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.