{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:36:26Z","timestamp":1776800186112,"version":"3.51.2"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-NMLP-2024-001"],"award-info":[{"award-number":["AISG-NMLP-2024-001"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-NMLP-2024-001"],"award-info":[{"award-number":["AISG-NMLP-2024-001"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s10994-025-06901-2","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T20:02:37Z","timestamp":1770235357000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["PC-MoE: memory-efficient and privacy-preserving collaborative training for Mixture-of-Experts LLMs"],"prefix":"10.1007","volume":"115","author":[{"given":"Ze Yu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bolin","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan Kian Hsiang","family":"Low","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,4]]},"reference":[{"key":"6901_CR1","doi-asserted-by":"crossref","unstructured":"Borzunov, A., Baranchuk, D., Dettmers, T., Ryabinin, M., Belkada, Y., Chumachenko, A., & Raffel, C. (2022). Petals: Collaborative inference and fine-tuning of large models. arXiv:2209.01188","DOI":"10.18653\/v1\/2023.acl-demo.54"},{"key":"6901_CR2","first-page":"374","volume":"1","author":"K Bonawitz","year":"2019","unstructured":"Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Kone\u010dn\u1ef3, J., Mazzocchi, S., McMahan, B., Van Overveldt, T., Petrou, D., Ramage, D., & Roselander, J. (2019). Towards federated learning at scale: System design. Proceedings of Machine Learning and Systems, 1, 374\u2013388.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"6901_CR3","doi-asserted-by":"crossref","unstructured":"Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017). Practical secure aggregation for privacy-preserving machine learning. In Proceedings of the 2017 ACM SIGSAC conference on computer and communications security (pp. 1175\u20131191).","DOI":"10.1145\/3133956.3133982"},{"key":"6901_CR4","unstructured":"Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert\u2011Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., & Amodei, D. (2020). Language models are few\u2011shot learners. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.), Advances in Neural Information Processing Systems (Vol. 33, pp. 1877\u20131901). Curran Associates, Inc."},{"key":"6901_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Bao, H., Huang, S., Dong, L., Jiao, B., Jiang, D., Zhou, H., Li, J., & Wei, F. (2022). The-x: Privacy-preserving transformer inference with homomorphic encryption. arXiv preprint. arXiv:2206.00216","DOI":"10.18653\/v1\/2022.findings-acl.277"},{"key":"6901_CR6","unstructured":"Clark, P., Cowhey, I., Etzioni, O., Khot, T., Sabharwal, A., Schoenick, C., & Tafjord, O. (2018). Think You have solved question answering? Try ARC, the AI2 reasoning challenge. arXiv preprint. arXiv:1803.05457"},{"key":"6901_CR7","doi-asserted-by":"crossref","unstructured":"Dibbo, S.V., Breuer, A., Moore, J., & Teti, M. (2024). Improving robustness to model inversion attacks via sparse coding architectures. arXiv preprint. arXiv:2403.14772.","DOI":"10.1007\/978-3-031-72989-8_7"},{"key":"6901_CR8","unstructured":"Castro, L., Polychroniadou, A., & Escudero, D. (2024). Privacy-preserving large language model inference via GPU-accelerated fully homomorphic encryption. In Neurips safe generative AI workshop 2024."},{"key":"6901_CR9","unstructured":"Douillard, A., Feng, Q., Rusu, A.A., Chhaparia, R., Donchev, Y., Kuncoro, A., Ranzato, M., Szlam, A., & Shen, J. (2023). DiLoCo: Distributed low-communication training of language models. arXiv:2311.08105."