Graph self-supervised learning (GSSL) alleviates the graph data labeling bottleneck without supervision, enabling wide application in domains like recommendation systems and social network analysis. High-frequency signals are valuable in GSSL for capturing local structural preferences, thereby enriching graph representations and boosting model performance. However, in practical applications, two critical problems hinder the efficient and robust use of these signals. First, the locality of high-frequency signals limits their full utilization by the model. Second, over-reliance on specific high-frequency signals will affect the model's generalization. To address the above problems, we propose the Frequency-Corrupt Based Graph Self-Supervised Learning (FC-GSSL) algorithm. Specifically, we generate corrupted graphs biased toward high-frequency signals by corrupting nodes and edges according to their low-frequency contributions. These corrupted graphs are fed as input to an autoencoder, with low-frequency and general features serving as the supervision. This compels the model to effectively fuse high- and low-frequency signals, thereby integrating and utilizing more valuable high-frequency information. Additionally, we design multiple sampling strategies and form diverse corrupted graphs based on the intersections and union between the results obtained from these strategies. By aligning the node representations from these views, the model can identify valuable frequency combinations, which helps reduce the negative impact of specific high-frequency components and improve generalization. FC-GSSL optimizes the design of GSSL for web applications, significantly improving model performance on complex web-related graphs, such as social networks and citation networks. This work makes a direct contribution to advancing the ''Graph Algorithms and Modeling for the Web'' research track. Experimental results on 14 datasets across multiple tasks illustrate the superiority of the proposed approach.

Disentanglement techniques used in collaborative filtering uncover interaction intents between nodes, improving the interpretability of node representations and enhancing recommendation performance. However, existing disentanglement methods still face the following two problems. 1) They focus on local structural features derived from direct node interactions, overlooking the comprehensive graph structure, which limits disentanglement accuracy. 2) The disentanglement process depends on backpropagation signals derived from recommendation tasks, lacking direct supervision, which may lead to biases and overfitting. To address the issues, we propose theIntentPropagationContrastiveCollaborativeFiltering (IPCCF) algorithm. Specifically, we design a double helix message propagation framework to more effectively extract the deep semantic information of nodes, thereby improving the model's understanding of interactions between nodes. An intent message propagation method is also developed that incorporates graph structure information into the disentanglement process, thereby expanding the consideration scope of disentanglement. In addition, contrastive learning techniques are employed to align node representations derived from the structure and intents, providing direct supervision for the disentanglement process, mitigating biases, and enhancing the model's robustness to overfitting. The experiments on three real data graphs illustrate the superiority of the proposed approach.

Multi-behavior recommendation systems enhance effectiveness by leveraging auxiliary behaviors (such as page views and favorites) to address the limitations of traditional models that depend solely on sparse target behaviors like purchases. Existing approaches to multi-behavior recommendations typically follow one of two strategies: some derive initial node representations from individual behavior subgraphs before integrating them for a comprehensive profile, while others interpret multi-behavior data as a heterogeneous graph, applying graph neural networks to achieve a unified node representation. However, these methods do not adequately explore the intricate patterns of behavior among users and items. To bridge this gap, we introduce a novel algorithm called Behavior Pattern mining-based Multi-behavior Recommendation (BPMR). Our method extensively investigates the diverse interaction patterns between users and items, utilizing these patterns as features for making recommendations. We employ a Bayesian approach to streamline the recommendation process, effectively circumventing the challenges posed by graph neural network algorithms, such as the inability to accurately capture user preferences due to over-smoothing. Our experimental evaluation on three realworld datasets demonstrates that BPMR significantly outperforms existing state-of-the-art algorithms, showing an average improvement of 268.29% in Recall@10 and 248.02% in NDCG@10 metrics. The code of our BPMR is openly accessible for use and further research at https://github.com/rookitkitlee/BPMR.

Bipartite graph representation learning embeds users and items into a low-dimensional latent space based on observed interactions. Previous studies mainly fall into two categories: one reconstructs the structural relations of the graph through the representations of nodes, while the other aggregates neighboring node information using graph neural networks. However, existing methods only explore the local structural information of nodes during the learning process. This makes it difficult to represent the macroscopic structural information and leaves it easily affected by data sparsity and noise. To address this issue, we propose the Intent Distribution based Bipartite graph Representation learning (IDBR) model, which explicitly integrates node intent distribution information into the representation learning process. Specifically, we obtain node intent distributions through clustering and design an intent distribution based graph convolution neural network to generate node representations. Compared to traditional methods, we expand the scope of node representations, enabling us to obtain more comprehensive representations of global intent. When constructing the intent distributions, we effectively alleviated the issues of data sparsity and noise. Additionally, we enrich the representations of nodes by integrating potential neighboring nodes from both structural and semantic dimensions. Experiments on the link prediction and recommendation tasks illustrate that the proposed approach outperforms existing state-of-the-art methods. The code of IDBR is available at https://github.com/rookitkitlee/IDBR.

Disentangled collaborative filtering can explicitly generate embeddings based on users’ interests and help improve the interpretability and robustness of recommendations. However, the existing disentangled graph collaborative filtering methods rely solely on direct interaction constraints between nodes to learn node embeddings, which cannot represent higher-order constraints between nodes and node-type differences, resulting in suboptimal node representations and negatively affecting recommendation performance. To address this problem, we propose a Multi-order Similarity Constraint Disentangled Graph Collaborative Filtering (DGCF-MSC) method, which considers not only direct interaction constraints between nodes but also designs a neighborhood enhancement mechanism based on high-order relationships between homogeneous nodes. We realize the disentanglement of heterogeneous type nodes in different feature spaces in a graph convolutional neural network to make the generated embedding more interpretable and improve the performance of graph collaborative filtering. We conduct extensive experiments with three recommendation system datasets and the results demonstrate that DGCF-MSC outperforms the existing disentangled graph collaborative filtering methods in all performance metrics. Our code is released on https://github.com/lustrelake/DGCF_MSC.

Ensemble learning is an effective approach for improving the generalization ability of base classifiers. To generate a set of accurate and diverse base classifiers, different data perturbation schemes have been proposed. For instance, Bagging perturbs the training data via bootstrap sampling. However, when a stable learning algorithm (e.g., KNN, Naive Bayes) is used to train base classifiers, the sole perturbation on the training data may not produce diverse base classifiers. In this paper, by using the attribute reduction technology in rough sets, a multi-modal perturbation-based algorithm (called ‘E _ EARBS’) is proposed for the ensemble of base classifiers. E _ EARBS simultaneously perturbs the feature space, training data and learning parameters, where the relative decision entropy(RDE)-based approximate reducts are used to perturb the feature space, and bootstrap sampling is used to perturb the training data. Experimental results show that E _ EARBS can provide competitive solutions for ensemble learning.