Publications

For a full list of publications, please see my Google Scholar profile.

Citations: 501, H-index: 9, I-10 index: 9

Disclaimer: This material is presented to ensure the timely dissemination of scholarly works. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms invoked by each author’s copyright.

* denotes equal contribution and authorship

Preprints and Working Projects

1. A. Chunduru, M. Morafah, et al., “FedMCP-Policy: Federated Learning of Schema-Aware Tool-Use Policies for LLMs”, Working Project, 2026.

2. H. Zhou, M. Morafah, S. Lee, M. Carbin, and S. Arora, “Why Reweighting Is Not Enough: A Multi-Objective View of Diffusion Training”, Working Project, 2026.

3. M. Morafah, K. Zhang, A. Rao, and X. Li, “Time-Conditioned Orthogonal Adapters for Diffusion Models”, Working Project, 2026.

4. V. Kungurtsev, M. Morafah, K. Mugo, and I. Sarmiento-Barbieri, “Deflating a Bubble While Spurring Growth: The Dual Case for Digital Twins for Agroforestry in Africa”, Working Paper, 2026.

5. V. Kungurtsev, M. Morafah, et al., “Data Markets and Market Failure: Asymmetric Information and Concentration”, Working Paper, 2026.

Under Review Papers

1. A. Chunduru, M. Morafah, V. Chellapandi, and A. Li, “Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data”, Under Review at TMLR, 2026.

2. A. Singh, J. Zhang, M. Morafah, and E. Bakhitov, “Deep Causal Inequalities”, Major Revision at Management Science, 2026.
   [Paper]

Preprints and Working Papers

Conference Papers

1. M. Morafah, V. Kungurtsev, H. Chang, C. Chen, and B. Lin, “Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration”, Advances in Neural Information Processing Systems (NeurIPS), Dec 2024. [Paper] [Project Website] [Code]

2. M. Morafah, H. Chang, and B. Lin, “Invited Paper: Large Scale Delocalized Federated Learning Over a Huge Diversity of Devices in Emerging Next-Generation Edge Intelligence Environments”, ACM/IEEE International Conference on Computer-Aided Design (ICCAD), October 2024. [Talk Website]

3. S. Vahidian, M. Morafah, W. Wang, C. Chen, M. Shah, and B. Lin, “Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces”, Association for the Advancement of Artificial Intelligence (AAAI), Nov 2022. [Paper] [Code]

4. S. Vahidian, M. Morafah, and B. Lin, “Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity”, IEEE 41st International Conference on Distributed Computing Systems (ICDCS), July 2021. [Paper] [Code] [Video]

Journal Papers

1. M. Morafah, H. Chang, C. Chen, and B. Lin, “Federated Learning Client Pruning for Noisy Labels”, ACM Transactions on Modeling and Performance Evaluation of Computing Systems, October 2024.

2. M. Morafah, W. Wang, and B. Lin, “FedZoo: A Practical Recipe to Federated Learning With Non-IID Data Experimental Design”, IEEE Transactions on Artificial Intelligence (IEEE TAI), July 2023. [Paper] [Code]

3. M. Morafah, S. Vahidian, W. Wang, and B. Lin, *“FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution”, IEEE Open Journal of the Computer Society, March 2023. [Paper] [Code]

4. M. Morafah, S. Vahidian, C. Chen, M. Shah, and B. Lin, “Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks”, IEEE Transactions on Artificial Intelligence (IEEE TAI), October 2022. [Paper] [Code]

5. V. Kungurtsev, M. Morafah, T. Javidi, and G. Scutari, “Decentralized Asynchronous Non-convex Stochastic Optimization on Directed Graphs”, IEEE Transactions on Control of Network Systems (TCNS), October 2022. [Paper]

Workshops

1. M. Morafah, M. Reisser, C. Louizos, and B. Lin, “Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data”, International Workshop on Federated Foundation Models for the Web (FL@FM-TheWebConf’24), May 2024. [Paper] [Website]

2. M. Morafah, S. Vahidian, W. Wang, and B. Lin, *“FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution”, International Workshop on Federated Learning in Conjunction with NeurIPS (FL-NeurIPS’22), October 2022. [Paper] [Code]

3. M. Morafah, S. Vahidian, C. Chen, M. Shah, and B. Lin, “Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks”, International Workshop on Federated Learning in Conjunction with NeurIPS (FL-NeurIPS’22), October 2022. [Paper] [Code] [Website]

Book Chapters

1. S. Ahmad, M. Alharbi, M. Morafah, and S. Jha, “Federated Learning - A Systematic Review”, IntechOpen, December 2024. [Book]

• denotes equal contribution