Graph Wasserstein Correlation Analysis for Movie Retrieval

TL;DR

This paper introduces Graph Wasserstein Correlation Analysis (GWCA), a novel method for cross-graph comparison in movie retrieval that combines spectral graph filtering with Wasserstein metric learning, achieving effective heterogeneous graph analysis.

Contribution

The paper proposes a new GWCA method that integrates spectral graph filtering with Wasserstein metric learning for cross-graph comparison in movie retrieval, with a closed-form solution for graph comparison.

Findings

GWCA outperforms baseline methods on MovieGraphs dataset.

The method achieves a seamless integration of graph filtering and metric learning.

Experimental results validate the effectiveness of GWCA in movie retrieval tasks.

Abstract

Movie graphs play an important role to bridge heterogenous modalities of videos and texts in human-centric retrieval. In this work, we propose Graph Wasserstein Correlation Analysis (GWCA) to deal with the core issue therein, i.e, cross heterogeneous graph comparison. Spectral graph filtering is introduced to encode graph signals, which are then embedded as probability distributions in a Wasserstein space, called graph Wasserstein metric learning. Such a seamless integration of graph signal filtering together with metric learning results in a surprise consistency on both learning processes, in which the goal of metric learning is just to optimize signal filters or vice versa. Further, we derive the solution of the graph comparison model as a classic generalized eigenvalue decomposition problem, which has an exactly closed-form solution. Finally, GWCA together with movie/text graphs generation are unified into the framework of movie retrieval to evaluate our proposed method. Extensive experiments on MovieGrpahs dataset demonstrate the effectiveness of our GWCA as well as the entire framework.