English
Related papers

Related papers: Transfer Learning Between Different Architectures …

200 papers

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

Machine Learning · Computer Science 2019-07-15 Farshid Varno , Behrouz Haji Soleimani , Marzie Saghayi , Lisa Di Jorio , Stan Matwin

This paper presents a data-efficient approach to learning transferable forward models for robotic push manipulation. Our approach extends our previous work on contact-based predictors by leveraging information on the pushed object's local…

Robotics · Computer Science 2019-05-10 Jochen Stüber , Marek Kopicki , Claudio Zito

In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-two weight representation and, as a result, performs only…

Computer Vision and Pattern Recognition · Computer Science 2017-06-09 Denis A. Gudovskiy , Luca Rigazio

In this paper, we propose Transformer Layer Injection (TLI), a novel method for efficiently upscaling large language models (LLMs) while minimizing computational costs and maintaining model performance. Model scale is a key factor in…

Computation and Language · Computer Science 2024-10-16 James Vo

Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in…

Machine Learning · Computer Science 2025-04-04 Jiho Choi , Donggyun Kim , Chanhyuk Lee , Seunghoon Hong

The existing domain-specific methods for mining information networks in machine learning aims to represent the nodes of an information network into a vector format. However, the real-world large-scale information network cannot make well…

Social and Information Networks · Computer Science 2019-11-13 Shan Xue , Jie Lu , Guangquan Zhang , Li Xiong

State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…

Artificial Intelligence · Computer Science 2017-11-08 Karim Ahmed , Nitish Shirish Keskar , Richard Socher

Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed…

Machine Learning · Computer Science 2019-11-27 Mark Edmonds , Xiaojian Ma , Siyuan Qi , Yixin Zhu , Hongjing Lu , Song-Chun Zhu

Exploiting the great expressive power of Deep Neural Network architectures, relies on the ability to train them. While current theoretical work provides, mostly, results showing the hardness of this task, empirical evidence usually differs…

Machine Learning · Computer Science 2017-06-05 Shai Shalev-Shwartz , Ohad Shamir , Shaked Shammah

Transfer learning is a problem defined over two domains. These two domains share the same feature space and class label space, but have significantly different distributions. One domain has sufficient labels, named as source domain, and the…

Machine Learning · Computer Science 2016-05-24 Hongqi Wang , Anfeng Xu , Shanshan Wang , Sunny Chughtai

Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operations on these parameters to manipulate the underlying…

Computation and Language · Computer Science 2024-05-09 Ming Zhong , Chenxin An , Weizhu Chen , Jiawei Han , Pengcheng He

Deep learning based models are used regularly in every applications nowadays. Generally we train a single model on a single task. However, we can train multiple tasks on a single model under multi-task learning settings. This provides us…

Machine Learning · Computer Science 2023-03-14 Aminul Huq , Mst Tasnim Pervin

Continual learning is a challenge for models with static architecture, as they fail to adapt to when data distributions evolve across tasks. We introduce a mathematical framework that jointly models architecture and weights in a Sobolev…

Machine Learning · Computer Science 2026-01-28 Allyson Hahn , Krishnan Raghavan

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

Encrypted traffic classification (TC) methods must adapt to new protocols and extensions as well as to advancements in other machine learning fields. In this paper, we adopt a transfer learning setup best known from computer vision. We…

Machine Learning · Computer Science 2026-01-21 Jan Luxemburk , Karel Hynek , Richard Plný , Tomáš Čejka

Data-driven methods -- such as machine learning and time series forecasting -- are widely used for sales forecasting in the food retail domain. However, for newly introduced products insufficient training data is available to train accurate…

Machine Learning · Computer Science 2020-05-15 Tristan Karb , Niklas Kühl , Robin Hirt , Varvara Glivici-Cotruta

The homogeneity, or more generally, the similarity between source domains and a target domain seems to be essential to a positive transfer learning. In practice, however, the similarity condition is difficult to check and is often violated.…

Methodology · Statistics 2023-02-23 Lu Lin , Weiyu Li

Given new tasks with very little data$-$such as new classes in a classification problem or a domain shift in the input$-$performance of modern vision systems degrades remarkably quickly. In this work, we illustrate how the neural network…

Computer Vision and Pattern Recognition · Computer Science 2021-02-18 Carl Doersch , Ankush Gupta , Andrew Zisserman

In this work, we present a novel approach for simultaneous knowledge transfer and model compression called Weight Squeezing. With this method, we perform knowledge transfer from a teacher model by learning the mapping from its weights to…

Machine Learning · Computer Science 2021-08-31 Artem Chumachenko , Daniil Gavrilov , Nikita Balagansky , Pavel Kalaidin

Machine-learning models in chemistry - when based on descriptors of atoms embedded within molecules - face essential challenges in transferring the quality of predictions of local electronic structures and their associated properties across…

Chemical Physics · Physics 2024-09-27 Frederik Ø. Kjeldal , Janus J. Eriksen
‹ Prev 1 8 9 10 Next ›