Enhancing Text-Based Hierarchical Multilabel Classification for Mobile Applications via Contrastive Learning

TL;DR

This paper introduces a hierarchical multilabel classification framework for mobile app text data, combining a novel network architecture with contrastive learning to improve label distinction and downstream task performance.

Contribution

The paper proposes HMCN and HMCL, integrating hierarchical classification with contrastive learning, and demonstrates their effectiveness on real-world datasets with deployment at Tencent.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Enhances downstream credit risk management by 10.70%.

Deployed successfully at Tencent for over a year.

Abstract

A hierarchical labeling system for mobile applications (apps) benefits a wide range of downstream businesses that integrate the labeling with their proprietary user data, to improve user modeling. Such a label hierarchy can define more granular labels that capture detailed app features beyond the limitations of traditional broad app categories. In this paper, we address the problem of hierarchical multilabel classification for apps by using their textual information such as names and descriptions. We present: 1) HMCN (Hierarchical Multilabel Classification Network) for handling the classification from two perspectives: the first focuses on a multilabel classification without hierarchical constraints, while the second predicts labels sequentially at each hierarchical level considering such constraints; 2) HMCL (Hierarchical Multilabel Contrastive Learning), a scheme that is capable of learning more distinguishable app representations to enhance the performance of HMCN. Empirical results on our Tencent App Store dataset and two public datasets demonstrate that our approach performs well compared with state-of-the-art methods. The approach has been deployed at Tencent and the multilabel classification outputs for apps have helped a downstream task--credit risk management of user--improve its performance by 10.70% with regard to the Kolmogorov-Smirnov metric, for over one year.