<p>Incomplete multi-view clustering (IMC) has gained increasing attention for the frequent occurrence of missing samples in real-world multi-view data. And adaptive sample completion has become a widely adopted strategy in handling IMC, as it facilitates the recovery of latent information from incomplete views. Unfortunately, most existing adaptive sample completion-based IMC methods still have the high computational cost. Although anchor-based strategies have been utilized to reduce computational complexity, existing methods typically minimize the anchor-based reconstruction error to iteratively complete the data matrix, thereby underutilizing latent discriminative structures and limiting the completion performance. To address both the high computational complexity and the underutilization of latent discriminative features in existing sample completion-based IMC methods, we propose a novel IMC method, DAM-ASC, based on discriminative anchor-feature mining-assisted adaptive sample completion. The proposed method integrates an adaptive dual reconstruction mechanism with a local geometric preservation strategy, enabling a mutual enhancement between sample completion and discriminative representation learning. Specifically, a dual reconstruction representation based on anchors and latent discriminative feature mining is designed to adaptively complete missing samples with improved efficiency and accuracy. Furthermore, a local manifold constraint based on anchor-sample-guided local geometric structure preservation is introduced to preserve the intrinsic data structure and enhance the reliability of the reconstructed samples. Experimental results on multiple public datasets demonstrate that DAM-ASC achieves superior clustering performance compared to several state-of-the-art IMC methods.</p>