One‐dimensional convolutional neural networks for high‐resolution range profile recognition via adaptively feature recalibrating and automatically channel pruning

Xiang, Qian; Wang, Xiaodan; Song, Yafei; Lei, Lei; Li, Rui; Lai, Jie

doi:10.1002/int.22302

Cited by 27 publications

(25 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They defined the embedding table search space by blocks and adjusted the controller with the validation set, making the model automatically determine the embedding size by maximizing the accuracy under the constraint of the embedding table memory. On top of that, some other neural search approaches such as Neural Architecture Search (NAS), 17 Efficient Neural Architecture Search (ENAS), 18 and Differentiable Architecture Search (DAS) 19 are also utilized to automatically determine the size of embeddings and some of them have been deployed in the industry media recommender systems and achieved certain benefits. Model Compression: 20,21 Common model compression technologies mainly includes pruning, 22 quantization 23 and distillation 24 . For example, Liu et al 10 compressed the embedding table by pruning the embedded vectors of each feature domain of the data.…”

Section: Related Workmentioning

confidence: 99%

“…Model Compression: 20,21 Common model compression technologies mainly includes pruning, 22 quantization 23 and distillation 24 . For example, Liu et al 10 compressed the embedding table by pruning the embedded vectors of each feature domain of the data.…”

Section: Related Workmentioning

confidence: 99%

“…Auto Machine Learning (AutoML): 7 Joglekar et al 16 17 Efficient Neural Architecture Search (ENAS), 18 and Differentiable Architecture Search (DAS) 19 are also utilized to automatically determine the size of embeddings and some of them have been deployed in the industry media recommender systems and achieved certain benefits. Model Compression: 20,21 Common model compression technologies mainly includes pruning, 22 quantization 23 and distillation. 24 For example, Liu et al 10 compressed the embedding table by pruning the embedded vectors of each feature domain of the data.…”

Section: Lightweight Embeddingmentioning

confidence: 99%

See 2 more Smart Citations

Exploring lottery ticket hypothesis in media recommender systems

Wang¹,

Sui²,

Wang³

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Media recommender systems aim to capture users’ preferences and provide precise personalized recommendation of media content. There are two critical components in the common paradigm of modern recommender models: (1) representation learning, which generates an embedding for each user and item; and (2) interaction modeling, which fits user preferences toward items based on their representations. In spite of great success, when a great amount of users and items exist, it usually needs to create, store, and optimize a huge embedding table, where the scale of model parameters easily reach millions or even larger. Hence, it naturally raises questions about the heavy recommender models: Do we really need such large‐scale parameters? We get inspirations from the recently proposed lottery ticket hypothesis (LTH), which argues that the dense and over‐parameterized model contains a much smaller and sparser sub‐model that can reach comparable performance to the full model. In this paper, we extend LTH to media recommender systems, aiming to find the winning tickets in deep recommender models. To the best of our knowledge, this is the first work to study LTH in media recommender systems. With Matrix Factorization and Light Graph Convolution Networks as the backbone models, we found that there widely exist winning tickets in recommender models. On three media convergence data sets—Yelp2018, TikTok and Kwai, the winning tickets can achieve comparable recommendation performance with only 29 % ~ 48 % , 7 % ~ 10 %, and 3 % ~ 17 % of parameters, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Lightweight Embeddingmentioning

confidence: 99%

See 1 more Smart Citation

Exploring lottery ticket hypothesis in media recommender systems

Wang¹,

Sui²,

Wang³

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…Model Compression. 20;21 Common model compression technologies mainly includes pruning 22 , quantization 23 and distillation 24 . For example, Liu et al 10 compressed the embedding table by pruning the embedded vectors of each feature domain of the data.…”

Section: Lightweight Embeddingmentioning

confidence: 99%

Exploring Lottery Ticket Hypothesis in Media Recommender Systems

Wang,

Sui,

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Media recommender systems aim to capture users' preferences and provide precise personalized recommendation of media content. There are two critical components in the common paradigm of modern recommender models: (1) representation learning, which generates an embedding for each user and item; and (2) interaction modeling, which fits user preferences towards items based on their representations. Despite of great success, when a great amount of users and items exist, it usually needs to create, store, and optimize a huge embedding table, where the scale of model parameters easily reach millions or even larger. Hence, it naturally raises questions about the heavy recommender models: Do we really need such large-scale parameters?We get inspirations from the recently proposed lottery ticket hypothesis (LTH), which argues that the dense and overparameterized model contains a much smaller and sparser sub-model that can reach comparable performance to the full model. In this paper, we extend LTH to media recommender systems, aiming to find the winning tickets in deep recommender models. To the best of our knowledge, this is the first work to study LTH in media recommender systems. With MF and LightGCN as the backbone models, we found that there widely exist winning tickets in recommender models. On three media convergence datasets -1

show abstract

“…2D CNNs have been successfully used to learn and reconstruct features from raw data and have developed into the dominant approach for accomplishing recognition and detection tasks of image and speech analysis [33]. Due to the good characteristics of CNN learning, 1D CNN has been proposed to address 1D signals based on 2D CNN and has achieved superior performance with high efficiency [34,35]. To adapt to the data characteristics of 1D signals, comparing 2D CNNs, the hierarchical architecture of 1D CNNs is simplified [36].…”

Section: Introductionmentioning

confidence: 99%

Network Threat Detection Based on Group CNN for Privacy Protection

Zhang

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The Internet of Things (IoT) contains a large amount of data, which attracts various types of network attacks that lead to privacy leaks. With the upgrading of network attacks and the increase in network security data, traditional machine learning methods are no longer suitable for network threat detection. At the same time, data analysis techniques and deep learning algorithms have developed rapidly and have been successfully applied to a variety of tasks for privacy protection. Convolutional neural networks (CNNs) are typical deep learning models that can learn and reconstruct features accurately and efficiently. Therefore, in this paper, we propose a group CNN models that is based on feature correlations to learn features and reconstruct security data. First, feature correlation coefficients are computed to measure the relationships among the features. Then, we sort the correlation coefficients in descending order and group the data by columns. Second, a 1D group CNN model with multiple 1D convolution kernels and 1D pooling filters is built to address the grouped data for feature learning and reconstruction. Third, the reconstructed features are input to shadow machine learning models for network threat prediction. The experimental results show that features reconstructed by the group CNN can reduce the dimensions and achieve the best performance compared to the other present dimension reduction algorithms. At the same time, the group CNN can decrease the floating point of operations (FLOP), parameters, and running time compared to the basic 1D CNN.

show abstract

One‐dimensional convolutional neural networks for high‐resolution range profile recognition via adaptively feature recalibrating and automatically channel pruning

Cited by 27 publications

References 39 publications

Exploring lottery ticket hypothesis in media recommender systems

Exploring lottery ticket hypothesis in media recommender systems

Exploring Lottery Ticket Hypothesis in Media Recommender Systems

Network Threat Detection Based on Group CNN for Privacy Protection

Contact Info

Product

Resources

About