arXiv subjects

Haipeng Yang

Publications and source records attributed to Haipeng Yang.

4 recordsLinked to original sources

arXiv2026

Robust Contrastive Graph Clustering with Adaptive Local-Global Integration

Graph clustering is essential in graph analysis for revealing structural patterns and node communities. Despite recent advances in self-supervised contrastive learning that have improved clustering via structural and attribute signals, existing methods still struggle to flexibly capture high-order local structures and often overlook global semantics in complex graphs. These limitations lead to suboptimal node representations, especially in real-world graphs with fragmented structures and ambiguous cluster boundaries. To address these limitations, a contrastive graph clustering framework is proposed to jointly integrate multi-scale local structures with global semantics via attention mechanisms. At the local level, GNN-based topological signals extracted from multiple propagation depths are adaptively fused through attention-based weighting to capture multi-scale neighborhood features. At the global level, semantic prototypes derived from dynamically evolving cluster centers are adaptively aggregated through attention to guide node representations and enhance inter-cluster separability. The model is trained under a dual-view contrastive learning paradigm with a hybrid objective that combines instance-level and structure-aware losses to improve representation robustness and discrimination. Experiments on eight real-world graph datasets demonstrate that our method achieves competitive clustering performance. Code is available at https://github.com/vege12138/w2.

cs.LG↗

arXiv2026

GCIB: Graph Contrastive Information Bottleneck for Multi-Behavior Recommendation

With the rapid emergence of multi-behavior learning in recommender systems, leveraging auxiliary user behaviors has proven effective for mitigating target-behavior data sparsity. Yet auxiliary behavior graphs frequently contain noisy or irrelevant interactions that do not align with the target task, impeding the learning of accurate user and item embeddings. Moreover, the scarcity of direct supervision from the target behavior complicates the extraction of informative collaborative signals. In this paper, we introduce GCIB (Graph Contrastive Information Bottleneck), a novel framework that denoises auxiliary behavior information and enriches target behavior representations at both the structural and feature levels. At the structural level, GCIB employs a Graph Information Bottleneck (GIB) objective to maximize mutual information between the denoised auxiliary graph and the target-behavior graph while minimizing mutual information with the original auxiliary graph. This formulation preserves task-relevant structural patterns and suppresses spurious interactions. At the feature level, we propose a cross-behavior Graph Contrastive Learning (GCL) scheme in which denoised auxiliary features and target-behavior features serve as complementary views for both users and items. By contrasting these views, GCIB enriches sparse target-behavior representations with semantics distilled from auxiliary behaviors. Extensive experiments demonstrate that GCIB outperforms state-of-the-art baselines, highlighting its ability to learn noise-resilient and target-aware representations for multi-behavior recommendation.

cs.IR↗

arXiv2023

Fair Influence Maximization in Social Networks: A Community-Based Evolutionary Algorithm

Influence Maximization (IM) has been extensively studied in network science, which attempts to find a subset of users to maximize the influence spread. A new variant of IM, Fair Influence Maximization (FIM), which primarily enhances the fair propagation of information, attracts increasing attention in academic. However, existing algorithms for FIM suffer from a trade-off between fairness and running time. Since it is a tough task to ensure that users are fairly influenced in terms of sensitive attributes, such as race or gender, while maintaining a high influence spread. To tackle this problem, in this paper, we propose an effective and efficient Community-based Evolutionary Algorithm for FIM (named CEA-FIM). In CEA-FIM, a community-based node selection strategy is proposed to identify potential nodes, which not only considers the size of the community but also the attributes of the nodes in the community. Subsequently, we design an evolutionary algorithm based on the proposed node selection strategy to hasten the search for the optimal solution, including the novel initialization, crossover and mutation strategies. We validate the proposed algorithm CEA-FIM by performing experiments on real-world and synthetic networks. The experimental results show that the proposed CEA-FIM achieves a better balance between effectiveness and efficiency, compared to the state-of-the-art baseline algorithms.

cs.SI↗

arXiv2023

Temperature dependent anisotropy and two-band superconductivity revealed by lower critical field in organic superconductor $\kappa$-(BEDT-TTF)$_{2}$Cu[N(CN)$_{2}$]Br

Resistivity and magnetization have been measured at different temperatures and magnetic fields in organic superconductors $\kappa$-(BEDT-TTF)$_{2}$Cu[N(CN)$_{2}$]Br. The lower critical field and upper critical field are determined, which allow to depict a complete phase diagram. Through the comparison between the upper critical fields with magnetic field perpendicular and parallel to the conducting ac-planes, and the scaling of the in-plane resistivity with field along different directions, we found that the anisotropy $\Gamma$ is strongly temperature dependent. It is found that $\Gamma$ is quite large (above 20) near $T_{c}$, which satisfies the 2D model, but approaches a small value in the low-temperature region. The 2D-Tinkham model can also be used to fit the data at high temperatures. This is explained as a crossover from the orbital depairing mechanism in high-temperature and low-field region to the paramagnetic depairing mechanism in the high-field and low-temperature region. The temperature dependence of lower critical field $H_{c1} (T)$ shows a concave shape in wide temperature region. It is found that neither a single $d$-wave nor a single $s$-wave gap can fit the $H_{c1} (T)$, however a two-gap model containing an $s$-wave and a $d$-wave can fit the data rather well, suggesting two-band superconductivity and an unconventional pairing mechanism in this organic superconductor.

cond-mat.supr-con↗