QoS-Aware Token Scheduling and Private Data Valuation for Multi-Modal Agentic Networks

Unknown Date

AI Summary

This work addresses the challenges of privacy leakage, degraded service quality, and fairness issues arising from data centralization and heterogeneity in multimodal agent networks. To tackle these problems, the authors propose a fair incentive framework that integrates differential privacy with multimodal semantic alignment. By constructing multimodal representations in a shared semantic space and introducing a differentially private prototype release mechanism, the framework enables efficient data valuation and token allocation under strong privacy guarantees. This approach uniquely combines differentially private prototypes with multimodal semantic alignment while accounting for resource constraints and service quality requirements. Experimental results demonstrate that, compared to baseline methods, the proposed scheme significantly improves contribution-aware fairness and service performance, while effectively resisting image reconstruction attacks and enhancing the privacy protection of individual multimodal data.

Abstract

In agentic systems, human-generated data records anchor the value of AI services. Yet cloud compute pipelines centralize processing on remote servers. Data centralization reduces personal data sovereignty and may potentially degrade the quality of service (QoS). Meanwhile, user contributions are diverse in quantity and quality: decentralized records can be biased, noisy, and heterogeneously distributed. To address the data challenge, we study fair token allocation and private data valuation for decentralized and resource-constrained agentic systems. Our approach embeds multi-modal representations in a shared semantic space and releases differentially private (DP) prototypes to preserve utility while reducing semantic leakage. With the DP guarantee, we design a fair token allocation scheme that rewards effective contributions and remains robust to data heterogeneity and AI resource scarcity. Extensive simulations demonstrate improved contribution-based fairness and QoS compared to standard benchmarks. The improved resistance to image reconstruction attacks indicates enhanced privacy for multi-modal personal data.

Problem

• QoS
• data valuation
• decentralized agentic systems
• multi-modal data
• data sovereignty

Innovation

• differentially private prototypes
• multi-modal agentic networks
• QoS-aware token scheduling
• fair contribution valuation
• semantic space embedding