Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention (D19-1)
Copied to clipboard
| Challenge: | Existing methods to improve NLP convergence and computational overhead are limited by stacking more layers. |
| Approach: | They propose a depth-scaled initialization method which reduces parameter variance at initialization and reduces output variance of residual connections to ease gradient back-propagation. |
| Outcome: | The proposed method outperforms the base model on translation tasks with five translation directions while matching the decoding speed of the baseline model. |
Similar Papers
Rewiring the Transformer with Depth-Wise LSTMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Stacking non-linear layers allows deep neural networks to model complicated functions . but residual connections within each layer fail to fuse information from previous layers effectively . |
| Approach: | They propose a Transformer with depth-wise LSTMs connecting cascading Transformer layers and sub-layers. |
| Outcome: | The proposed model improves in English-German / French and multilingual tasks with BLEU. |
Learning Deep Transformer Models for Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural machine translation models have advanced the previous state-of-the-art by learning mappings between sequences via neural networks and attention mechanisms. |
| Approach: | They propose to use layer normalization to pass the combination of previous layers to the next layer to improve the model. |
| Outcome: | The proposed model outperforms the shallow Transformer-Big/Base baseline model on English-German and Chinese-English tasks by 0.4-2.4 BLEU points. |
Training Deeper Neural Machine Translation Models with Transparent Attention (D18-1)
Copied to clipboard
| Challenge: | Existing NMT models are shallow in comparison to convolutional models used for both text and vision tasks. |
| Approach: | They propose to modify the attention mechanism to ease the optimization of deeper models by a simple modification to the seq2seq with attention paradigm. |
| Outcome: | The proposed model achieves consistent gains of 0.7-1.1 BLEU on the benchmark WMT’14 English-German and WMT'15 Czech-English tasks. |
Lipschitz Constrained Parameter Initialization for Deep Transformers (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies show that deep Transformers have difficulty in training even with residual connection and layer normalization. |
| Approach: | They propose a method that leverages the Lipschitz constraint on the initialization of Transformer parameters to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. |
| Outcome: | The proposed model outperforms previous RNN/CNN models but fails to converge with the original computation order. |
RealFormer: Transformer Likes Residual Attention (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing techniques to create Residual Attention Layer Transformer networks outperform the canonical Transformer on a wide spectrum of tasks. |
| Approach: | They propose a technique to create Residual Attention Layer Transformer networks that outperform the canonical Transformer on a wide spectrum of tasks. |
| Outcome: | The proposed technique outperforms the canonical Transformer on a wide spectrum of tasks including Masked Language Modeling, GLUE, SQUAD, Neural Machine Translation, WikiHop, HotpotQA, Natural Questions, and OpenKP. |
Speeding up Transformer Decoding via an Attention Refinement Network (2022.coling-1)
Copied to clipboard
| Challenge: | Extensive experiments on ten WMT machine translation tasks show that the proposed model yields an average of 1.35x faster (with almost no decrease in BLEU) |
| Approach: | They propose a weighted residual network which reconstructs attention by reusing the features across layers. |
| Outcome: | The proposed model is 1.35x faster than the state-of-the-art inference model on translation tasks compared to AAN and SAN models with fewer parameter numbers . |
Shallow-to-Deep Training for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that deep training is 1:4 faster than training from scratch. |
| Approach: | They propose a shallow-to-deep training method that learns deep models by stacking shallow models. |
| Outcome: | The proposed method is 1:4 faster than training from scratch and achieves BLEU scores of 30:33 and 43:29 on two translation tasks. |
Optimizing Deeper Transformers on Small Datasets (2021.acl-long)
Copied to clipboard
Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J.D. Prince, Yanshuai Cao
| Challenge: | a common belief that training deep transformers from scratch requires large datasets is wrong . however, with proper initialization and optimization, the benefits of very deep transformer can carry over to challenging tasks with small datasets. |
| Approach: | They train 48 layers of transformers from pre-trained RoBERTa and 24 relation-aware layers from scratch. |
| Outcome: | The proposed scheme achieves state-of-the-art performance on a text-to-sql parsing benchmark . it uses 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers from scratch . |
Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping (2026.findings-acl)
Copied to clipboard
Yao Chen, Yilong Chen, Yinqi Yang, Junyuan Shang, Zhenyu Zhang, Zefeng Zhang, Shuaiyi Nie, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang, Tingwen Liu
| Challenge: | Existing approaches to increasing effective depth of LLMs rely on parameter reuse, extending computation through recursive execution. |
| Approach: | They propose a training-time sparse depth allocation framework that progressively increases depth for a small subset of parameters as training evolves. |
| Outcome: | The proposed model outperforms existing approaches to increasing the effective depth of language models while reducing training FLOPs overhead from approximately 16–20% to only 1–3% relative to a standard Transformer backbone. |
Choose Your Transformer: Improved Transferability Estimation of Transformer Models on Classification Tasks (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models for NLP tasks require fine-tuning, but it is computationally infeasible. |
| Approach: | They propose an approach that inexpensively estimates a ranking of the expected performance of a given set of transformer language models for a specific task. |
| Outcome: | The proposed model improves the Pearson correlation coefficient between the true model ranks and the estimate. |