},{"key":"6901_CR10","unstructured":"Du, N., Huang, Y., Dai, A. M., Tong, S., Lepikhin, D., Xu, Y., Krikun, M., Zhou, Y., Yu, A. W., Firat, O., Zoph, B., Fedus, L., Bosma, M. P., Zhou, Z., Wang, T., Wang, E., Webster, K., Pellat, M., Robinson, K., Meier\u2011Hellstern, K., Duke, T., Dixon, L., Zhang, K., Le, Q. V., Wu, Y., Chen, Z., & Cui, C.(2022). GLAM: Efficient scaling of language models with mixture-of-experts. In International conference on machine learning (pp. 5547\u20135569). PMLR."},{"key":"6901_CR11","unstructured":"Eloul, S., Silavong, F., Kamthe, S., Georgiadis, A., & Moran, S. J. (2022). Enhancing privacy against inversion attacks in federated learning by using mixing gradients strategies. arXiv:2204.12495"},{"issue":"120","key":"6901_CR12","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., & Shazeer, N. (2022). Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research, 23(120), 1\u201339.","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"6901_CR14","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1109\/TSIPN.2023.3325963","volume":"9","author":"F Gauthier","year":"2023","unstructured":"Gauthier, F., Gogineni, V. C., Werner, S., Huang, Y.-F., & Kuh, A. (2023). Personalized graph federated learning with differential privacy. IEEE Transactions on Signal and Information Processing over Networks, 9(3), 736\u2013749. https:\/\/doi.org\/10.1109\/TSIPN.2023.3325963","journal-title":"IEEE Transactions on Signal and Information Processing over Networks"},{"key":"6901_CR13","unstructured":"Geiping, J., Bauermeister, H., Dr\u00f6ge, H., & Moeller, M. (2020). Inverting gradients\u2014how easy is it to break privacy in federated learning? In Advances in neural information processing systems (pp. 16937\u201316947)."},{"key":"6901_CR15","doi-asserted-by":"crossref","unstructured":"Gema, A. P., Leang, J. O. J., Hong, G., Devoto, A., Mancino, A. C. M., Saxena, R., He, X., Zhao, Y., Du, X., Ghasemi Madani, M. R., Barale, C., McHardy, R., Harris, J., Kaddour, J., Van Krieken, E., & Minervini, P. (2025). Are we done with MMLU? In L. Chiruzzo, A. Ritter, & L. Wang (Eds.), Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (pp. 5069\u20135096). Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.naacl-long.262"},{"issue":"7","key":"6901_CR21","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1109\/TMI.2023.3239391","volume":"42","author":"A Hatamizadeh","year":"2023","unstructured":"Hatamizadeh, A., Yin, H., Molchanov, P., Myronenko, A., Li, W., Dogra, P., Feng, A., Flores, M. G., Kautz, J., Xu, D., & Roth, H. R. (2023). Do gradient inversion attacks make federated learning unsafe? IEEE Transactions on Medical Imaging, 42(7), 2044\u20132056. https:\/\/doi.org\/10.1109\/TMI.2023.3239391","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"6901_CR18","unstructured":"He, X.O.: Mixture of a Million Experts. arXiv:2407.04153 (2024)"},{"key":"6901_CR16","doi-asserted-by":"crossref","unstructured":"Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., de Las Casas, D., Hendricks, L. A., Welbl, J., Clark, A., Hennigan, T., Noland, E., Millican, K., van den Driessche, G., Damoc, B., Guy, A., Osindero, S., Simonyan, K., Elsen, E., Vinyals, O., Rae, J. W., & Sifre, L. (2022). An empirical analysis of compute\u2011optimal large language model training. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, & A. Oh (Eds.), Advances in Neural Information Processing Systems (Vol. 35, pp. 30016\u201330030). Curran Associates, Inc.","DOI":"10.52202\/068431-2176"},{"issue":"2","key":"6901_CR20","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E. J., Shen, Y., Wallis, P., Allen\u2011Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). LoRA: Low\u2011rank adaptation of large language models. In International Conference on Learning Representations (ICLR).","journal-title":"ICLR"},{"key":"6901_CR19","unstructured":"Huang, Y., Gupta, S., Song, Z., Li, K., & Arora, S. (2021). Evaluating gradient inversion attacks and defenses in federated learning. In Advances in neural information processing systems (pp. 7232\u20137241)."