Community search is a fundamental graph-based retrieval problem that aims to identify a query-dependent subgraph whose nodes exhibit strong internal connectivity. While recent learning-based methods improve retrieval effectiveness via graph representation learning, they follow a ''one-use-one-train'' paradigm that requires retraining or fine-tuning for each target graph, leading to high data dependency, high training costs, and limited generalization. To handle this, we propose OFA-CS, a ''one-for-all'' community search framework trained once on source datasets and directly deployed to arbitrary unseen graphs without retraining or fine-tuning, while preserving strong performance. Specifically, we introduce a Spectral-Aware Feature Alignment module to unify feature dimensionality and align cross-domain semantics in a community-aware manner. We further develop a Graph Diffusion Tokenized Transformer that constructs hybrid token sequences from local and global structural contexts for Transformer encoding, and applies diffusion-based refinement to mitigate distribution shifts on unseen graphs. With the unified representations, communities are efficiently retrieved via a modularity-driven search procedure. Extensive experiments on diverse real-world graphs demonstrate that OFA-CS achieves strong cross-domain generalization and competitive retrieval effectiveness against state-of-the-art methods, without requiring target-domain supervision.

Entity alignment (EA) aims to identify equivalent entities across different knowledge graphs (KGs). While existing approaches leverage KG neighborhood structures for alignment, they often fail to effectively distinguish relevant from irrelevant neighbors due to insufficient handling of neighbor heterogeneity. Additionally, entity enhancement strategies remain underutilized. To address these issues, we propose a novel Relationship Structure Line Graph for Semi-supervised Entity Alignment Based on Edge Weight Adjustment, named RSGEA. It first enhances entity representations by deeply analyzing relational connectivity structures in KGs, capturing key relational information from second-order and triangular-ring structures. It then employs an attention mechanism to dynamically adjust edge weights, mitigating the impact of noisy edges during information propagation. Finally, we employ the Sinkhorn algorithm to refine the similarity matrix, improving alignment accuracy. Furthermore, we introduce an unsupervised version to accommodate diverse scenarios. Extensive experiments on five cross-lingual datasets validate the effectiveness and robustness of the RSGEA, demonstrating significant performance improvements.

At present, event-based social network (EBSN) platforms are becoming more and more popular, which main function is to arrange appropriate social activities for interested users. The existing methods usually assume that each user can participate in a limited number of events and solve the spatio-temporal conflicts caused by the limited number of events. However, in practical applications, the existing methods emerge the following problems: (1) they don't estimate the time cost caused by travel distance; (2) the constraint of the limiting number of users participating events and the schedule of users is not accurate enough. Therefore, first, we combine the position information and propose RDP algorithm to provide personalized event planning based on considering the free time of users, the average moving speed of users, the interest value of users as a whole, which ensures the approximate ratio of our algorithm. Second, we present RGPV and the RGPT algorithms to reduce the running time and improve the efficiency of time and space, so as to ensure each user can participate in the events on time. Finally, the experiments based on the real dataset can show that the proposed algorithms are effective and efficient.