| Challenge: | UltraSparseBERT uses 0.3% of its neurons during inference, compared to similar BERT models. |
| Approach: | They propose a BERT variant that selectively engages just 12 out of 4095 neurons for each layer inference. |
| Outcome: | The proposed model employs 0.3% of its neurons during inference while performing on par with similar models. |
Similar Papers
SkipBERT: Efficient Inference with Shallow Layer Skipping (2022.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models have significant demands in computation and inference time, limiting their use in resource-constrained or latencysensitive applications. |
| Approach: | They propose to encode text chunks into independent representations and skip computation of shallow layers to accelerate inference. |
| Outcome: | The proposed approach can reduce latency by 65% without sacrificing performance. |
EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models have shown remarkable results on various NLP tasks. |
| Approach: | They propose to improve the feed-forward network (FFN) in BERT with a higher computational cost than improving the multi-head attention (MHA). |
| Outcome: | The proposed model is 6.9 smaller and 4.4 faster than BERTBASE and has competitive performances on GLUE and SQuAD Benchmarks. |
KinyaBERT: a Morphology-aware Kinyarwanda Language Model (2022.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models such as BERT are sub-optimal at handling morphologically rich languages. |
| Approach: | They propose a two-tier BERT architecture that leverages a morphological analyzer and explicitly represents morphology in a low-resource Kinyarwanda language. |
| Outcome: | The proposed model outperforms baseline models on the low-resource morphologically rich Kinyarwanda language by 2% in F1 score and 4.3% in average score of GLUE benchmark. |
The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models (2022.emnlp-main)
Copied to clipboard
Eldar Kurtic, Daniel Campos, Tuan Nguyen, Elias Frantar, Mark Kurtz, Benjamin Fineran, Michael Goin, Dan Alistarh
| Challenge: | Pre-trained Transformer models provide robust language representations which can be specialized on various tasks. |
| Approach: | They propose an efficient pruning method based on approximate second-order information that allows pruning weight blocks to be used for pruning. |
| Outcome: | The proposed method is the first to be applied at the BERT scale and significantly pushes the boundaries of the current sparse models with respect to all metrics: model size, inference speed and task accuracy. |
TernaryBERT: Distillation-aware Ultra-low Bit BERT (2020.emnlp-main)
Copied to clipboard
| Challenge: | Transformer-based pre-training models like BERT are computationally expensive and limited to resource-constrained devices. |
| Approach: | They propose a method which ternarizes the weights in a fine-tuned BERT model. |
| Outcome: | The proposed method outperforms the other methods on the GLUE and SQUAD benchmarks while being 14.9x smaller. |
HybridBERT - Making BERT Pretraining More Efficient Through Hybrid Mixture of Attention Mechanisms (2024.naacl-srw)
Copied to clipboard
| Challenge: | Pretrained transformer-based language models have produced state-of-the-art performance in most natural language understanding tasks. |
| Approach: | They propose two hybrid architectures that combine self-attention and additive attention mechanisms with sub-layer normalization to achieve double the pretraining accuracy of a vanilla-BERT baseline. |
| Outcome: | The proposed architectures outperform BERT-base on two downstream tasks while accelerating inference. |
Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning (2020.acl-main)
Copied to clipboard
| Challenge: | Existing deep bidirectional language models are limited by repetitive inferences on unsupervised tasks for the computation of contextual language representations. |
| Approach: | They propose a deep bidirectional language model called a Transformer-based Text Autoencoder (T-TA) it computes contextual language representations without repetition and shows competitive or even better accuracies than BERT . |
| Outcome: | The proposed model performs six times faster on a reranking task and twelve times faster in a semantic similarity task. |
Blockwise Self-Attention for Long Document Understanding (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in pre-training and fine-tuning methods have drastically reshaped the landscape of natural language processing research. |
| Approach: | They propose a lightweight BERT model that introduces sparse block structures into the attention matrix to reduce memory consumption and training/inference time. |
| Outcome: | The proposed model uses 18.7-36.1% less memory and 12.0-25.1% more time to learn compared to an advanced BERT-based model, RoBERTa. |
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference (2020.acl-main)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models such as BERT are notorious for being slow in both training and inference. |
| Approach: | They propose a method to accelerate BERT inference by inserting extra classification layers between each transformer layer of BERT. |
| Outcome: | The proposed method saves up to 40% inference time with minimal degradation in model quality. |
TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing pre-trained language models (PLMs) are expensive in inference, making them impractical in resource-limited real-world applications. |
| Approach: | They propose a dynamic token reduction approach to accelerate PLMs' inference by adapting the layer number of each token to avoid redundant calculation. |
| Outcome: | The proposed approach speeds up BERT by 2-5 times and improves performance in long-text tasks with less computation. |