},{"key":"6901_CR17","unstructured":"Hwang, C., Cui, W., Xiong, Y., Yang, Z., Liu, Z., Hu, H., Wang, Z., Salas, R., Jose, J., Ram, P., Chau, H., Cheng, P., Yang, F., Yang, M., & Xiong, Y. (2023). Tutel: Adaptive mixture\u2011of\u2011experts at scale. In D. Song, M. Carbin, & T. Chen (Eds.), Proceedings of Machine Learning and Systems (Vol. 5, pp. 269\u2013287)."},{"issue":"14","key":"6901_CR22","doi-asserted-by":"publisher","first-page":"6421","DOI":"10.3390\/app11146421","volume":"11","author":"D Jin","year":"2021","unstructured":"Jin, D., Pan, E., Oufattole, N., Weng, W.-H., Fang, H., & Szolovits, P. (2021). What disease does this patient have? A large-scale open domain question answering dataset from medical exams. Applied Sciences, 11(14), 6421. https:\/\/doi.org\/10.3390\/app11146421","journal-title":"Applied Sciences"},{"key":"6901_CR23","unstructured":"Jin, L., Zhang, Y., Li, Y., Wang, S., Yang, H.H., Wu, J., & Zhang, M. (2025). Moe2: Optimizing collaborative inference for edge large language models. arXiv preprint. arXiv:2501.09410"},{"key":"6901_CR25","unstructured":"Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020). Scaling laws for neural language models. arXiv:2001.08361. https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"6901_CR24","doi-asserted-by":"crossref","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners. In Advances in neural information processing systems (pp. 22199\u201322213).","DOI":"10.52202\/068431-1613"},{"key":"6901_CR30","unstructured":"Lai, K., Tang, Z., Pan, X., Dong, P., Liu, X., Chen, H., Shen, L., Li, B., & Chu, X. (2025). MEDIATOR: Memory-efficient llm merging with less parameter conflicts and uncertainty based routing. arXiv preprint. arXiv:2502.04411"},{"key":"6901_CR26","unstructured":"Lepikhin, D., Lee, H., Xu, Y., Chen, D., Firat, O., Huang, Y., Krikun, M., Shazeer, N., & Chen, Z. (2021). GShard: Scaling giant models with conditional computation and automatic sharding. In International Conference on Learning Representations (ICLR)."},{"key":"6901_CR28","unstructured":"Li, D., Shao, R., Wang, H., Guo, H., Xing, E. P., & Zhang, H. (2022). MPCFORMER: Fast, performant and private transformer inference with MPC. arXiv preprint. arXiv:2211.01452."},{"key":"6901_CR27","doi-asserted-by":"crossref","unstructured":"Li, Q., Shen, Z., Qin, Z., Xie, Y., Zhang, X., Du, T., Cheng, S., Wang, X., & Yin, J. (2024). TRANSLINKGUARD: Safeguarding transformer models against model stealing in edge deployment. In Proceedings of the 32nd ACM international conference on multimedia (pp. 3479\u20133488).","DOI":"10.1145\/3664647.3680786"},{"key":"6901_CR29","first-page":"429","volume":"2","author":"T Li","year":"2020","unstructured":"Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated optimization in heterogeneous networks. Proceedings of Machine Learning and Systems, 2, 429\u2013450.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"6901_CR31","doi-asserted-by":"crossref","unstructured":"Li, W., Xu, Q., & Dras, M. (2024). Seeing the forest through the trees: Data leakage from partial transformer gradients. arXiv:2406.00999.","DOI":"10.18653\/v1\/2024.emnlp-main.275"},{"key":"6901_CR33","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics (pp. 1273\u20131282). PMLR."