Multi-modal Dynamic Proxy Learning for Personalized Multiple Clustering

TL;DR

This paper introduces Multi-DProxy, a dynamic multi-modal framework that uses learnable textual proxies and adaptive fusion to improve personalized multiple clustering, addressing static semantic rigidity and manual screening issues.

Contribution

The paper proposes a novel multi-modal dynamic proxy learning framework with adaptive fusion, dual-constraint proxy optimization, and iterative proxy refinement for personalized multiple clustering.

Findings

Achieves state-of-the-art performance on multi-clustering benchmarks.

Effectively captures user interest through learnable textual proxies.

Significantly improves clustering discrimination and relevance.

Abstract

Multiple clustering aims to discover diverse latent structures from different perspectives, yet existing methods generate exhaustive clusterings without discerning user interest, necessitating laborious manual screening. Current multi-modal solutions suffer from static semantic rigidity: predefined candidate words fail to adapt to dataset-specific concepts, and fixed fusion strategies ignore evolving feature interactions. To overcome these limitations, we propose Multi-DProxy, a novel multi-modal dynamic proxy learning framework that leverages cross-modal alignment through learnable textual proxies. Multi-DProxy introduces 1) gated cross-modal fusion that synthesizes discriminative joint representations by adaptively modeling feature interactions. 2) dual-constraint proxy optimization where user interest constraints enforce semantic consistency with domain concepts while concept constraints employ hard example mining to enhance cluster discrimination. 3) dynamic candidate management that refines textual proxies through iterative clustering feedback. Therefore, Multi-DProxy not only effectively captures a user's interest through proxies but also enables the identification of relevant clusterings with greater precision. Extensive experiments demonstrate state-of-the-art performance with significant improvements over existing methods across a broad set of multi-clustering benchmarks.