paper-with-me

홈 › Papers

Analyzing Redundancy in Pretrained Transformer Models

2020-04-08 · EMNLP 2020 11 · Fahim Dalvi, Hassan Sajjad, Nadir Durrani, Yonatan Belinkov

Transformer-based deep NLP models are trained using hundreds of millions of parameters, limiting their applicability in computationally constrained environments. In this paper, we study the cause of these limitations by defining a notion of Redundancy, which we categorize into two classes: General Redundancy and Task-specific Redundancy. We dissect two popular pretrained models, BERT and XLNet, studying how much redundancy they exhibit at a representation-level and at a more fine-grained neuron-level. Our analysis reveals interesting insights, such as: i) 85% of the neurons across the network are redundant and ii) at least 92% of them can be removed when optimizing towards a downstream task. Based on our analysis, we present an efficient feature-based transfer learning procedure, which maintains 97% performance while using at-most 10% of the original neurons.

📄 PDF Abstract BibTeX arXiv:2004.04010

Code (1)

fdalvi/analyzing-redundancy-in-pretrained-transformer-models 공식 구현 pytorch

Tasks

Transfer Learning

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
SentencePiece 설명 없음
XLNet 설명 없음
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Toward Manifest Relationality in Transformers via Symmetry Reduction

2026-02-21 · J. François, L. Ravera arxiv

Transformer models contain substantial internal redundancy arising from coordinate-dependent representations and continuous symmetries, in model space and in head space, respectively. While recent approaches address this…

ElastiFormer: Learned Redundancy Reduction in Transformer via Self-Distillation

2024-11-22 · Junzhang Liu, Tingkai Liu, Yueyuan Sui, Stephen Xia

We introduce ElastiFormer, a post-training technique that adapts pretrained Transformer models into an elastic counterpart with variable inference time compute. ElastiFormer introduces small routing modules (as low as .0…

Causal Language ModelingLanguage ModelingLanguage Modelling

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study

2024-11-18 · Xibo Sun, Jiarui Fang, Aoyu Li, Jinzhe Pan

The increased model capacity of Diffusion Transformers (DiTs) and the demand for generating higher resolutions of images and videos have led to a significant rise in inference latency, impacting real-time performance adv…

Scheduling

Understanding Differential Transformer Unchains Pretrained Self-Attentions

2025-05-22 · Chaerin Kong, Jiho Jang, Nojun Kwak

Differential Transformer has recently gained significant attention for its impressive empirical performance, often attributed to its ability to perform noise canceled attention. However, precisely how differential attent…

Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing

2020-06-05 · NeurIPS 2020 12 · Zihang Dai, Guokun Lai, Yiming Yang, Quoc V. Le

With the success of language pretraining, it is highly desirable to develop more efficient architectures of good scalability that can exploit the abundant unlabeled data at a lower cost. To improve the efficiency, we exa…

DecoderReading ComprehensionText Classification