Trusted Multi-view Learning for Long-tailed Classification

TL;DR

This paper introduces TMLC, a framework for long-tailed multi-view classification that uses opinion aggregation and pseudo-data generation to effectively address class imbalance issues.

Contribution

The paper presents a novel multi-view long-tailed classification framework with a group consensus opinion mechanism and an uncertainty-guided pseudo-data generation method.

Findings

Achieves superior performance on long-tailed multi-view datasets.

Effectively mitigates class imbalance through pseudo-data generation.

Demonstrates the effectiveness of opinion aggregation in multi-view learning.

Abstract

Class imbalance has been extensively studied in single-view scenarios; however, addressing this challenge in multi-view contexts remains an open problem, with even scarcer research focusing on trustworthy solutions. In this paper, we tackle a particularly challenging class imbalance problem in multi-view scenarios: long-tailed classification. We propose TMLC, a Trusted Multi-view Long-tailed Classification framework, which makes contributions on two critical aspects: opinion aggregation and pseudo-data generation. Specifically, inspired by Social Identity Theory, we design a group consensus opinion aggregation mechanism that guides decision making toward the direction favored by the majority of the group. In terms of pseudo-data generation, we introduce a novel distance metric to adapt SMOTE for multi-view scenarios and develop an uncertainty-guided data generation module that produces high-quality pseudo-data, effectively mitigating the adverse effects of class imbalance. Extensive experiments on long-tailed multi-view datasets demonstrate that our model is capable of achieving superior performance. The code is released at https://github.com/cncq-tang/TMLC.