Multi-relation Message Passing for Multi-label Text Classification

TL;DR

This paper introduces Multi-relation Message Passing (MrMP), a novel method for multi-label text classification that models various types of label dependencies, including rare co-occurrences and directional relationships, improving performance with minimal overhead.

Contribution

The paper proposes MrMP, a new approach that captures multiple types of label relationships, including rare and directional dependencies, for enhanced multi-label classification.

Findings

MrMP achieves comparable or better accuracy than state-of-the-art methods.

The approach adds minimal computational and memory overhead.

Experimental results on benchmark datasets validate the effectiveness of MrMP.

Abstract

A well-known challenge associated with the multi-label classification problem is modelling dependencies between labels. Most attempts at modelling label dependencies focus on co-occurrences, ignoring the valuable information that can be extracted by detecting label subsets that rarely occur together. For example, consider customer product reviews; a product probably would not simultaneously be tagged by both "recommended" (i.e., reviewer is happy and recommends the product) and "urgent" (i.e., the review suggests immediate action to remedy an unsatisfactory experience). Aside from the consideration of positive and negative dependencies, the direction of a relationship should also be considered. For a multi-label image classification problem, the "ship" and "sea" labels have an obvious dependency, but the presence of the former implies the latter much more strongly than the other way around. These examples motivate the modelling of multiple types of bi-directional relationships between labels. In this paper, we propose a novel method, entitled Multi-relation Message Passing (MrMP), for the multi-label classification problem. Experiments on benchmark multi-label text classification datasets show that the MrMP module yields similar or superior performance compared to state-of-the-art methods. The approach imposes only minor additional computational and memory overheads.