Search

Graph Collaborative Filtering (GraphCF) has emerged as a promising approach in recommendation systems, leveraging the inferential power of Graph Neural Networks. Furthermore, the integration of contrastive learning has enhanced the performance of GraphCF methods. Recent research has shifted from graph augmentation to noise perturbation in contrastive learning, leading to significant performance improvements. However, we contend that the primary factor in performance enhancement is not graph augmentation or noise perturbation, but rather the balance of the embedding from each layer in the output embedding. To substantiate our claim, we conducted preliminary experiments with multiple state-of-the-art GraphCF methods. Based on our observations and insights, we propose a novel approach named Unraveled Graph Contrastive Learning (UGCL), which includes a new propagation scheme to further enhance performance. To the best of our knowledge, this is the first approach that specifically addresses the balance factor in the output embedding for performance improvement. We have carried out extensive experiments on multiple large-scale benchmark datasets to evaluate the effectiveness of our proposed approach. The results indicate that UGCL significantly outperforms all other state-of-the-art baseline models, also showing superior performance in terms of fairness and debiasing capabilities compared to other baselines. [ABSTRACT FROM AUTHOR]

Graph collaborative filtering uses user-item interactions to capture user preferences for items. While this approach proves highly effective, its performance may suffer from the sparse user-item interactions. On one hand, existing methods lack consideration about the effective incorporation of multi-hop neighbors’ information and can be sensitive to noise. On the other hand, acquiring information from distant neighbors often necessitates stacking multiple layers of graph neural networks, which may lead to over-smoothing problems. To overcome the limitations, we propose a novel Second-order Neighbor Enhanced Graph Convolutional Network (SNE–GCN), which involves both first-order and second-order neighbor information. Specifically, we first design a second-order neighbor-based module, which includes the second-order neighbor selection and the second-order neighbor information propagation based on attention mechanisms. The second-order information is then aggregated with the first-order ones via a proposed information aggregation module. SNE–GCN can serve as a universal framework for improving recommendation performance based on GCN models. Extensive experiments on five public data sets show the effectiveness and potential of SNE–GCN in recommendation systems. The most remarkable improvements are observed on the Amazon-book data set, which is notably large and sparse, and the Recall and NDCG metrics were boosted by 23.59% and 27.43%, respectively. [ABSTRACT FROM AUTHOR]

A D2D cooperative caching strategy based on graph collaborative filtering model was proposed for the problem of difficulty in obtaining sufficient data to predict user preferences in device-to-device (D2D) caching due to the limited signal coverage of base stations.Firstly, a graph collaborative filtering model was constructed, which captured the higher-order connectivity information in the user-content interaction graph through a multilayer graph convolutional neural network, and a multilayer perceptron was used to learn the nonlinear relationship between users and content to predict user preferences.Secondly, in order to minimize the average access delay, considering user preference and cache delay benefit, the cache content placement problem was modeled as a Markov decision process model, and a cooperative cache algorithm based on deep reinforcement learning was designed to solve it.Simulation experiments show that the proposed caching strategy achieves optimal performance compared with existing caching strategies for different content types, user densities, and D2D communication distance parameters.

Multiple studies have demonstrated that microRNA (miRNA) can be deeply involved in the regulatory mechanism of human microbiota, thereby inducing disease. Developing effective methods to infer potential associations between microRNAs (miRNAs) and diseases can aid early diagnosis and treatment. Recent methods utilize machine learning or deep learning to predict miRNA-disease associations (MDAs), achieving state-of-the-art performance. However, the problem of sparse neighborhoods of nodes due to lack of data has not been well solved. To this end, we propose a new model named MTCL-MDA, which integrates multiple-types of contrastive learning strategies into a graph collaborative filtering model to predict potential MDAs. The model adopts a contrastive learning strategy based on topology, which alleviates the damage to model performance caused by sparse neighborhoods. In addition, the model also adopts a semantic-based contrastive learning strategy, which not only reduces the impact of noise introduced by topology-based contrastive learning, but also enhances the semantic information of nodes. Experimental results show that our model outperforms existing models on all evaluation metrics. Case analysis shows that our model can more accurately identify potential MDA, which is of great significance for the screening and diagnosis of real-life diseases. Our data and code are publicly available at: https://github.com/Lqingquan/MTCL-MDA.

Recommendation systems for TV programs play an important role in alleviating the information overload problem. Existing TV program recommendation methods either do not aggregate neighborhood information well to capture collaborative signals from interaction data, or fail to make good use of auxiliary information, because they ignore the heterogeneity of different entities and relationships. In this paper, we propose a multi-component graph collaborative filtering recommendation based on auxiliary information, which learns representations of user and program through heterogeneous data modeling and information propagation on graphs. We extract homogeneous subgraphs from the heterogeneous graph based on multiple symmetric meta-paths, learn the components of the node representation by performing graph convolution on the homogeneous subgraphs, and finally combine the components to obtain the complete user representation and program representation. Experiments on real-world datasets show that our approach can effectively improve the performance of TV program recommendations compared to the existing baselines. [ABSTRACT FROM AUTHOR]

