English
Related papers

Related papers: Parameter-efficient Multi-Task and Multi-Domain Le…

200 papers

Tensor Networks (TN) offer a powerful framework to efficiently represent very high-dimensional objects. TN have recently shown their potential for machine learning applications and offer a unifying view of common tensor decomposition models…

Machine Learning · Computer Science 2021-06-24 Meraj Hashemizadeh , Michelle Liu , Jacob Miller , Guillaume Rabusseau

Graph Neural Networks (GNNs) are a framework for graph representation learning, where a model learns to generate low dimensional node embeddings that encapsulate structural and feature-related information. GNNs are usually trained in an…

Machine Learning · Computer Science 2020-12-15 Davide Buffelli , Fabio Vandin

This paper introduces a tensor neural network (TNN) to address nonparametric regression problems, leveraging its distinct sub-network structure to effectively facilitate variable separation and enhance the approximation of complex,…

Machine Learning · Statistics 2024-09-16 Yongxin Li , Yifan Wang , Zhongshuo Lin , Hehu Xie

In pursuit of reinforcement learning systems that could train in physical environments, we investigate multi-task approaches as a means to alleviate the need for massive data acquisition. In a tabular scenario where the Q-functions are…

Machine Learning · Computer Science 2025-01-22 Sergio Rozada , Santiago Paternain , Juan Andres Bazerque , Antonio G. Marques

Depth factorization and quantization have emerged as two of the principal strategies for designing efficient deep convolutional neural network (CNN) architectures tailored for low-power inference on the edge. However, there is still little…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Stone Yun , Alexander Wong

A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain. Recently, inspired by the successes of transfer learning, several authors have proposed to learn instead universal,…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Sylvestre-Alvise Rebuffi , Hakan Bilen , Andrea Vedaldi

The prominence of deep learning, large amount of annotated data and increasingly powerful hardware made it possible to reach remarkable performance for supervised classification tasks, in many cases saturating the training sets. However the…

Computer Vision and Pattern Recognition · Computer Science 2019-11-25 Adrian Bulat , Jean Kossaifi , Georgios Tzimiropoulos , Maja Pantic

We present two simple ways of reducing the number of parameters and accelerating the training of large Long Short-Term Memory (LSTM) networks: the first one is "matrix factorization by design" of LSTM matrix into the product of two smaller…

Computation and Language · Computer Science 2018-02-27 Oleksii Kuchaiev , Boris Ginsburg

Multi-task networks rely on effective parameter sharing to achieve robust generalization across tasks. In this paper, we present a novel parameter sharing method for multi-task learning that conditions parameter sharing on both the task and…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Elahe Rahimian , Golara Javadi , Frederick Tung , Gabriel Oliveira

Convolutional networks (ConvNets) have become a popular approach to computer vision. It is important to accelerate ConvNet training, which is computationally costly. We propose a novel parallel algorithm based on decomposition into a set of…

Neural and Evolutionary Computing · Computer Science 2016-06-21 Aleksandar Zlateski , Kisuk Lee , H. Sebastian Seung

Multi-task learning (MTL) jointly learns a set of tasks by sharing parameters among tasks. It is a promising approach for reducing storage costs while improving task accuracy for many computer vision tasks. The effective adoption of MTL…

Machine Learning · Computer Science 2022-10-03 Lijun Zhang , Xiao Liu , Hui Guan

Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find…

Machine Learning · Statistics 2018-11-20 Sebastian Ruder , Joachim Bingel , Isabelle Augenstein , Anders Søgaard

Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed…

Computer Vision and Pattern Recognition · Computer Science 2016-11-17 Yongxi Lu , Abhishek Kumar , Shuangfei Zhai , Yu Cheng , Tara Javidi , Rogerio Feris

Deep Q-learning has achieved significant success in single-agent decision making tasks. However, it is challenging to extend Q-learning to large-scale multi-agent scenarios, due to the explosion of action space resulting from the complex…

Multiagent Systems · Computer Science 2019-10-14 Ming Zhou , Yong Chen , Ying Wen , Yaodong Yang , Yufeng Su , Weinan Zhang , Dell Zhang , Jun Wang

In Convolutional Neural Network (CNN) based image processing, most of the studies propose networks that are optimized for a single-level (or a single-objective); thus, they underperform on other levels and must be retrained for delivery of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-13 Hyeongmin Lee , Taeoh Kim , Hanbin Son , Sangwook Baek , Minsu Cheon , Sangyoun Lee

State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forgetting. However, there is a tradeoff between the number of…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Thomas De Min , Massimiliano Mancini , Karteek Alahari , Xavier Alameda-Pineda , Elisa Ricci

Tensor decomposition is a popular technique for tensor completion, However most of the existing methods are based on linear or shallow model, when the data tensor becomes large and the observation data is very small, it is prone to over…

Numerical Analysis · Mathematics 2021-05-21 Qianxi Wu , An-Bao Xu

Traditional methods for tabular classification usually rely on supervised learning from scratch, which requires extensive training data to determine model parameters. However, a novel approach called Prior-Data Fitted Networks (TabPFN) has…

Machine Learning · Computer Science 2024-06-12 Quangao Liu , Wei Yang , Chen Liang , Longlong Pang , Zhuozhang Zou

Modern transportation network modeling increasingly involves the integration of diverse methodologies including sensor-based forecasting, reinforcement learning, classical flow optimization, and demand modeling that have traditionally been…

Optimization and Control · Mathematics 2025-07-08 Xuesong , Zhou , Taehooie Kim , Mostafa Ameli , Henan , Zhu , Yu- dai Honma , Ram M. Pendyala

The classical approach to non-linear regression in physics, is to take a mathematical model describing the functional dependence of the dependent variable from a set of independent variables, and then, using non-linear fitting algorithms,…

Machine Learning · Computer Science 2020-07-29 Umberto , Michelucci , Francesca Venturini