| Challenge: | Prior work has noted that BERT’s computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions. |
| Approach: | They propose to combine topic and language models to optimize the computational cost of fine-tuning for document classification by complementary learning. |
| Outcome: | The proposed model achieves a 1.4x speedup with 40% reduction in CO2 emission while retaining 99.9% performance over 5 datasets. |
Similar Papers
Energy and Carbon Considerations of Fine-Tuning BERT (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work quantifying energy costs and associated carbon emissions has focused on pretraining and fine-tuning. |
| Approach: | They perform an empirical study to quantify the energy requirements of language model fine-tuning in the context of pretraining and inference. |
| Outcome: | The proposed model fine-tuning energy and carbon footprints are compared with pre-training and inference energy requirements and outline recommendations for NLP researchers and practitioners. |
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. |
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. |
Evaluating Parameter-Efficient Finetuning Approaches for Pre-trained Models on the Financial Domain (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale language models with millions, billions, or trillions of trainable parameters are becoming increasingly popular. |
| Approach: | They compare performance of financial BERT-like models to their fully fine-tuned counterparts by using parameter-efficient tuning methods. |
| Outcome: | The proposed approaches match full fine-tuning performance on common NLP tasks, but are less studied in finance. |
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. |
Evaluating Cost-Efficiency of LLMs in a RAG Setup on Polish Wikipedia: Quality vs. Energy Consumption (2026.eacl-srw)
Copied to clipboard
| Challenge: | Retrieval-augmented generation systems are a dominant paradigm for knowledge-intensive applications. |
| Approach: | They evaluate language models from 4B to 70B parameters within a Polish Wikipedia-based RAG pipeline. |
| Outcome: | The proposed model selection process reduces energy consumption by 83% and improves quality. |
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. |
Fusing Label Embedding into BERT: An Efficient Improvement for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to improve text classification performance of pre-trained models have been used to improve their performance. |
| Approach: | They propose a method for improving BERT's performance by using a label embedding technique while keeping almost the same computational cost. |
| Outcome: | The proposed method improves BERT's performance on six text classification benchmark datasets while keeping almost the same computational cost. |
Parameter-Efficient Tuning Makes a Good Classification Head (2022.emnlp-main)
Copied to clipboard
| Challenge: | In recent years, pretrained models revolutionized the paradigm of natural language understanding . but the final-layer output of the backbone, i.e. the input of the classification head, will change greatly during finetuning . |
| Approach: | They propose to append a randomly initialized classification head after the pretrained backbone and finetune the whole model. |
| Outcome: | The proposed classification head can be replaced with the randomly initialized heads for a stable performance gain. |
FastBERT: a Self-distilling BERT with Adaptive Inference Time (2020.acl-main)
Copied to clipboard
| Challenge: | Pre-trained language models like BERT have proven to be highly performant, but are often computationally expensive in many practical scenarios. |
| Approach: | They propose a speed-tunable FastBERT with adaptive inference time that can be flexibly adjusted under varying demands. |
| Outcome: | The proposed model achieves promising results in English and Chinese datasets. |