Social recommendation algorithms based on Graph Neural Network (GNN) leverage social networks to improve recommendation performance. However, most existing methods directly integrate the raw social graph into the recommendation system, which often introduces noise as they overlook the presence of non-homophilous social connections. Furthermore, prevailing negative sampling strategies typically select negative samples with a fixed level of hardness, which is prone to generating false negatives and consequently limits the model’s ability to effectively discriminate between user preferences. To address these issues, this paper proposed a novel recommendation algorithm based on social diffusion and adaptive negative sampling. First, forward diffusion and interest-guided denoising were performed on the social network to derive user representations that reflect homophilic social relations. Subsequently, a multi-view representation alignment approach was employed to maximize the mutual information among user representations from the denoised social graph, the original social graph, and the user-item interaction graph, thereby enhancing the quality of user embeddings. Finally, negative samples of adaptive hardness were selected based on the predicted scores of positive samples, enabling dynamic calibration of the similarity boundary between positive and negative pairs to improve overall model performance. Extensive experimental results demonstrate that the proposed algorithm significantly outperforms state-of-the-art recommendation baselines. On the Douban dataset, it improves recall and NDCG by 11.99% and 10.54%, respectively; on Epinions, by 15.62% and 11.14%; and on Yelp, by 13.80% and 14.90%. These results validate its effectiveness in alleviating social noise and enhancing the differentiation between positive and negative samples.

Previous session-based recommendation systems usually capture users’ consumption preferences from their recent transaction records, and this method ignores the influence of global transaction information and friends’ preferences on users’ transaction behavior, resulting in less accurate recommendation results of the model. To solve the problem, this paper proposed a social recommendation model AFGSRec based on an adaptive fusion of global collaborative features. Firstly, a heterogeneous graph neural network was used to model users and their historical transaction information on the social network for capturing global collaborative features and social influence among friends. Secondly, this paper designed a graph neural network based on a selection mechanism that effectively filters out the node transition features irrelevant to the current session and captures user preferences more accurately. Thirdly, an adaptive fusion method was designed to capture the impact of global collaborative features on users’ current preferences dynamically and improve the model’s recommendation accuracy. Finally, this paper used a dynamic cyclical learning rate to help the model better handle saddle points during the training process to improve the convergence speed of model AFGSRec. The experimental results show that AFGSRec is robust; both the HR (Hit Rate) and MRR (Mean Reciprocal Rank) of AFGSRec outperform the state-of-art model SERec. On the Gowalla dataset, HR@10 and HR@20 are increased by 1.91% and 1.15%, respectively; MRR@10 and MRR@20 are increased by 5.05% and 4.83%, respectively. On the Delicious dataset, HR@10 and HR@20 are increased by 2.45% and 1.19%, respectively; MRR@10 and MRR@20 are increased by 4.84% and 4.32%, respectively.

The social recommendation model based on graph neural network has achieved good performance in improving the performance of the recommendation system. However, the existing methods ignored the possible feature mismatch between the queried target users and content nodes and their neighbors, which leads to the introduction of noise and reduces the model performance. To solve this problem, this paper proposed a social recommendation model DNSSR. Firstly, it constructed a relational graph containing multiple relationships between users and items, with richer information associations between nodes in the graph. Then the dynamic neighborhood sampling mechanism was used to obtain neighbor nodes that are more consistent with the characteristics of the target query pair, reducing noise information. In addition, in order to further improve the predictive performance of the model, this paper designed an enhanced graph neural network to model the sampled relationship subgraphs. It can distinguish the importance of different neighboring nodes and select more reliable information sources to obtain more robust user and item embedding vectors for rating prediction. The experimental results show that the prediction error of this model is significantly reduced compared to that of other advanced models, proving the effectiveness of the methods proposed in the paper. Especially for the dynamic neighborhood sampling mechanism, if it is abandoned, the RMSE and MAE indicators of DNSSR on the Ciao dataset will increase by 6.05% and 7.31% respectively, and the Epinions dataset will increase by 3.49% and 5.41% respectively, which fully demonstrate their effectiveness in reducing noise interference and improving the performance of social recommendation models.

Current unsupervised contrastive learning methods mainly rely on pure textual information to construct sentence embeddings, which presents limitations in comprehensively understanding the deeper meanings conveyed by sentences. Meanwhile, traditional contrastive learning methods focus excessively on maximizing the mutual information between positive instances of text, overlooking the potential noise interference within sentence embeddings. To effectively retain useful information in the text while eliminating noise interference in the embeddings, the paper proposed a contrastive learning model based on text-vision and information entropy minimization. Firstly, the text and the corresponding visual information are deeply fused under the framework of contrastive learning, and jointly mapped to a unified grounding space, ensuring their representations remain consistent within this space. This approach overcomes the limitations of relying solely on pure textual information for sentence embedding learning, making the contrastive learning process more comprehensive and precise. Secondly, following the principle of information minimization, the model reconstructs positive text instances based on information entropy minimization while maximizing mutual information between positive text instances. Experimental results on the standard semantic textual similarity (STS) task demonstrate that the proposed model achieves significant improvements in the Spearman correlation coefficient evaluation metric, showcasing a notable advantage over existing state-of-the-art methods. This also confirms the effectiveness of the proposed model.