Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies

TL;DR

This paper introduces ProxyGML, a novel graph-based deep metric learning method that uses fewer proxies to effectively capture global and local data relationships, improving performance and efficiency over existing approaches.

Contribution

The paper proposes a proxy-based graph metric learning approach that reduces the number of proxies while enhancing global and local relationship modeling for better performance.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Achieves higher accuracy with fewer proxies

Demonstrates improved efficiency in metric learning tasks

Abstract

Deep metric learning plays a key role in various machine learning tasks. Most of the previous works have been confined to sampling from a mini-batch, which cannot precisely characterize the global geometry of the embedding space. Although researchers have developed proxy- and classification-based methods to tackle the sampling issue, those methods inevitably incur a redundant computational cost. In this paper, we propose a novel Proxy-based deep Graph Metric Learning (ProxyGML) approach from the perspective of graph classification, which uses fewer proxies yet achieves better comprehensive performance. Specifically, multiple global proxies are leveraged to collectively approximate the original data points for each class. To efficiently capture local neighbor relationships, a small number of such proxies are adaptively selected to construct similarity subgraphs between these proxies and each data point. Further, we design a novel reverse label propagation algorithm, by which the neighbor relationships are adjusted according to ground-truth labels, so that a discriminative metric space can be learned during the process of subgraph classification. Extensive experiments carried out on widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate the superiority of the proposed ProxyGML over the state-of-the-art methods in terms of both effectiveness and efficiency. The source code is publicly available at https://github.com/YuehuaZhu/ProxyGML.