English
Related papers

Related papers: Subformer: Exploring Weight Sharing for Parameter …

200 papers

In this work, we introduce a method to fine-tune a Transformer-based generative model for molecular de novo design. Leveraging the superior sequence learning capacity of Transformers over Recurrent Neural Networks (RNNs), our model can…

Machine Learning · Computer Science 2024-03-11 Pengcheng Xu , Tao Feng , Tianfan Fu , Siddhartha Laghuvarapu , Jimeng Sun

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention…

Machine Learning · Computer Science 2025-10-07 Ruoxi Yu , Haotian Jiang , Jingpu Cheng , Penghao Yu , Qianxiao Li , Zhong Li

Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training examples, making it difficult to avoid overfitting, even when…

In this paper, we explore the idea of weight sharing over multiple scales in convolutional networks. Inspired by traditional computer vision approaches, we share the weights of convolution kernels over different scales in the same layers of…

Computer Vision and Pattern Recognition · Computer Science 2020-01-10 Shubhra Aich , Ian Stavness , Yasuhiro Taniguchi , Masaki Yamazaki

Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further improve graph…

Machine Learning · Computer Science 2021-07-21 Xueting Han , Zhenhuan Huang , Bang An , Jing Bai

Hyperparameter optimization is very frequently employed in machine learning. However, an optimization of a large space of parameters could result in overfitting of models. In recent studies on solubility prediction the authors collected…

Machine Learning · Computer Science 2024-11-26 Igor V. Tetko , Ruud van Deursen , Guillaume Godin

Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sharing practice is to share the bottom layers of a deep…

Machine Learning · Computer Science 2022-03-22 Lijun Zhang , Qizheng Yang , Xiao Liu , Hui Guan

The Universal Transformer (UT) is a variant of the Transformer that shares parameters across its layers. Empirical evidence shows that UTs have better compositional generalization than Vanilla Transformers (VTs) in formal language tasks.…

Computation and Language · Computer Science 2023-10-12 Shawn Tan , Yikang Shen , Zhenfang Chen , Aaron Courville , Chuang Gan

Foundation models, with a vast number of parameters and pretraining on massive datasets, achieve state-of-the-art performance across various applications. However, efficiently adapting them to downstream tasks with minimal computational…

Machine Learning · Computer Science 2025-04-07 Van-Anh Nguyen , Thanh-Toan Do , Mehrtash Harandi , Dinh Phung , Trung Le

Ensemble of machine learning models yields improved performance as well as robustness. However, their memory requirements and inference costs can be prohibitively high. Knowledge distillation is an approach that allows a single model to…

Computer Vision and Pattern Recognition · Computer Science 2022-10-06 Zhengcong Fei , Shuman Tian , Junshi Huang , Xiaoming Wei , Xiaolin Wei

The current landscape in time-series forecasting is dominated by Transformer-based models. Their high parameter count and corresponding demand in computational resources pose a challenge to real-world deployment, especially for commercial…

Machine Learning · Computer Science 2024-12-18 Nicholas Kiefer , Arvid Weyrauch , Muhammed Öz , Achim Streit , Markus Götz , Charlotte Debus

Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision, e.g., GPT-3 and Swin Transformer. Although originally…

Machine Learning · Computer Science 2023-06-27 Muning Wen , Runji Lin , Hanjing Wang , Yaodong Yang , Ying Wen , Luo Mai , Jun Wang , Haifeng Zhang , Weinan Zhang

Modern Foundation Models (FMs) are typically trained on corpora spanning a wide range of different data modalities, topics and downstream tasks. Utilizing these models can be very computationally expensive and is out of reach for most…

Machine Learning · Computer Science 2025-06-09 Andrey Zhmoginov , Jihwan Lee , Mark Sandler

We introduce EdgeFormer -- a parameter-efficient Transformer for on-device seq2seq generation under the strict computation and memory constraints. Compared with the previous parameter-efficient Transformers, EdgeFormer applies two novel…

Computation and Language · Computer Science 2023-01-02 Tao Ge , Si-Qing Chen , Furu Wei

The video action segmentation task is regularly explored under weaker forms of supervision, such as transcript supervision, where a list of actions is easier to obtain than dense frame-wise labels. In this formulation, the task presents…

Computer Vision and Pattern Recognition · Computer Science 2022-01-24 John Ridley , Huseyin Coskun , David Joseph Tan , Nassir Navab , Federico Tombari

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

We consider the problem of test-time domain generalization, where a model is trained on several source domains and adjusted on target domains never seen during training. Different from the common methods that fine-tune the model or adjust…

Machine Learning · Computer Science 2025-02-19 Sameer Ambekar , Zehao Xiao , Xiantong Zhen , Cees G. M. Snoek

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language models (LLMs) in recent years. A promising direction to further…

Machine Learning · Computer Science 2026-02-02 Zekai Li , Ji Liu , Guanchen Li , Yixing Xu , Ziqiong Liu , Xuanwu Yin , Dong Li , Emad Barsoum

With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention. As training every child model from scratch is very time-consuming, recent works leverage…

Machine Learning · Computer Science 2020-01-07 Yuge Zhang , Zejun Lin , Junyang Jiang , Quanlu Zhang , Yujing Wang , Hui Xue , Chen Zhang , Yaming Yang

Diffusion models have gained popularity in graph generation tasks; however, the extent of their expressivity concerning the graph distributions they can learn is not fully understood. Unlike models in other domains, popular backbones for…

Machine Learning · Computer Science 2025-02-05 Xiyuan Wang , Yewei Liu , Lexi Pang , Siwei Chen , Muhan Zhang