English
Related papers

Related papers: Understanding Parameter Sharing in Transformers

200 papers

Transformer-based models have recently become wildly successful across a diverse set of domains. At the same time, recent work has shown empirically and theoretically that Transformers are inherently limited. Specifically, they argue that…

Machine Learning · Computer Science 2024-07-30 Gbètondji J-S Dovonon , Michael M. Bronstein , Matt J. Kusner

In this work we analyze strategies for convolutional neural network scaling; that is, the process of scaling a base convolutional network to endow it with greater computational complexity and consequently representational power. Example…

Computer Vision and Pattern Recognition · Computer Science 2021-03-12 Piotr Dollár , Mannat Singh , Ross Girshick

Federated learning (FL) enables wireless terminals to collaboratively learn a shared parameter model while keeping all the training data on devices per se. Parameter sharing consists of synchronous and asynchronous ways: the former…

Information Theory · Computer Science 2024-01-17 Haihui Xie , Minghua Xia , Peiran Wu , Shuai Wang , Kaibin Huang

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-03 Zhengxian Lu , Fangyu Wang , Zhiwei Xu , Fei Yang , Tao Li

Transformer becomes the state-of-the-art translation model, while it is not well studied how each intermediate component contributes to the model performance, which poses significant challenges for designing optimal architectures. In this…

Computation and Language · Computer Science 2020-11-10 Wenxuan Wang , Zhaopeng Tu

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial…

We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead…

Machine Learning · Computer Science 2019-02-26 Pramod Kaushik Mudrakarta , Mark Sandler , Andrey Zhmoginov , Andrew Howard

Overparameterization, the condition where models have more parameters than necessary to fit their training loss, is a crucial factor for the success of deep learning. However, the characteristics of the features learned by overparameterized…

Machine Learning · Computer Science 2024-07-02 Ahmet Cagri Duzgun , Samy Jelassi , Yuanzhi Li

Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity. Indeed, neural networks often have many more parameters than there are data points, yet still provide good…

Machine Learning · Computer Science 2020-05-26 Wesley J. Maddox , Gregory Benton , Andrew Gordon Wilson

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…

Computation and Language · Computer Science 2021-06-10 Demi Guo , Alexander M. Rush , Yoon Kim

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Computation and Language · Computer Science 2020-06-24 Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , Joseph E. Gonzalez

Trainable layers such as convolutional building blocks are the standard network design choices by learning parameters to capture the global context through successive spatial operations. When designing an efficient network, trainable layers…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Dongyoon Han , YoungJoon Yoo , Beomyoung Kim , Byeongho Heo

With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been…

Machine Learning · Statistics 2025-07-09 Javan Tahir , Surya Ganguli , Grant M. Rotskoff

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 first trains BERT with…

Machine Learning · Computer Science 2021-10-11 Shuo Yang , Le Hou , Xiaodan Song , Qiang Liu , Denny Zhou

Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high-performing models share similar biases regardless of training…

Machine Learning · Computer Science 2022-04-27 Raphael Gontijo-Lopes , Yann Dauphin , Ekin D. Cubuk

The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results. However, the scaling up of large foundation models has led to soaring costs in…

Machine Learning · Computer Science 2024-12-30 Chongjie Si , Xiaokang Yang , Wei Shen

Solving multiple visual tasks using individual models can be resource-intensive, while multi-task learning can conserve resources by sharing knowledge across different tasks. Despite the benefits of multi-task learning, such techniques can…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Sara Shoouri , Mingyu Yang , Zichen Fan , Hun-Seok Kim

Distributed optimization algorithms are widely used in machine learning. This paper investigates how a small amount of data sharing can improve their performance. Focusing on general linear models, we analyze the effects of data sharing on…

Optimization and Control · Mathematics 2025-05-19 Mingxi Zhu , Yinyu Ye

More transformer blocks with residual connections have recently achieved impressive results on various tasks. To achieve better performance with fewer trainable parameters, recent methods are proposed to go shallower by parameter sharing or…

Machine Learning · Computer Science 2021-09-08 Fuzhao Xue , Ziji Shi , Futao Wei , Yuxuan Lou , Yong Liu , Yang You

Many deep learning applications benefit from using large models with billions of parameters. Training these models is notoriously expensive due to the need for specialized HPC clusters. In this work, we consider alternative setups for…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-06-30 Max Ryabinin , Tim Dettmers , Michael Diskin , Alexander Borzunov