Federated Incomplete Multi-View Clustering with Tensorized Low-Rank Constraint

Federated Multi-View Clustering (FedMVC) has gained widespread attention for its ability to discover complementary clustering structures of distributed multi-view data while preserving data privacy. However, real-world clients often only have access to partial information, and the view incompleteness makes it more challenging for federated multi-view feature fusion to exploit consistency and complementary information. For another, efficiency is highly expected in federated scenarios, while existing federated incomplete multi-view clustering (FedIMVC) methods generally suffers from the curse of dimension. To alleviate these issues, we propose \textbf{F}ederated \textbf{I}ncomplete \textbf{M}ulti-\textbf{V}iew \textbf{C}lustering with \textbf{T}ensorized \textbf{L}ow-\textbf{R}ank \textbf{C}onstraint (FMVC-TLRC), which incorporates anchors to improve efficiency and is able to process ubiquitous view incompleteness issue in federated scenarios. FMVC-TLRC first aligns the local anchor graphs and employ tensorized low-rank constraint based on tensor Schatten p-norm to enforce the consistency of the data representations learned by each client. Besides, a federated unified framework is developed to jointly optimize the construction and alignment of anchor graphs, enabling collaborative model training. Experimental results on multiple datasets demonstrate the effectiveness of FIMVC-TLRC.