English
Related papers

Related papers: Understanding Parameter Sharing in Transformers

200 papers

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally correlates with…

Computation and Language · Computer Science 2022-08-16 Hassan Sajjad , Fahim Dalvi , Nadir Durrani , Preslav Nakov

To keep up with increasing dataset sizes and model complexity, distributed training has become a necessity for large machine learning tasks. Parameter servers ease the implementation of distributed parameter management---a key concern in…

Machine Learning · Computer Science 2020-07-06 Alexander Renz-Wieland , Rainer Gemulla , Steffen Zeuch , Volker Markl

Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models…

Machine Learning · Computer Science 2020-02-24 Jeffrey Li , Mikhail Khodak , Sebastian Caldas , Ameet Talwalkar

Adapter Tuning, which freezes the pretrained language models (PLMs) and only fine-tunes a few extra modules, becomes an appealing efficient alternative to the full model fine-tuning. Although computationally efficient, the recent Adapters…

Computation and Language · Computer Science 2022-11-11 Shwai He , Liang Ding , Daize Dong , Miao Zhang , Dacheng Tao

Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks. Such property is in prevalent use in real-world…

Machine Learning · Computer Science 2019-09-27 Hong Liu , Mingsheng Long , Jianmin Wang , Michael I. Jordan

Symmetry in the parameter space of deep neural networks (DNNs) has proven beneficial for various deep learning applications. A well-known example is the permutation symmetry in Multi-Layer Perceptrons (MLPs), where permuting the rows of…

Machine Learning · Computer Science 2025-05-30 Binchi Zhang , Zaiyi Zheng , Zhengzhang Chen , Jundong Li

MOTIVATION: Proteins fold into complex structures that are crucial for their biological functions. Experimental determination of protein structures is costly and therefore limited to a small fraction of all known proteins. Hence, different…

Biomolecules · Quantitative Biology 2018-04-18 David Menéndez Hurtado , Karolis Uziela , Arne Elofsson

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis

Recent isotropic networks, such as ConvMixer and vision transformers, have found significant success across visual recognition tasks, matching or outperforming non-isotropic convolutional neural networks (CNNs). Isotropic architectures are…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Chien-Yu Lin , Anish Prabhu , Thomas Merth , Sachin Mehta , Anurag Ranjan , Maxwell Horton , Mohammad Rastegari

The performance of neural network classifiers is determined by a number of hyperparameters, including learning rate, batch size, and depth. A number of attempts have been made to explore these parameters in the literature, and at times, to…

Neural and Evolutionary Computing · Computer Science 2015-08-13 Thomas M. Breuel

We explore the impact of parameter sparsity on the scaling behavior of Transformers trained on massive datasets (i.e., "foundation models"), in both vision and language domains. In this setting, we identify the first scaling law describing…

Machine Learning · Computer Science 2023-09-18 Elias Frantar , Carlos Riquelme , Neil Houlsby , Dan Alistarh , Utku Evci

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

Deep convolutional neural networks (DCNNs) have become the state-of-the-art (SOTA) approach for many computer vision tasks: image classification, object detection, semantic segmentation, etc. However, most SOTA networks are too large for…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Alireza Azadbakht , Saeed Reza Kheradpisheh , Ismail Khalfaoui-Hassani , Timothée Masquelier

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together. Every few iterations, the RL agent is asked…

Machine Learning · Computer Science 2024-01-24 Tamir David Hay , Lior Wolf

Large language models are often adapted using parameter-efficient techniques such as Low-Rank Adaptation (LoRA), formulated as $y = W_0x + BAx$, where $W_0$ is the pre-trained parameters and $x$ is the input to the adapted layer. While…

Machine Learning · Computer Science 2026-04-28 Hao Ban , Kaiyi Ji

In the software development process, model transformation is increasingly assimilated. However, systems being developed with model transformation sometimes grow in size and become complex. Meanwhile, the performance of model transformation…

Software Engineering · Computer Science 2020-04-21 Vijayshree Vijayshree , Markus Frank , Steffen Becker

Over time, a growing wave of large language models from various series has been introduced to the community. Researchers are striving to maximize the performance of language models with constrained parameter sizes. However, from a…

Computation and Language · Computer Science 2025-11-24 Yihuai Hong , Yiran Zhao , Wei Tang , Yang Deng , Yu Rong , Wenxuan Zhang

The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from the new domain would address this issue, it is often too…

Computer Vision and Pattern Recognition · Computer Science 2018-03-13 Artem Rozantsev , Mathieu Salzmann , Pascal Fua

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva

Traditional end-to-end deep learning models often enhance feature representation and overall performance by increasing the depth and complexity of the network during training. However, this approach inevitably introduces issues of parameter…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Yuming Zhang , Peizhe Wang , Shouxin Zhang , Dongzhi Guan , Jiabin Liu , Junhao Su
‹ Prev 1 4 5 6 7 8 10 Next ›