Navigating Conflicting Views: Harnessing Trust for Learning

2024-06-03

arXiv.org

AI Summary

To address unreliable decision-making caused by inter-view information conflicts in multi-view classification, this paper proposes an instance-level dynamic discounting fusion method grounded in computational trust. Departing from conventional equal-weight alignment assumptions, it introduces a probability-sensitive trust evaluation mechanism and a novel multi-view consistency metric—MVAGT—to enable heterogeneous, view-specific trust modeling. The method integrates evidence theory with uncertainty-aware prediction to adaptively weight contributions from individual views. Evaluated on six real-world datasets, the approach achieves significant improvements in Top-1 accuracy and AUC-ROC. Furthermore, Fleiss’ Kappa and MVAGT analyses confirm its effectiveness in mitigating view conflicts, thereby enhancing model robustness and decision reliability.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Multiagent Systems: Multiagent Systems under Uncertainty

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Resolving conflicts is essential to make the decisions of multi-view classification more reliable. Much research has been conducted on learning consistent informative representations among different views, assuming that all views are identically important and strictly aligned. However, real-world multi-view data may not always conform to these assumptions, as some views may express distinct information. To address this issue, we develop a computational trust-based discounting method to enhance the existing trustworthy framework in scenarios where conflicts between different views may arise. Its belief fusion process considers the trustworthiness of predictions made by individual views via an instance-wise probability-sensitive trust discounting mechanism. We evaluate our method on six real-world datasets, using Top-1 Accuracy, AUC-ROC for Uncertainty-Aware Prediction, Fleiss' Kappa, and a new metric called Multi-View Agreement with Ground Truth that takes into consideration the ground truth labels. The experimental results show that computational trust can effectively resolve conflicts, paving the way for more reliable multi-view classification models in real-world applications.

Problem

• Resolving conflicts in multi-view classification decisions
• Addressing non-identical importance and misalignment of views
• Enhancing trustworthiness framework with computational trust method

Innovation

• Trust-based discounting method for conflict resolution
• Probability-sensitive trust discounting mechanism
• Multi-view agreement metric with ground truth