Explainable Multi-Agent Budget Optimization for Privacy-Preserving Creator Economy Advertising in AI-Driven Digital Platforms
Keywords:
multi-agent systems, budget optimization, privacy preservation, creator economy, explainable AI, differential privacy, federated learning, advertising attribution, fairness, digital platform governanceAbstract
The rapid expansion of the creator economy within AI-driven digital platforms has introduced critical challenges at the intersection of advertising effectiveness, user privacy, and algorithmic fairness. This paper proposes a comprehensive framework for explainable multi-agent budget optimization tailored to privacy-preserving creator economy advertising. The framework integrates multiple intelligent agents responsible for budget allocation, attribution modeling, privacy budget management, and explainability generation, operating under federated and differentially private constraints. We examine the structural trade-offs inherent in balancing ad performance with creator monetization, user data protection, and platform governance. A key contribution is the design of a hierarchical multi-agent architecture that enables decentralized decision-making while preserving global optimization objectives through coordinated budget negotiations. The paper analyzes the role of differential privacy budgets in cross-device attribution and the implications of adaptive privacy mechanisms for fairness across creators of varying scales. Explainability is achieved through agent-level audit trails and counterfactual explanations that allow stakeholders to interpret budget reallocation decisions. We further explore deployment considerations including scalability under heterogeneous device environments, robustness against adversarial attacks, and sustainability of privacy guarantees over long-term learning horizons. Policy implications are discussed with respect to regulatory compliance, creator equity, and transparency obligations. By bridging explainable AI, multi-agent systems, and privacy-preserving techniques, this work provides a systematic framework for designing trustworthy advertising ecosystems in the creator economy.
References
1. Dwork, C., & Roth, A. (2014). The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science, 9(3–4), 211–407.
2. McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. y. (2017). Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) (pp. 1273–1282). PMLR.
3. Lipton, Z. C. (2018). The mythos of model interpretability. Queue, 16(3), 31–57.
4. Shi, C., Li, S., Guo, S., Xie, S., Wu, W., Dou, J., ... & Chua, T. S. (2025). Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation. arXiv preprint arXiv:2511.17282.
5. Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS) (pp. 308–318). ACM.
6. Buolamwini, J., & Gebru, T. (2018). Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (FAccT) (pp. 77–91). PMLR.
7. Dwork, C., Rothblum, G. N., & Vadhan, S. (2010). Boosting and differential privacy. In Proceedings of the 51st Annual IEEE Symposium on Foundations of Computer Science (FOCS) (pp. 51–60). IEEE.
8. Zinkevich, M., Weimer, M., Li, L., & Smola, A. J. (2010). Parallelized stochastic gradient descent. In Advances in Neural Information Processing Systems 23 (NeurIPS) (pp. 2595–2603).
9. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems 30 (NeurIPS) (pp. 5998–6008). 10.Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016). Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492.
11. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (NeurIPS) (pp. 4765–4774).
12. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (pp. 1135–1144). ACM.
13. Chen, J., & Shapiro, J. (2022). Fairness and privacy in online advertising. Journal of Economics & Management Strategy, 31(3), 563–587.
14. Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2020). How to backdoor federated learning. In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS) (pp. 2938–2948). PMLR.
15. Chaudhuri, K., Sarwate, A. D., & Sinha, K. (2013). A near-optimal algorithm for differentially private principal components. Journal of Machine Learning Research, 14, 2905–2943.
16. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
17. Hardt, M., & Rothblum, G. N. (2010). A multiplicative weights mechanism for privacy-preserving data analysis. In Proceedings of the 51st Annual IEEE Symposium on Foundations of Computer Science (FOCS) (pp. 61–70). IEEE.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Artificial Intelligence Engineering and Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
