paper-with-me

Papers

Weight Squeezing: Reparameterization for Knowledge Transfer and Model Compression

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In this work, we present a novel approach to simultaneous knowledge transfer and model compression called \textbf{Weight Squeezing}. With this method, we perform knowledge transfer from a teacher model \textbf{by learning the mapping from its weights to smaller student model weights}. We applied Weight Squeezing to a pre-trained text classification model based on a BERT-Medium model. We compared our method to various other knowledge transfer and model compression methods using the GLUE multitask benchmark. We observed that our approach produces better results while being significantly faster than other methods for training student models. We also proposed a variant of Weight Squeezing called Gated Weight Squeezing, in which we combined fine-tuning a small BERT model and learning mapping from larger BERT weights. We showed that, in most cases, fine-tuning a BERT model with Gated Weight Squeezing can outperform plain fine-tuning.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compressiontext-classificationText ClassificationTransfer Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Weight Squeezing: Reparameterization for Knowledge Transfer and Model Compression

2020-10-14 · Artem Chumachenko, Daniil Gavrilov, Nikita Balagansky, Pavel Kalaidin

In this work, we present a novel approach for simultaneous knowledge transfer and model compression called Weight Squeezing. With this method, we perform knowledge transfer from a teacher model by learning the mapping fr…

General ClassificationModel Compressiontext-classificationText Classification+1

Weight Squeezing: Reparameterization for Compression and Fast Inference

2020-05-30 · Anonymous

In this work, we present a novel approach for simultaneous knowledge transfer and model compression called Weight Squeezing. With this method, we perform knowledge transfer from a pre-trained teacher model by learning th…

Knowledge DistillationModel Compressiontext-classificationText Classification+1

Scalable Model Compression by Entropy Penalized Reparameterization

2019-06-15 · ICLR 2020 1 · Deniz Oktay, Johannes Ballé, Saurabh Singh, Abhinav Shrivastava

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equi…

General ClassificationmodelModel Compression

A Unified Knowledge Distillation Framework for Deep Directed Graphical Models

2021-09-29 · CVPR 2023 1 · Yizhuo Chen, Kaizhao Liang, Zhe Zeng, Yifei Yang 외

Knowledge distillation (KD) is a technique that transfers the knowledge from a large teacher network to a small student network. It has been widely applied to many different tasks, such as model compression and federate…

Continual LearningFederated LearningKnowledge DistillationModel Compression

Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method

2025-07-24 · Qingcheng Zhu, Yangyang Ren, Linlin Yang, Mingbao Lin 외 arxiv

Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can significantly reduce storage and accelerate inference, but extreme compre…