English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Community Search (CS), a crucial task in network science, has attractedconsiderable interest owing to its prowess in unveiling personalizedcommunities, thereby finding applications across diverse domains. Existingresearch primarily focuses on traditional homogeneous networks, which cannot bedirectly applied to heterogeneous information networks (HINs). However,existing research also has some limitations. For instance, either they solelyfocus on single-type or multi-type community search, which severely lackingflexibility, or they require users to specify meta-paths or predefinedcommunity structures, which poses significant challenges for users who areunfamiliar with community search and HINs. In this paper, we propose aninnovative method, FCS-HGNN, that can flexibly identify either single-type ormulti-type communities in HINs based on user preferences. We propose theheterogeneous information transformer to handle node heterogeneity, and theedge-semantic attention mechanism to address edge heterogeneity. This not onlyconsiders the varying contributions of edges when identifying differentcommunities, but also expertly circumvents the challenges presented bymeta-paths, thereby elegantly unifying the single-type and multi-type communitysearch problems. Moreover, to enhance the applicability on large-scale graphs,we propose the neighbor sampling and depth-based heuristic search strategies,resulting in LS-FCS-HGNN. This algorithm significantly improves training andquery efficiency while maintaining outstanding community effectiveness. Weconducted extensive experiments on five real-world large-scale HINs, and theresults demonstrated that the effectiveness and efficiency of our proposedmethod, which significantly outperforms state-of-the-art methods.

FCS-HGNN: Flexible Multi-type Community Search in Heterogeneous Information Networks