Graph contrastive learning (GCL) has shown excellent performance in recommender systems. However, GCL-based methods have two major problems. First, many methods use graph perturbations to create the contrastive view, this operation may compromise the structure of the original graph. Second, some algorithms pursue the uniformity of features, but neglect the alignment, which may lead to the features of similar samples in the feature space distancing from each other, thereby reducing the model’s ability to distinguish similar samples. To address these problems, we propose the SiamGCL framework, which consists of two modules: multilevel alignment (MLA) and enhanced uniformity (EU). MLA uses the siamese network structure to process user and item data in parallel and achieves model-level alignment through shared structure and parameters. In addition, we introduce alignment loss in the optimization process to further refine the alignment of user and item embeddings. EU employs noise modulated augmentation and batch normalization regulator as alternatives to traditional graph perturbation methods. This embedding perturbation strategy effectively prevents over-aggregation in the feature space, which can also enhance the uniformity of the embedding distribution. Experiments on five large-scale benchmark datasets show that SiamGCL improves Recall@20 and NDCG@20 by 0.97%–5.51% and 1.31%–2.73%, respectively, compared with the current state-of-the-art method.
Debiased recommendation focuses on alleviating the negative impact of various biases on recommendation quality to achieve fairer personalized recommendations. Current research mainly relies on propensity score estimation or causal inference methods to alleviate selection bias; at the same time, research on prevalence bias has proposed a variety of methods based on causal graphs and contrastive learning. However, these methods have shortcomings in dealing with unstable propensity score estimates, bias interactions, and decoupling of interest and bias signals, which limits the performance improvement of recommender systems. To this end, this paper proposes APWCF, a collaborative filtering debiased method that combines dynamic propensity modeling and adversarial learning. APWCF solves the problem of high variance in propensity scores through the dynamic propensity factor, and decouples user interests and bias signals through the adversarial learning to effectively remove multiple biases. Experiments show that APWCF significantly outperforms existing methods across various benchmark datasets from different domains. Compared with the current optimal baseline PDA, Recall@10 and NDCG@10 improve by 0.10%-5.42% and 1.01%-8.60% respectively.
20 May 2026 in ACM Transactions on Knowledge Discovery From Data
Recommender systems are effective tools to alleviate the challenges posed by information overload, but data sparsity has greatly affected their performance. Knowledge Graphs (KGs) and self-supervised learning are used to alleviate the data sparsity problem. However, existing KG-enhanced self-supervised learning recommendation methods have the following limitations: (1) Generality : existing CL-based recommendation methods strongly rely on manually designed data augmentation strategies, leading to poor generality of the CL-based models. (2) Robustness : KG usually contains lots of task-irrelevant entities, and the user–item interactions constructed from implicit feedback are usually noisy. The noisy data will generate intrusive supervised and self-supervised signals and will degrade recommendation performance. To address these limitations, we propose a novel KG-enhanced self-supervised learning recommendation method, named Knowledge-Variational Contrastive Learning for Recommendation (KVCL) . Specifically, we first design an adaptively denoising mechanism to identify and prune the noisy data in the KG and user–item interaction bipartite graph. Then, we learn a normal distribution for each node by the variational auto-encoder, and sample multiple times from the learned distribution to obtain different contrastive views. Extensive experiments based on three public datasets show that KVCL achieves improved performance over state-of-the-art methods, notably with 3.13% performance gain over state-of-the-art methods on Recall@20 and NDCG@20. Furthermore, evaluations including ablation studies and detailed analyses of multi-scenarios, computational efficiency, complexity, and denoising interpretability further underscore its scalability and practical applicability.