Understanding the Difficulty of Training Transformers (2020.emnlp-main)

Copied to clipboard

Challenge: Admin (Adaptive model initialization) is more stable, converges faster, and leads to better performance.
Approach: They propose a model initialization algorithm to stabilize early training and unleash its full potential in the late stage.
Outcome: The proposed model initialization method stabilizes early training and unleashes full potential in late stage.

Similar Papers

BranchNorm: Robustly Scaling Extremely Deep Transformers (2024.findings-acl)

Copied to clipboard

Challenge: Recent work on DeepNorm scales Transformers into extremely deep (1000 layers) due to the training instability of Transformers, the depths of these SOTA models are still relatively shallow.
Approach: They propose a branch-rescaled model which dynamically rescales the non-residual branch of Transformer in accordance with the training period.
Outcome: The proposed approach significantly outperforms existing shallow models on multiple translation tasks and achieves better training stability and convergent performance.
BERT Busters: Outlier Dimensions that Disrupt Transformers (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies show that pre-trained Transformers are remarkably robust to pruning.
Approach: They show that pre-trained Transformer encoders are surprisingly fragile to pruning . they show that disabling them significantly degrades both the MLM loss and the downstream task performance.
Outcome: The results show that the removal of features in pre-trained transformers significantly degrades both the MLM loss and the downstream task performance.
Analyzing Redundancy in Pretrained Transformer Models (2020.emnlp-main)

Copied to clipboard

Challenge: Recent work shows that transformer-based deep NLP models are over-parameterized and do not require all the representational power lent by the rich architectural choices during inference.
Approach: They define a notion of Redundancy and propose a feature-based transfer learning procedure which maintains 97% performance while using at-most 10% of the original neurons.
Outcome: The proposed model maintains 97% performance while using 10% of the original neurons.
Exploring Quantization for Efficient Pre-Training of Transformer Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Quantization has proven to be effective after pre-training and during fine-tuning, but its effects on pre-trainer performance have remained unexplored.
Approach: They propose a linear quantization strategy to be applied during the pre-training of Transformers to improve model efficiency and stability.
Outcome: The proposed method improves model efficiency, stability, and performance while maintaining language modeling ability.
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT (2021.tacl-1)

Copied to clipboard

Challenge: Popular pre-trained Transformers have improved performance for various NLP tasks by sizable margins, but are too resource-hungry and computation-intensive to suit low-capacity devices or applications with strict latency requirements.
Approach: They present a literature review of the compression of Transformers, focusing on the popular BERT model, which has attracted considerable research attention.
Outcome: The proposed models improve Sentiment analysis, paraphrase detection, machine reading comprehension, question answering, text summarization, and other tasks by sizable margins.
Understanding and Overcoming the Challenges of Efficient Transformer Quantization (2021.emnlp-main)

Copied to clipboard

Challenge: Recent advances in transformer quantization have shown remarkable improvement in many Natural Language Processing tasks and beyond.
Approach: They propose a novel quantization scheme for transformers that can be quantized to ultra-low bit-widths, leading to significant memory savings with a minimum accuracy loss.
Outcome: The proposed methods achieve state-of-the-art results on the GLUE benchmark using BERT, while preserving memory and accuracy.
B2T Connection: Serving Stability and Performance in Deep Transformers (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to prevent the vanishing gradient problem in deep neural networks are not effective.
Approach: They propose a method that can equip both higher stability and effective training by a simple modification from Post-LN.
Outcome: The proposed method outperforms Pre-LN and Post-Ln on a wide range of tasks.
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent (2021.emnlp-main)

Copied to clipboard

Challenge: Evidence is emerging that neural networks learn due to inductive bias in the training routine, typically a variant of gradient descent (GD).
Approach: They propose to characterize GD as an inductive bias in transformer training . they document norm growth in transformer language models and show they are saturated .
Outcome: Empirically, we document norm growth in the training of transformer language models . the results suggest saturation is a new characterization of an inductive bias implicit in GD .
Optimizing Deeper Transformers on Small Datasets (2021.acl-long)

Copied to clipboard

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 .
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies show that fine-tuned textual transformer models are vulnerable to adversarial text perturbations.
Approach: They extract 13 different features representing a wide range of input fine-tuning corpora properties and use them to predict adversarial robustness of the fine- tuned models.
Outcome: The proposed framework can be used as an additional tool for robustness evaluation since it saves 30x-193x runtime compared to the traditional technique and can be easily used under adversarial training.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations