English
Related papers

Related papers: Growing Neural Network with Shared Parameter

200 papers

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural…

Machine Learning · Computer Science 2016-11-08 Ark Anderson , Kyle Shaffer , Artem Yankov , Court D. Corley , Nathan O. Hodas

Many tasks in natural language understanding require learning relationships between two sequences for various tasks such as natural language inference, paraphrasing and entailment. These aforementioned tasks are similar in nature, yet they…

Machine Learning · Statistics 2018-09-18 James O' Neill , Danushka Bollegala

This paper proposes to make a first step towards compatible and hence reusable network components. Rather than training networks for different tasks independently, we adapt the training process to produce network components that are…

Machine Learning · Computer Science 2020-12-17 Michael Gygli , Jasper Uijlings , Vittorio Ferrari

While increasingly large models have revolutionized much of the machine learning landscape, training even mid-sized networks for Reinforcement Learning (RL) is still proving to be a struggle. This, however, severely limits the complexity of…

Machine Learning · Computer Science 2025-06-16 Lukas Fehring , Marius Lindauer , Theresa Eimer

Tuning hyperparameters is a crucial but arduous part of the machine learning pipeline. Hyperparameter optimization is even more challenging in federated learning, where models are learned over a distributed network of heterogeneous devices;…

Machine Learning · Computer Science 2021-11-05 Mikhail Khodak , Renbo Tu , Tian Li , Liam Li , Maria-Florina Balcan , Virginia Smith , Ameet Talwalkar

Current state-of-the-art visual recognition systems usually rely on the following pipeline: (a) pretraining a neural network on a large-scale dataset (e.g., ImageNet) and (b) finetuning the network weights on a smaller, task-specific…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Guangrun Wang , Liang Lin , Rongcong Chen , Guangcong Wang , Jiqi Zhang

Using evolutionary computation algorithms to solve multiple tasks with knowledge sharing is a promising approach. Image feature learning can be considered as a multitask problem because different tasks may have a similar feature space.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-16 Ying Bi , Bing Xue , Mengjie Zhang

Novel architectures have recently improved generative image synthesis leading to excellent visual quality in various tasks. Much of this success is due to the scalability of these architectures and hence caused by a dramatic increase in…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Andreas Blattmann , Robin Rombach , Kaan Oktay , Jonas Müller , Björn Ommer

Graph-based and sequential methods are two popular recommendation paradigms, each excelling in its domain but lacking the ability to leverage signals from the other. To address this, we propose a novel method that integrates both approaches…

Information Retrieval · Computer Science 2025-01-30 Yuwei Cao , Liangwei Yang , Zhiwei Liu , Yuqing Liu , Chen Wang , Yueqing Liang , Hao Peng , Philip S. Yu

It is widely recognized that the deeper networks or networks with more feature maps have better performance. Existing studies mainly focus on extending the network depth and increasing the feature maps of networks. At the same time,…

Computer Vision and Pattern Recognition · Computer Science 2018-11-27 Shenlong Lou , Yan Luo , Qiancong Fan , Feng Chen , Yiping Chen , Cheng Wang , Jonathan Li

Machine learning models are often tuned by nesting optimization of model weights inside the optimization of hyperparameters. We give a method to collapse this nested optimization into joint stochastic optimization of weights and…

Machine Learning · Computer Science 2018-03-09 Jonathan Lorraine , David Duvenaud

In this work, a method of random parameters generation for randomized learning of a single-hidden-layer feedforward neural network is proposed. The method firstly, randomly selects the slope angles of the hidden neurons activation functions…

Machine Learning · Computer Science 2019-08-16 Grzegorz Dudek

Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works on neural network parameterisations, such as $\mu$P, have enabled transfer of optimal global hyperparameters across…

Machine Learning · Computer Science 2025-12-30 Bruno Mlodozeniec , Pierre Ablin , Louis Béthune , Dan Busbridge , Michal Klein , Jason Ramapuram , Marco Cuturi

Well-tuned hyperparameters are crucial for obtaining good generalization behavior in neural networks. They can enforce appropriate inductive biases, regularize the model and improve performance -- especially in the presence of limited data.…

Machine Learning · Computer Science 2023-05-01 Bruno Mlodozeniec , Matthias Reisser , Christos Louizos

The problem of learning simultaneously several related tasks has received considerable attention in several domains, especially in machine learning with the so-called multitask learning problem or learning to learn problem [1], [2].…

Signal Processing · Electrical Eng. & Systems 2021-09-29 Roula Nassif , Stefan Vlaski , Cedric Richard , Jie Chen , Ali H. Sayed

We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures. Our method works in a steepest descent fashion,…

Machine Learning · Computer Science 2021-06-22 Lemeng Wu , Bo Liu , Peter Stone , Qiang Liu

We introduce network with sub-networks, a neural network which its weight layers could be detached into sub-neural networks during inference. To develop weights and biases which could be inserted in both base and sub-neural networks,…

Machine Learning · Computer Science 2021-10-20 Ninnart Fuengfusin , Hakaru Tamukoh

Using a vocabulary that is shared across languages is common practice in Multilingual Neural Machine Translation (MNMT). In addition to its simple design, shared tokens play an important role in positive knowledge transfer, assuming that…

Computation and Language · Computer Science 2024-01-23 Di Wu , Christof Monz

Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training…

Recurrent neural networks have been widely used in sequence learning tasks. In previous studies, the performance of the model has always been improved by either wider or deeper structures. However, the former becomes more prone to…

Machine Learning · Computer Science 2019-11-20 Yu-Xuan Li , Jin-Yuan Liu , Liang Li , Xiang Guan