Graph Collaborative Filtering (GCF) methods have emerged as an effective recommendation approach, capturing users' preferences over items by modeling user–item interaction graphs. However, these methods suffer from data sparsity in real scenarios, and their performance can be improved using contrastive learning. In this paper, we propose an optimized method, named LoRA-NCL, for GCF based on Neighborhood-enriched Contrastive Learning (NCL) and low-rank dimensionality reduction. We incorporate low-rank features obtained through matrix factorization into the NCL framework and employ LightGCN to extract high-dimensional representations. Extensive experiments on five public datasets demonstrate that the proposed method outperforms a competitive graph collaborative filtering base model, achieving 4.6% performance gains on the MovieLens dataset, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Journal on Communication / Tongxin Xuebao is the property of Journal on Communications Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In tag-aware recommender systems, users are strongly encouraged to utilize arbitrary tags to mark items of interest. These user-defined tags can be viewed as a bridge linking users and items. Most tag-aware recommendation models focus on improving the accuracy by introducing ingenious design or complicated structures to handle the tagging information appropriately. Beyond accuracy, diversity is considered to be another important indicator affecting the user satisfaction. Recommending more diverse items will provide more interesting items and commercial sales. Therefore, we propose a diversified tag-aware recommendation model based on graph collaborative filtering. The proposed model establishes a generic graph collaborative filtering framework tailored for tag-aware recommendations. To promote diversity, we adopt two modules: personalized category-boosted negative sampling to select a certain proportion of similar but negative items as negative samples for training, and adversarial learning to make the learned item representation category-free. To improve accuracy, we conduct a two-way TransTag regularization to model the relationship among users, items, and tags. Blending these modules into the proposed framework, we can optimize both the accuracy and diversity concurrently in an end-to-end manner. Experiments on Movielens datasets show that the proposed model can provide diverse recommendations while maintaining a high level of accuracy. [ABSTRACT FROM AUTHOR]

Graph Collaborative Filtering (GCF) methods have emerged as an effective recommendation approach, capturing users’ preferences over items by modeling user–item interaction graphs. However, these methods suffer from data sparsity in real scenarios, and their performance can be improved using contrastive learning. In this paper, we propose an optimized method, named LoRA-NCL, for GCF based on Neighborhood-enriched Contrastive Learning (NCL) and low-rank dimensionality reduction. We incorporate low-rank features obtained through matrix factorization into the NCL framework and employ LightGCN to extract high-dimensional representations. Extensive experiments on five public datasets demonstrate that the proposed method outperforms a competitive graph collaborative filtering base model, achieving 4.6% performance gains on the MovieLens dataset, respectively.

Collaborative filtering approach greatly promotes the development and application of personalized recommendation. In location-based social networks (LBSNs), the sparsity of check-in data is one of the main obstacles for traditional Point-of-Interest (POI) recommendation models. Graph convolutional network (GCN) is an efficient tool to overcome this kind of problems, which enhances the representational ability of embeddings by capture high-order connectivity of users and POIs. In real applications, social tie is a crucial factor for POI recommendation that ignored in most current graph-based methods. Moreover, most message aggregation functions fail to capture contextual information. To address these problems, a novel framework named Friends-aware Graph Collaborative Filtering (FG-CF) is proposed in this paper, which incorporates social information into a user-POI graph. Firstly, a user-POI correlation matrix is estimated by check-in data and social links, and then, user embedding is updated according to the user-POI correlation matrix. Secondly, interaction messages are constructed in a novel way by integrating nodes' ego embeddings, neighbors' embeddings and social embeddings. Thirdly, by aggregating previous state embeddings and non-linear combination of neighbor messages with interaction messages, a new message aggregation function is present to update user and POI embeddings. Fourthly, we concatenate embeddings from each additional interaction layer to get the final embeddings, and inner product is used to compute the preference score of a user to a targeted POI. Finally, extensive experiments on two large-scale LBSN datasets demonstrate the superiority of our model over several state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In tag-aware recommender systems, users are strongly encouraged to utilize arbitrary tags to mark items of interest. These user-defined tags can be viewed as a bridge linking users and items. Most tag-aware recommendation models focus on improving the accuracy by introducing ingenious design or complicated structures to handle the tagging information appropriately. Beyond accuracy, diversity is considered to be another important indicator affecting the user satisfaction. Recommending more diverse items will provide more interesting items and commercial sales. Therefore, we propose a diversified tag-aware recommendation model based on graph collaborative filtering. The proposed model establishes a generic graph collaborative filtering framework tailored for tag-aware recommendations. To promote diversity, we adopt two modules: personalized category-boosted negative sampling to select a certain proportion of similar but negative items as negative samples for training, and adversarial learning to make the learned item representation category-free. To improve accuracy, we conduct a two-way TransTag regularization to model the relationship among users, items, and tags. Blending these modules into the proposed framework, we can optimize both the accuracy and diversity concurrently in an end-to-end manner. Experiments on Movielens datasets show that the proposed model can provide diverse recommendations while maintaining a high level of accuracy.

Multiple studies have demonstrated that microRNA (miRNA) can be deeply involved in the regulatory mechanism of human microbiota, thereby inducing disease. Developing effective methods to infer potential associations between microRNAs (miRNAs) and diseases can aid early diagnosis and treatment. Recent methods utilize machine learning or deep learning to predict miRNA-disease associations (MDAs), achieving state-of-the-art performance. However, the problem of sparse neighborhoods of nodes due to lack of data has not been well solved. To this end, we propose a new model named MTCL-MDA, which integrates multiple-types of contrastive learning strategies into a graph collaborative filtering model to predict potential MDAs. The model adopts a contrastive learning strategy based on topology, which alleviates the damage to model performance caused by sparse neighborhoods. In addition, the model also adopts a semantic-based contrastive learning strategy, which not only reduces the impact of noise introduced by topology-based contrastive learning, but also enhances the semantic information of nodes. Experimental results show that our model outperforms existing models on all evaluation metrics. Case analysis shows that our model can more accurately identify potential MDA, which is of great significance for the screening and diagnosis of real-life diseases. Our data and code are publicly available at: https://github.com/Lqingquan/MTCL-MDA., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Liao, Fu, Zhuo and Chen.)