},{"key":"6901_CR32","doi-asserted-by":"crossref","unstructured":"Mihaylov, T., Clark, P., Khot, T., & Sabharwal, A. (2018). Can a suit of armor conduct electricity? A new dataset for open book question answering. arXiv:1809.02789","DOI":"10.18653\/v1\/D18-1260"},{"key":"6901_CR36","doi-asserted-by":"crossref","unstructured":"Pan, X., Lin, W., Shi, S., Chu, X., Sun, W., & Li, B. (2024). PARM: Efficient training of large sparsely-activated models with dedicated schedules. In IEEE INFOCOM 2024-IEEE conference on computer communications (pp. 1880\u20131889). IEEE.","DOI":"10.1109\/INFOCOM52122.2024.10621327"},{"key":"6901_CR37","doi-asserted-by":"crossref","unstructured":"Pan, X., Lin, W., Zhang, L., Shi, S., Tang, Z., Wang, R., Li, B., & Chu, X. (2025). FSMOE: A flexible and scalable training system for sparse mixture-of-experts models. In Proceedings of the 30th ACM international conference on architectural support for programming languages and operating systems (Vol. 1, pp. 524\u2013539).","DOI":"10.1145\/3669940.3707272"},{"key":"6901_CR35","unstructured":"Patterson, D. A., Gonzalez, J., Le, Q. V., Liang, C., Munguia, L.-M., Rothchild, D., So, D. R., Texier, M., & Dean, J. (2021). Carbon emissions and large neural network training. arXiv:2104.10350."},{"key":"6901_CR34","doi-asserted-by":"crossref","unstructured":"Petrov, I., Dimitrov, D.I., Baader, M., M\u00fcller, M., & Vechev, M. (2024). DAGER: Exact gradient inversion for large language models. In Advances in neural information processing systems (pp. 87801\u201387830).","DOI":"10.52202\/079017-2787"},{"key":"6901_CR38","unstructured":"Rajbhandari, S., Li, C., Yao, Z., Zhang, M., Aminabadi, R.Y., Awan, A. A., Rasley, J., & He, Y. (2022). Deepspeed-MOE: Advancing mixture-of-experts inference and training to power next-generation AI scale. In International conference on machine learning (pp. 18332\u201318346). PMLR."},{"key":"6901_CR39","doi-asserted-by":"crossref","unstructured":"Sarlin, P.-E., DeTone, D., Malisiewicz, T., & Rabinovich, A. (2020). Superglue: Learning feature matching with graph neural networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 4938\u20134947).","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"6901_CR40","unstructured":"Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., & Dean, J. (2017). Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv:1701.06538"},{"key":"6901_CR41","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., & Catanzaro, B. (2019). Megatron-LM: Training multi-billion parameter language models using model parallelism. arXiv:1909.08053"},{"key":"6901_CR43","doi-asserted-by":"crossref","unstructured":"Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017). Membership inference attacks against machine learning models. In 2017 IEEE symposium on security and privacy (SP) (pp. 3\u201318). IEEE.","DOI":"10.1109\/SP.2017.41"},{"key":"6901_CR42","doi-asserted-by":"crossref","unstructured":"Suzgun, M., Scales, N., Sch\u00e4rli, N., Gehrmann, S., Tay, Y., Chung, H. W., Chowdhery, A., Le, Q. V., Chi, E. H., Zhou, D., & Wei, J. (2023). Challenging BIG-bench tasks and whether chain-of-thought can solve them. In Findings of the Association for Computational Linguistics: ACL 2023 (pp. 13003\u201313051). Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"6901_CR45","doi-asserted-by":"crossref","unstructured":"Tan, S., Knott, B., Tian, Y., & Wu, D. J. (2021). CRYPTGPU: Fast privacy-preserving machine learning on the GPU. In 2021 IEEE symposium on security and privacy (SP) (pp. 1021\u20131038). IEEE.","DOI":"10.1109\/SP40001.2021.00098"},{"key":"6901_CR46","doi-asserted-by":"crossref","unstructured":"Tan, Y., Long, G., Liu, L., Zhou, T., Lu, Q., Jiang, J., & Zhang, C. (2022). FEDPROTO: Federated prototype learning across heterogeneous clients. In Proceedings of the AAAI conference on artificial intelligence (Vol. 36, pp. 8432\u20138440).","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"6901_CR47","doi-asserted-by":"crossref","unstructured":"Tang, Z., Zhang, Y., Dong, P., Cheung, Y.