LargeMvC-Net: Anchor-based Deep Unfolding Network for Large-scale Multi-view Clustering

TL;DR

LargeMvC-Net introduces a novel deep unfolding network for large-scale multi-view clustering, explicitly modeling the optimization process to improve effectiveness and scalability over existing heuristic methods.

Contribution

The paper proposes a structurally clear deep unfolding network, LargeMvC-Net, that directly models the optimization of anchor-based multi-view clustering, enhancing both interpretability and performance.

Findings

Outperforms state-of-the-art methods on large-scale benchmarks.

Demonstrates improved scalability and clustering accuracy.

Provides a novel modular architecture for anchor-based clustering.

Abstract

Deep anchor-based multi-view clustering methods enhance the scalability of neural networks by utilizing representative anchors to reduce the computational complexity of large-scale clustering. Despite their scalability advantages, existing approaches often incorporate anchor structures in a heuristic or task-agnostic manner, either through post-hoc graph construction or as auxiliary components for message passing. Such designs overlook the core structural demands of anchor-based clustering, neglecting key optimization principles. To bridge this gap, we revisit the underlying optimization problem of large-scale anchor-based multi-view clustering and unfold its iterative solution into a novel deep network architecture, termed LargeMvC-Net. The proposed model decomposes the anchor-based clustering process into three modules: RepresentModule, NoiseModule, and AnchorModule, corresponding to representation learning, noise suppression, and anchor indicator estimation. Each module is derived by unfolding a step of the original optimization procedure into a dedicated network component, providing structural clarity and optimization traceability. In addition, an unsupervised reconstruction loss aligns each view with the anchor-induced latent space, encouraging consistent clustering structures across views. Extensive experiments on several large-scale multi-view benchmarks show that LargeMvC-Net consistently outperforms state-of-the-art methods in terms of both effectiveness and scalability.