Cross‐media search method based on complementary attention and generative adversarial network for social networks

Shi, Lei; Du, Junping; Cheng, Gang; Liu, Xia; Xiong, Zenggang; Luo, Jia

doi:10.1002/int.22723

Cited by 20 publications

(8 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers have also combined deep learning with CCA in methods, such as deep CCA 11 . To realize cross‐media data and its continuous affiliation in social structures/networks, Shi et al 18 proposed an algorithm of complementary attention technique containing the unfocused as well as focused characteristics of images.…”

Section: Related Workmentioning

confidence: 99%

Cross‐modal retrieval based on deep regularized hashing constraints

Khan

Hayat

Wen

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Cross‐modal retrieval has attracted great attention due to the increasing demand for tremendous amounts of multimodal data in recent years. These retrievals could either be text‐to‐image or image‐to‐text. To address the problem of inappropriate information included between images and texts, we propose two cross‐modal recovery techniques established on a dual‐branch neural network defined on a common subspace and the hashing learning method. First, a cross‐modal recovery technique established on a multilabel information deep ranking model (MIDRM) is provided. In this method, we introduce a triplet‐loss function into the dual‐branch neural network model. This function takes advantage of the semantic information of the bimodal components, focusing on not only the similarities between similar images and text features but also the distances between dissimilar images and texts. Second, we establish a new cross‐modal hashing technique said to be the deep regularized hashing constraint (DRHC). In this method, the regularized function is used to replace the binary constraint, and the discrete value is constrained to a certain numerical range so that the network can achieve end‐to‐end training. Overall, the time complexity is greatly improved, and the occupied storage space is also greatly reduced. Different experiments on our proposed MIDRM and DRHC models demonstrate their superior performance to those of the state‐of‐the‐art methods on two widely used data sets. The experimental results show that our approach also increases the mean average precision of cross‐modal recovery.

show abstract

Section: Related Workmentioning

confidence: 99%

Cross‐modal retrieval based on deep regularized hashing constraints

Khan

Hayat

Wen

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…Social networks are widely used to model the interactions of users in many real-world applications [1][2][3]. Location-based social networks (LBSNs) are typical social networks that provide location-based services for users.…”

Section: Introductionmentioning

confidence: 99%

Muti-channel graph attention networks for POI recommendation

Jin

Huang

2023

IFS

View full text Add to dashboard Cite

This paper focuses on the task of Point-of-interest (POI) recommendation whose goal is to generate a list of POIs for a target user based on his or her history check-in records. Different from the traditional recommendation tasks (e.g., movie recommendation), there are many factors, like temporal factor and geographical factor, which make a great influence on user preference. Though existing POI recommendation methods tend to model the user preference from temporal factor, geographical factor or social factor, they fail to model these factors into a jointly model, leading to learn the suboptimal user preference. To tackle this issue, we propose a Muti-channel Graph Attention Network (MGAN) for POI recommendation which learns the user preference from multiple aspects in a unify model. Specifically, MGAN first constructs several graphs with corresponding contextual features to capture the user preference from temporal, geographical, semantic and social aspects. Then MGAN leverages the graph attention networks to learn the representations of POIs from these graphs. Finally, MGAN estimates the user preference from the history check-in records and other similar users via the learned POI representations. We conduct extensive experiments on real-world datasets. And the results indicate that our proposed MGAN outperforms mainstream POI recommendation methods.

show abstract

“…This challenge mainly consists of two aspects: data sparsity and complex context. First, data sparsity: in the scenario of POI recommendation, the cost of generating an activity record is relatively high, resulting in fewer check-in records for most users, i.e., serious data sparsity problems will be faced during modeling; second, complex context: a checkin decision of a user is affected not only by the temporal context but also by the geographical context, which also means that the decision of a user is affected by multiple contexts, that is, a user's preference [2,3] will vary with the context. How to accurately capture a user's preference in a complex context is another challenge in the field of POI recommendation.…”

Section: Introductionmentioning

confidence: 99%

“…(1) We construct two novel graphs for capture user preferences in complex context (2) We propose an enhanced neighborhood aggregation function for precisely representing the user preferences…”

Section: Introductionmentioning

confidence: 99%

Point-of-Interest Recommendation Model Based on Graph Convolutional Neural Network

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the development of location-based social networks, the point-of-interest recommendation has become one of the research hotspots in the field of recommendation. However, traditional technologies like collaborative filtering are limited by the influence of data sparsity and cannot accurately capture the users’ preferences from the complex context. In order to address this problem, a recommendation model based on graph convolutional neural network is proposed, named RMGCN. RMGCN is composed of three parts: graph structure features extraction module, geographical factor evaluation module, and score calculation module. The graph structure feature extraction module is used to extract node features from the graph structure data composed of user check-in records. The geographical factor evaluation module is used to calculate the influence coefficient of geographical factors on user’s decision-making behaviors. The score calculation module is used to combine the output results of the above two modules and calculate the user’s preference scores of point-of-interests combined with temporal context and spatial context. Experimental results on two real-world datasets show that RMGCN has better recommendation performance than baselines.

show abstract

Cross‐media search method based on complementary attention and generative adversarial network for social networks

Cited by 20 publications

References 45 publications

Cross‐modal retrieval based on deep regularized hashing constraints

Cross‐modal retrieval based on deep regularized hashing constraints

Muti-channel graph attention networks for POI recommendation

Point-of-Interest Recommendation Model Based on Graph Convolutional Neural Network

Contact Info

Product

Resources

About