Beyond Binary Opinions: A Deep Reinforcement Learning-Based Approach to Uncertainty-Aware Competitive Influence Maximization

2025-04-21

AI Summary

Existing competitive information diffusion models in online social networks suffer from oversimplified binary opinion assumptions, neglecting user behavioral heterogeneity and prior knowledge, thereby failing to capture opinion uncertainty. To address this, we propose DRIM, an uncertainty-aware deep reinforcement learning framework. Its core innovation is the Uncertainty-aware Opinion Model (UOM), the first multidimensional opinion representation grounded in subjective logic, which jointly quantifies user belief, uncertainty, and bias, and integrates them into the DRL decision-making process to achieve dynamic exploration-exploitation trade-offs and robust optimization against initial biases. Evaluated under dual objectives—promoting true information diffusion and suppressing misinformation—DRIM outperforms state-of-the-art methods by up to 57% in true-information influence and 88% in misinformation resistance, while accelerating runtime by 77%. Performance gains are particularly pronounced in highly observable and strongly connected networks.

Technology Category

• Reasoning under Uncertainty: Uncertainty Representations
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

The Competitive Influence Maximization (CIM) problem involves multiple entities competing for influence in online social networks (OSNs). While Deep Reinforcement Learning (DRL) has shown promise, existing methods often assume users' opinions are binary and ignore their behavior and prior knowledge. We propose DRIM, a multi-dimensional uncertainty-aware DRL-based CIM framework that leverages Subjective Logic (SL) to model uncertainty in user opinions, preferences, and DRL decision-making. DRIM introduces an Uncertainty-based Opinion Model (UOM) for a more realistic representation of user uncertainty and optimizes seed selection for propagating true information while countering false information. In addition, it quantifies uncertainty in balancing exploration and exploitation. Results show that UOM significantly enhances true information spread and maintains influence against advanced false information strategies. DRIM-based CIM schemes outperform state-of-the-art methods by up to 57% and 88% in influence while being up to 48% and 77% faster. Sensitivity analysis indicates that higher network observability and greater information propagation boost performance, while high network activity mitigates the effect of users' initial biases.

Problem

• Modeling multi-dimensional uncertainty in user opinions and preferences
• Optimizing seed selection for true information propagation
• Balancing exploration and exploitation in competitive influence maximization

Innovation

• Uses Subjective Logic for uncertainty modeling
• Introduces Uncertainty-based Opinion Model (UOM)
• Optimizes seed selection for information control