Differentiable Information Bottleneck for Deterministic Multi-view Clustering

arXiv:2403.15681v1 Announce Type: cross
Abstract: In recent several years, the information bottleneck (IB) principle provides an information-theoretic framework for deep multi-view clustering (MVC) by compressing multi-view observations while preserving the relevant information of multiple views. Although existing IB-based deep MVC methods have achieved huge success, they rely on variational approximation and distribution assumption to estimate the lower bound of mutual information, which is a notoriously hard and impractical problem in high-dimensional multi-view spaces. In this work, we propose a new …

abstract approximation arxiv clustering cs.it cs.lg differentiable distribution framework information math.it multiple success the information type view