paper-with-me

홈 › Papers

Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling

2021-10-07 · 2021 18th International SoC Design Conference (ISOCC) 2021 11 · Kyuhong Shim, Iksoo Choi, Wonyong Sung, Jungwook Choi

While Transformer-based models have shown impressive language modeling performance, the large computation cost is often prohibitive for practical use. Attention head pruning, which removes unnecessary attention heads in the multihead attention, is a promising technique to solve this problem. However, it does not evenly reduce the overall load because the heavy feedforward module is not affected by head pruning. In this paper, we apply layer-wise attention head pruning on All-attention Transformer so that the entire computation and the number of parameters can be reduced proportionally to the number of pruned heads. While the architecture has the potential to fully utilize head pruning, we propose three training methods that are especially helpful to minimize performance degradation and stabilize the pruning process. Our pruned model shows consistently lower perplexity within a comparable parameter size than Transformer-XL on WikiText-103 language modeling benchmark.

📄 PDF Abstract BibTeX arXiv:2110.03252

Code (1)

aiha-lab/Attention-Head-Pruning 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Pruning 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Variational Dropout Variational Dropout is a regularization technique based on dropout, but uses a variational inference grounded approach. In…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

On the weak link between importance and prunability of attention heads

2020-11-01 · EMNLP 2020 11 · Aakriti Budhraja, Madhura Pande, Preksha Nema, Pratyush Kumar 외

Given the success of Transformer-based models, two directions of study have emerged: interpreting role of individual attention heads and down-sizing the models for efficiency. Our work straddles these two streams: We ana…

Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning

2026-01-11 · Jaewon Sok, Jewon Yeom, Seonghyeon Park, Jeongjae Park 외 arxiv

Large Language Models (LLMs) are known to contain significant redundancy, yet a systematic explanation for why certain components, particularly in higher layers, are more redundant has remained elusive. In this work, we …

Model Compression

Complementary Attention Head Pruning for Efficient Transformers

2026-06-17 · Yaniv Livertovsky, Shahar Somin, Gonen Singer arxiv

The remarkable success of Transformer-based models in natural language processing stems from architectural scaling, which leads to a large number of parameters and hinders deployment in resource-constrained environments.…

Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection for Fusing Dialogue Coreference Information

2023-12-15 · Zhengyuan Liu, Nancy F. Chen

The Transformer-based models with the multi-head self-attention mechanism are widely used in natural language processing, and provide state-of-the-art results. While the pre-trained language backbones are shown to implic…

Network Pruning

AutoAttention: Automatic Attention Head Selection Through Differentiable Pruning

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Multi-head attention is considered as a driving force and key component behind the state-of-art transformer models. However, recent research reveals that there are many redundant heads with duplicated patterns in each la…