Recently, numerous studies have integrated self-supervised contrastive learning with Graph Convolutional Networks (GCNs) to address the data sparsity and popularity bias to enhance recommendation performance. While such studies have made breakthroughs in accuracy metric, they often neglect non-accuracy objectives such as diversity, novelty and percentage of long-tail items, which greatly reduces the user experience in real-world applications. To this end, we propose a novel graph collaborative filtering model named Multi-Objective Graph Contrastive Learning for recommendation (MOGCL), designed to provide more comprehensive recommendations by considering multiple objectives. Specifically, MOGCL comprises three modules: a multi-objective embedding generation module, an embedding fusion module and a transfer learning module. In the multi-objective embedding generation module, we employ two GCN encoders with different goal orientations to generate node embeddings targeting accuracy and non-accuracy objectives, respectively. These embeddings are then effectively fused with complementary weights in the embedding fusion module. In the transfer learning module, we suggest an auxiliary self-supervised task to promote the maximization of the mutual information of the two sets of embeddings, so that the obtained final embeddings are more stable and comprehensive. The experimental results on three real-world datasets show that MOGCL achieves optimal trade-offs between multiple objectives comparing to the state-of-the-arts.

Despite advancements using graph neural networks (GNNs) to capture complex user-item interactions, challenges persist due to data sparsity and noise. To address these, self-supervised learning (SSL) methods, particularly recent generative approaches, have gained attention due to their ability to augment graph data without requiring complex view constructions and unstable negative sampling. However, existing generative SSL solutions often focus on structural rather than semantic (refer to collaborative signals in recommendation scenarios) reconstruction, limiting their potential as comprehensive recommender. This paper explores the untapped potential of generative SSL for graph-based recommender systems. We highlight two critical challenges: firstly, designing effective diffusion mechanisms to enhance semantic information and collaborative signals while avoiding optimization biases; and secondly, developing adaptive structural masking mechanisms within graph diffusion to improve overall model performance. Motivated by these challenges, we propose a novel approach: the Guided Diffusion enhanced Mask graph AutoEncoder (GDiffMAE). GDiffMAE integrates an adaptive mask encoder for structural reconstruction and a guided diffusion model for semantic reconstruction, addressing the limitations of current methods. Experimental results on diverse datasets demonstrate that GDiffMAE consistently outperforms powerful baseline models, particularly in handling noisy data scenarios. By enhancing both structural and semantic dimensions through guided diffusion, our model advances the state-of-the-art in graph-based recommender systems.

Recently, the multi-behavior information on a specific domain has been successfully exploited by aggregating diverse user behaviors to solve the problems of cold start and data sparsity in recommendations. However, the user behavior information captured from multiple behaviors in a single domain is insufficient. Our study seeks to enhance user behavior prediction by leveraging both multi-behavior information and cross-domain information in a more effective manner. In order to explore the correlations and differences between different behaviors and different domains, we propose a novel competition framework consists of intra-domain competition and inter-domain competition for knowledge learning. Specifically, for intra-domain, a behavior competition mechanism is designed to enable the model to mine users’ interests and behavior patterns effectively. For inter-domain, a domain competition mechanism is designed to perform knowledge transfer and knowledge fusion for overlapping users in different domains. Through the competition mechanisms, our proposedGraph Competitive Transfer Network (GCTN)achieves knowledge transfer between different domains and captures users’ behavior patterns in different contexts. The effectiveness of the GCTN and its competition mechanisms has been validated through sufficient experimental trials onDoubanandAmazondatasets. Compared to baseline methods, GCTN has demonstrated a marked improvement in both$AUC$and$F1$scores.

Community detection plays an important role in understanding complex networks. Many traditional embedding-based community detection methods only focus on the relations between nodes in the topology space (i.e., topology graph). Besides, there are also some works that consider the feature embedding of nodes to further improve the detection performance. However, most of them ignore the relationships between nodes in the feature space (i.e., feature graph). To address this issue, in this article, we construct the feature graph from the features of nodes to capture the relations between nodes in the feature space, and incorporate it with the topology graph and the feature embedding, leading to the novel feature graph augmented network representation for community detection (FGCD) method. Specifically, FGCD extracts the embeddings of topology graph, node features, and feature graph, respectively, and ensembles them by a layerwise fusion method with an attention mechanism. Extensive experiments on 11 real-world datasets show that FGCD outperforms most existing state-of-the-art algorithms, which well demonstrates its superiority.

In recent years, multi-behavior information has been utilized to address data sparsity and cold-start issues. The general multi-behavior models capture multiple behaviors of users to make the representation of relevant features more fine-grained and informative. However, most current multi-behavior recommendation methods neglect the exploration of social relations between users. Actually, users’ potential social connections are critical to assist them in filtering multifarious messages, which may be one key for models to tap deeper into users’ interests. Additionally, existing models usually focus on the positive behaviors (e.g., click , follow , and purchase ) of users and tend to ignore the value of negative behaviors (e.g., unfollow and badpost ). In this work, we present a Multi-Behavior Graph (MBG) construction method based on user behaviors and social relationships and then introduce a novel socially enhanced and behavior-aware graph neural network for behavior prediction. Specifically, we propose a Socially Enhanced Heterogeneous Graph Convolutional Network (SHGCN) model, which utilizes behavior heterogeneous graph convolution module and social graph convolution module to effectively incorporate behavior features and social information to achieve precise multi-behavior prediction. In addition, the aggregation pooling mechanism is suggested to integrate the outputs of different graph convolution layers, and a dynamic adaptive loss (DAL) method is presented to explore the weight of each behavior. The experimental results on the datasets of the e-commerce platforms (i.e., Epinions and Ciao) indicate the promising performance of SHGCN. Compared with the most powerful baseline, SHGCN achieves 3.3% and 1.4% uplift in terms of AUC on the Epinions and Ciao datasets. Further experiments, including model efficiency analysis, DAL mechanism, and ablation experiments, confirm the validity of the multi-behavior information and social enhancement.

With the popularity of social network, link prediction that aims to predict missing links in complex networks has attracted much attention. Among the existing link prediction methods, the method based on local information shows considerable competitiveness due to its simplicity and efficiency. However, the majority of local information based methods only perform the task by exploring low order neighbor information to make the prediction of new links, while the higher order information and community information are neglected. In this paper, we propose a community and local information preserved link prediction algorithm named CLLP for accurate link prediction in complex network. Specifically, we design a novel local similarity method based on probability propagation algorithm to get the local information of both low-order and high-order neighbor information, and propose a community information fusion strategy to integrate the community information into the suggested similarity method in order to obtain better prediction effect. Experimental results on real complex networks with different characteristics demonstrate the superiority of the proposed algorithm over several representative link prediction algorithms.