TRAL: A Tag-Aware Recommendation Algorithm Based on Attention Learning

Zuo, Yi; Liu, Shengzong; Zhou, Yun; Liu, Huanhua

doi:10.3390/app13020814

Cited by 6 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The underlying attention network can simulate the impact of different element pairs on the information, while the top-level attention network learns attention scores for different information. Zuo et al [40] employed attention mechanisms to differentiate the importance of different features in the tag space. They extracted lowdimensional dense features from the user-tag matrix and item-tag matrix, and a pooling layer with different attention compressed features into a single representation.…”

Section: Tag Recommendation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep feature fusion‐based stacked denoising autoencoder for tag recommendation systems

Fei,

Wang,

Liu

et al. 2023

IET Cyber-Syst and Robotics

View full text Add to dashboard Cite

With the rapid development of artificial intelligence technology, commercial robots have gradually entered our daily lives. In order to promote product dissemination, shopping guide robots are a new service options of commerce platforms that use tag recommendation systems to identify users' intentions. A large number of applications combine user historical tagging information with the multi‐round dialogue ability of shopping guide robots to help users efficiently search for and retrieve products of interest. Recently, tensor decomposition methods have become a common approach for modelling entity interaction relationships in tag recommendation systems. However, due to the sparsity of data, these methods only consider low‐order information of entities, making it difficult to capture the higher‐order collaborative signals among entities. Recommendation methods by autoencoders can effectively extract abstract feature representations while they only focus on the two‐dimensional relationship between users and items, ignoring the interaction relationship among users, items and tags in real complex recommendation scenarios. The authors focus on modelling the similarity relationship among entities and propose a method called deep feature fusion tag (DFFT) based on the deep feature fusion of stacked denoising autoencoders. This method can extract high‐order information with different embedding dimensions and fuse them in a unified framework. To extract robust feature representations, the authors inject random noise (mask‐out/drop‐out noise) into the tag information corresponding to users and items to generate corrupted input data, and then utilise autoencoders to encode the interaction relationship among entities. To further obtain the interaction relationship with different dimensions, different encoding layers are stacked and combined to produce a better expanded model which can reinforce each other. Finally, a decoding component is used to reconstruct the original input data. According to the experimental results on two common datasets, the proposed DFFT method outperforms other baselines in terms of the F1@N, NDCG@N and Recall@N evaluation metrics.

show abstract

Section: Tag Recommendation Methodsmentioning

confidence: 99%

“…Zuo et al. [40] employed attention mechanisms to differentiate the importance of different features in the tag space. They extracted low‐dimensional dense features from the user–tag matrix and item–tag matrix, and a pooling layer with different attention compressed features into a single representation.…”

Section: Related Workmentioning

confidence: 99%

Deep feature fusion‐based stacked denoising autoencoder for tag recommendation systems

Fei,

Wang,

Liu

et al. 2023

IET Cyber-Syst and Robotics

View full text Add to dashboard Cite

show abstract

“…Therefore, we explicitly partition the long-term interest features and use similarity and contrast loss to compensate for the shortcomings of previous methods. In practical applications, more side information is often introduced to enhance user and item features and reduce the bias of fusion features [27][28][29]. However, less research has been conducted on the enhancement of interest features.…”

Section: Introductionmentioning

confidence: 99%

CDF-LS: Contrastive Network for Emphasizing Feature Differences with Fusing Long- and Short-Term Interest Features

Liu

Wang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Modelling both long- and short-term user interests from historical data is crucial for generating accurate recommendations. However, unifying these metrics across multiple application domains can be challenging, and existing approaches often rely on complex, intertwined models which can be difficult to interpret. To address this issue, we propose a lightweight, plug-and-play interest enhancement module that fuses interest vectors from two independent models. After analyzing the dataset, we identify deviations in the recommendation performance of long- and short-term interest models. To compensate for these differences, we use feature enhancement and loss correction during training. In the fusion process, we explicitly split long-term interest features with longer duration into multiple local features. We then use a shared attention mechanism to fuse multiple local features with short-term interest features to obtain interaction features. To correct for bias between models, we introduce a comparison learning task that monitors the similarity between local features, short-term features, and interaction features. This adaptively reduces the distance between similar features. Our proposed module combines and compares multiple independent long-term and short-term interest models on multiple domain datasets. As a result, it not only accelerates the convergence of the models but also achieves outstanding performance in challenging recommendation scenarios.

show abstract