainable low-rank layers.
  arXiv  Detail & Related papers  (2023-08-28T23:08:15Z)
• Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding [12.030179065286928]
  The paper proposes a quantization-aware tensor-compressed training approach to reduce the model size, arithmetic operations, and runtime latency of transformer-based models. A layer-by-layer distillation is applied to distill a quantized and tensor-compressed student model from a pre-trained transformer. The performance is demonstrated in two natural language understanding tasks, showing up to $63times$ compression ratio, little accuracy loss and remarkable inference and training speedup.
  arXiv  Detail & Related papers  (2023-06-01T18:32:08Z)
• Emergent Agentic Transformer from Chain of Hindsight Experience [96.56164427726203]
  We show that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches. This is the first time that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches.
  arXiv  Detail & Related papers  (2023-05-26T00:43:02Z)
• Controlled Descent Training [0.0]
  A novel and model-based artificial neural network (ANN) training method is developed supported by optimal control theory. The method augments training labels in order to robustly guarantee training loss convergence and improve training convergence rate. The applicability of the method is demonstrated on standard regression and classification problems.
  arXiv  Detail & Related papers  (2023-03-16T10:45:24Z)
• Finetuning Pretrained Transformers into RNNs [81.72974646901136]
  Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. A linear-complexity recurrent variant has proven well suited for autoregressive generation. This work aims to convert a pretrained transformer into its efficient recurrent counterpart.
  arXiv  Detail & Related papers  (2021-03-24T10:50:43Z)
• Self-Progressing Robust Training [146.8337017922058]
  Current robust training methods such as adversarial training explicitly uses an "attack" to generate adversarial examples. We propose a new framework called SPROUT, self-progressing robust training. Our results shed new light on scalable, effective and attack-independent robust training methods.
  arXiv  Detail & Related papers  (2020-12-22T00:45:24Z)
• Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free [115.81899803240758]
  Adversarial training and its many variants substantially improve deep network robustness, yet at the cost of compromising standard accuracy. This paper asks how to quickly calibrate a trained model in-situ, to examine the achievable trade-offs between its standard and robust accuracies. Our proposed framework, Once-for-all Adversarial Training (OAT), is built on an innovative model-conditional training framework.
  arXiv  Detail & Related papers  (2020-10-22T16:06:34Z)
• Understanding the Difficulty of Training Transformers [120.99980924577787]
  We show that unbalanced gradients are not the root cause of the instability of training. We propose Admin to stabilize the early stage's training and unleash its full potential in the late stage.
  arXiv  Detail & Related papers  (2020-04-17T13:59:07Z)
• Mode-Assisted Unsupervised Learning of Restricted Boltzmann Machines [7.960229223744695]
  We show that properly combining standard gradient updates with an off-gradient direction improves their training dramatically over traditional gradient methods. This approach, which we call mode training, promotes faster training and stability, in addition to lower converged relative entropy (KL divergence) The mode training we suggest is quite versatile, as it can be applied in conjunction with any given gradient method, and is easily extended to more general energy-based neural network structures.
  arXiv  Detail & Related papers  (2020-01-15T21:12:44Z)

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.