paper-with-me

홈 › Papers

Speeding up Deep Learning Training by Sharing Weights and Then Unsharing

2021-01-01 · Shuo Yang, Le Hou, Xiaodan Song, Qiang Liu, Denny Zhou

It has been widely observed that increasing deep learning model sizes often leads to significant performance improvements on a variety of natural language processing and computer vision tasks. In the meantime, however, computational costs and training time would dramatically increase when models get larger. In this paper, we propose a simple approach to speed up training for a particular kind of deep networks which contain repeated structures, such as the transformer module. In our method, we first train such a deep network with the weights shared across all the repeated layers. Once an unsharing condition is triggered, we stop weight sharing and continue training until convergence. Empirical results show that our method is able to reduce the training time of BERT by 50%. We also conduct a preliminary theoretic analysis which motivates our approach.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
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 $x$…
Residual Connection 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 &…
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…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

Speeding up Deep Model Training by Sharing Weights and Then Unsharing

2021-10-08 · Shuo Yang, Le Hou, Xiaodan Song, Qiang Liu 외

We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transformer encoders). Our proposed approach fi…

FedMes: Speeding Up Federated Learning with Multiple Edge Servers

2021-01-01 · Dong-Jun Han, Minseok Choi, Jungwuk Park, Jaekyun Moon

We consider federated learning with multiple wireless edge servers having their own local coverages. We focus on speeding up training in this increasingly practical setup. Our key idea is to utilize the devices located i…

Federated Learning

AMS-QUANT: Adaptive Mantissa Sharing for Floating-point Quantization

2025-10-16 · Mengtao Lv, Ruiqi Zhu, Xinyu Wang, Yun Li arxiv

Large language models (LLMs) have demonstrated remarkable capabilities in various kinds of tasks, while the billion or even trillion parameters bring storage and efficiency bottlenecks for inference. Quantization, partic…

GoSGD: Distributed Optimization for Deep Learning with Gossip Exchange

2018-04-04 · Michael Blot, David Picard, Matthieu Cord

We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization setup uses several threads, each applyi…

Deep LearningDistributed Optimization

Learning Compact Neural Networks with Regularization

2018-02-05 · ICML 2018 7 · Samet Oymak

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for le…

Network Pruning