解耦多视图表示，提升聚类质量
Learning Disentangled Representations for Generalized Multi-view Clustering
- 双路径自编码器分离视图特有与共有特征
- 跨视图对抗判别器增强特征区分性
- 在13个数据集上优于现有方法
多视图聚类（MVC）因其能利用不同视图间的互补信息而受到广泛关注。然而，现有深度MVC方法在跨视图融合时常面临视图分布纠缠问题，影响共享潜在空间质量，导致聚类效果不佳。为此，我们提出广义多视图自编码器（GMAE），通过解耦表示学习保留跨视图互补性。GMAE采用双路径自编码器，将源特征解耦为视图特有和视图共有嵌入，促进更清晰的聚类结构发现。进一步构建跨视图对抗判别器，引导视图特有编码器捕捉更具区分性的特征。通过策略性调节互信息，GMAE有效对齐分布并防止表示坍缩，确保生成鲁棒、非平凡的嵌入。在13个基准数据集上的综合实验表明，GMAE在完整与不完整MVC任务中均持续优于当前最优方法。代码已开源：https://github.com/obananas/GMAE。
原文摘要 · Abstract (English)
Multi-View Clustering (MVC) has gained significant attention for its ability to leverage complementary information across diverse views. However, existing deep MVC methods often struggle with view-distribution entanglement during cross-view fusion, which hampers the quality of the shared latent space and leads to suboptimal Figures. To address this issue, we propose the Generalized Multi-view Auto-Encoder (GMAE), a framework designed to preserve cross-view complementarity through disentangled representation learning. Specifically, GMAE employs dual-path autoencoders to decouple source features into view-specific and view-common embeddings, facilitating the discovery of clearer clustering structures. We further construct cross-view adversarial discriminators to guide view-specific encoders in capturing more discriminative features. By strategically modulating mutual information, GMAE effectively aligns distributions and prevents representation collapse, ensuring the generation of robust, non-trivial embeddings. Comprehensive experiments on 13 benchmark datasets demonstrate that GMAE consistently outperforms state-of-the-art methods in both complete and incomplete MVC tasks. Our code implementation is available at the repository: https://github.com/obananas/GMAE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。