ECLARE: Extreme Classification with Label Graph Correlations

TL;DR

ECLARE is a scalable deep learning model for extreme classification that leverages label correlations and text to improve accuracy and efficiency in predicting rare labels in large label sets.

Contribution

It introduces a frugal, scalable architecture that incorporates label correlation graphs and textual descriptions for improved extreme classification performance.

Findings

ECLARE achieves 2-14% higher accuracy on benchmark datasets.

It provides real-time predictions within a few milliseconds.

The method scales to millions of labels efficiently.

Abstract

Deep extreme classification (XC) seeks to train deep architectures that can tag a data point with its most relevant subset of labels from an extremely large label set. The core utility of XC comes from predicting labels that are rarely seen during training. Such rare labels hold the key to personalized recommendations that can delight and surprise a user. However, the large number of rare labels and small amount of training data per rare label offer significant statistical and computational challenges. State-of-the-art deep XC methods attempt to remedy this by incorporating textual descriptions of labels but do not adequately address the problem. This paper presents ECLARE, a scalable deep learning architecture that incorporates not only label text, but also label correlations, to offer accurate real-time predictions within a few milliseconds. Core contributions of ECLARE include a frugal architecture and scalable techniques to train deep models along with label correlation graphs at the scale of millions of labels. In particular, ECLARE offers predictions that are 2 to 14% more accurate on both publicly available benchmark datasets as well as proprietary datasets for a related products recommendation task sourced from the Bing search engine. Code for ECLARE is available at https://github.com/Extreme-classification/ECLARE.