Adversarial Learning for Personalized Tag Recommendation

Quintanilla, Erik; Rawat, Yogesh Singh; Sakryukin, Andrey; Shah, Mubarak; Kankanhalli, Mohan

doi:10.1109/tmm.2020.2992941

Cited by 26 publications

(10 citation statements)

References 66 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…People are increasingly demanding tailored learning as modern society progresses. e rapid growth of online learning technology is due to the advent of education informatization [1]. Most contemporary online learning tools, on the other hand, are homogenized, neglecting learners' unique peculiarities and failing to suit their specific demands.…”

Section: Introductionmentioning

confidence: 99%

Method of Ideological and Political Teaching Resources in Universities Based on School-Enterprise Cooperation Mode

Xia¹,

Ahmad

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The personalized recommendation system influences the recommendation of ideological and political teaching resources in universities, resulting in a high MAE score. As a result, under the school-enterprise collaboration paradigm, this study proposes a customised recommendation approach for ideological and political teaching resources in colleges and universities. The ideological and political teaching resource bank is developed against the backdrop of the teaching paradigm that combines universities and businesses. Learners’ browsing data history is gathered to create a learning interest model for them. A hybrid collaborative filtering recommendation method was devised, and a recommendation engine was established by Taste component, taking into account individualised resource recommendation needs and information entropy weight distribution mode. When compared to previous techniques, the developed customised recommendation method considerably enhances the recommendation quality of instructional resources and reduces MAE by 29% and 34%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Method of Ideological and Political Teaching Resources in Universities Based on School-Enterprise Cooperation Mode

Xia¹,

Ahmad

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Tensor factorization methods have good decomposition effect and can handle user-tag and item-tag interactions separately, predicting tag-ranked lists based on users' historical behaviors. In addition, deep neural networks (DNN) have been used for tag recommendation [35], [36], [5] to mine the entity relationships of hidden information in data, and these methods improve the performance of traditional tag recommendation algorithms due to the effective learning capability of DNN. Although tensor factorization and deep neural network methods have been shown to be effective for modeling entity information, they do not satisfy the triangle inequality and cannot capture the fine-grained preference information.…”

Section: Related Work a Tag Recommendationmentioning

confidence: 99%

“…Since different users tend to provide different tags for the same item, it is quite important to provide individual users with tags that match their personalities. Tag recommendation [2], [3], [4], [5] infers the probability that a given user is likely to annotate tags for a specific item from the given historical interactive data, and also needs to satisfy the user to describe an item using keywords (tags) based on their own understanding to predict a personalized Top-N tag list. For example, Movielens platform recommends relevant tags for users according to their individual needs to describe a movie of interest.…”

mentioning

confidence: 99%

Pairwise Metric Learning With Angular Margin for Tag Recommendation

et al. 2023

View full text Add to dashboard Cite

The users on the Internet have been growing exponentially, and tag recommendation can automatically provide users with a selection of tags of interest to meet their personalized needs. Users can utilize these tags to freely annotate their favorite resources, making them efficient and fast in retrieving related resources. Tensor factorization methods are commonly used in tag recommendation at present. These methods model the user × item × tag interactions, transform the latent feature representations of users, items and tags into low-rank matrices and use inner products for prediction. However, the problem of using inner product is that it does not satisfy the triangle inequality, it ignores the distance relationship among entity pairs and cannot capture the fine-grained preference information. Metric learning in recommendation domains focus on using pairwise loss, which assumes that different categories (such as users, items and tags) have fixed margins. Different categories often have different intra-class variations. With fixed margins, it is often difficult to accurately distinguish between positive and negative samples, thus reducing recommendation performance and limiting the expression ability of the model. In this study, the metric learning method is used to explore the distance relationship among user × item × tag triplet, and the existing metric learning based methods (namely LRML, CML, SML) are applied to the tag recommendation. A pairwise metric learning method with angular margin is proposed, named PMLT. The pairwise distance relationship between user-tag and item-tag is modeled for the information of different entities. And an extra angular margin regularizer is added to the original pairwise loss to control the size of angular margin for user-tag and item-tag respectively. The strength of the constrained angular margin regularizer is controlled to dynamically adjust the distance changes of entity. This method constrains the fixed margin and also the angular margin of user-tag and item-tag. Compared with the traditional metric learning method, this method can capture additional relationship structure and has good recommendation performance. Finally, we conducted extensive experiments on two datasets, LastFm and Movielens, and the experimental results showed that the proposed method PMLT outperform the state-of-the-art baseline in the evaluation metrics Recall@N and NDCG@N, and obtain better prediction quality. We also analyze the influence of different parameters and internal components on the performance of the proposed method, which improves the interpretability of the proposed method.INDEX TERMS Tag recommendation, tensor factorization, metric learning, angular margin.

show abstract

“…Although there are applications in the field of recommendation systems [ 23 , 24 ], the application of adversarial learning in temporal set recommendation is an unexplored task. Inspired by the application of generative adversarial networks in image multi-tag recommendation [ 6 ], we introduce generative adversarial networks into our study.…”

Section: Related Workmentioning

confidence: 99%

“…All the independent recommendation model learns about is the treatment pattern between inpatient days, but the individual features of inpatients are not emphasized. Inspired by [ 6 ], a generative adversarial network is used to solve this problem. The goal is to train the recommendation network to learn effective features which can recommend medical activities which better match the individual characteristics of inpatients.…”

Section: Introductionmentioning

confidence: 99%

Next-Day Medical Activities Recommendation Model with Double Attention Mechanism Using Generative Adversarial Network

Yang

Min

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Medical activities recommendation is a key aspect of an intelligent healthcare system, which can assist doctors with little clinical experience in clinical decision making. Medical activities recommendation can be seen as a kind of temporal set prediction. Previous studies about them are based on Recurrent Neural Network (RNN), which does not incorporate personalized medical history or differentiate between the impact of medical activities. To address the above-given issues, this paper proposes a Next-Day Medical Activities Recommendation (NDMARec) model. Specifically, our model firstly proposes an inpatient day embedding method based on soft-attention which balances the impact of different medical activities to get a joint representation of medical activities that occurred within the same day. Then, a fusion module is designed to combine features of inpatient day and medical history to achieve personalization. These features are learned by the self-attention mechanism that solves the long-term dependency problem of RNNs. Last, adversarial training is introduced to improve the generalization ability of our model. Extensive experiments on a real dataset from a hospital are conducted to show that NDMARec outperformed both classical and state-of-the-art methods.

show abstract

Adversarial Learning for Personalized Tag Recommendation

Cited by 26 publications

References 66 publications

Method of Ideological and Political Teaching Resources in Universities Based on School-Enterprise Cooperation Mode

Method of Ideological and Political Teaching Resources in Universities Based on School-Enterprise Cooperation Mode

Pairwise Metric Learning With Angular Margin for Tag Recommendation

Next-Day Medical Activities Recommendation Model with Double Attention Mechanism Using Generative Adversarial Network

Contact Info

Product

Resources

About