MAST: A Multi-View Alignment Strategy for Optimal Transport-Based Contrastive Clustering of Short Text

Short text clustering has gained significant prominence due to its ubiquity in real-world applications. Despite the recent success of contrastive clustering, existing paradigms still suffer from two bottlenecks: (1) conventional data augmentation provides limited semantic granularity and may introduce unintended noise; and (2) the absence of global optimization for cluster assignments often precipitates the accumulation of pseudo-label noise, thereby compromising semantic consistency. To bridge these gaps, we propose MAST, a Multi-view Alignment Strategy with Transport-based clustering. MAST constructs complementary structural views to capture multi-granularity semantic features and introduces a multi-view contrastive objective that jointly aligns original, augmented, and structure-enhanced embeddings. To mitigate representation oversmoothing, we incorporate structure-aware negative reweighting and intermediate-layer negative sampling. Furthermore, MAST employs high-confidence guided refinement and an optimal transport-based pseudo-label alignment mechanism to enforce semantic consistency across multiple views. Extensive experiments on several benchmark datasets demonstrate that MAST consistently outperforms state-of-theart methods, establishing a competitive baseline for short text clustering.