-M., Zhou, A., Han, B., & Chu, X. (2024). Fusefl: one-shot federated learning through the lens of causality with progressive model fusion. In Advances in neural information processing systems (Vol. 37, pp. 28393\u201328429).","DOI":"10.52202\/079017-0891"},{"key":"6901_CR44","unstructured":"Thompson, N. C., Greenewald, K., Lee, K., & Manso, G. F. (2020). The computational limits of deep learning. arXiv:2007.05558"},{"key":"6901_CR53","unstructured":"Watson, J.-L., Wagh, S., & Popa, R. A. (2022). PIRANHA: A {GPU} platform for secure computation. In 31st USENIX security symposium (USENIX Security 22) (pp. 827\u2013844)."},{"key":"6901_CR52","unstructured":"Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., Chi, E. H., Hashimoto, T., Vinyals, O., Liang, P., Dean, J., & Fedus, W. (2022). Emergent abilities of large language models. Transactions on Machine Learning Research."},{"issue":"8","key":"6901_CR48","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","volume":"15","author":"K Wei","year":"2020","unstructured":"Wei, K., Li, J., Ding, M., Ma, C., Yang, H. H., Farokhi, F., Jin, S., Quek, T. Q. S., & Poor, H. V. (2020). Federated learning with differential privacy: Algorithms and performance analysis. IEEE Transactions on Information Forensics and Security, 15(8), 3454\u20133469. https:\/\/doi.org\/10.1109\/TIFS.2020.2988575","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"6901_CR50","doi-asserted-by":"crossref","unstructured":"Wei, W., Liu, L., Wu, Y., Su, G., & Iyengar, A. (2021). Gradient-leakage resilient federated learning. In 2021 IEEE 41st international conference on distributed computing systems (ICDCS) (pp. 797\u2013807). IEEE.","DOI":"10.1109\/ICDCS51616.2021.00081"},{"issue":"14s","key":"6901_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3593021","volume":"55","author":"NC Will","year":"2023","unstructured":"Will, N. C., & Maziero, C. A. (2023). Intel software guard extensions applications: A survey. ACM Computing Surveys, 55(14s), 1\u201338.","journal-title":"ACM Computing Surveys"},{"key":"6901_CR49","doi-asserted-by":"crossref","unstructured":"Wu, F., Li, Z., Li, Y., Ding, B., & Gao, J. (2024). FEDBIOT: LLM local fine-tuning in federated learning without full model. In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining (pp. 3345\u20133355).","DOI":"10.1145\/3637528.3671897"},{"key":"6901_CR55","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, Y., Zheng, Y., Tian, X., Peng, H., Liu, T., & Han, B. (2023). FEDFED: Feature distillation against data heterogeneity in federated learning. In Advances in neural information processing systems (Vol. 36, pp. 60397\u201360428).","DOI":"10.52202\/075280-2639"},{"key":"6901_CR54","doi-asserted-by":"crossref","unstructured":"Yao, J., Anthony, Q., Shafi, A., Subramoni, H., & Panda, D. K. D. (2024). Exploiting inter-layer expert affinity for accelerating mixture-of-experts model inference. In 2024 IEEE International parallel and distributed processing symposium (IPDPS) (pp. 915\u2013925). IEEE.","DOI":"10.1109\/IPDPS57955.2024.00086"},{"key":"6901_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, R., Guo, S., Wang, J., Xie, X., & Tao, D. (2022). A survey on gradient inversion: Attacks, defenses and future directions. arXiv:2206.07284","DOI":"10.24963\/ijcai.2022\/791"},{"key":"6901_CR60","unstructured":"Zhang, Y., Qin, Z., Wu, Z., Hou, J., & Deng, S. (2024). Personalized federated fine-tuning for llms via data-driven heterogeneous model architectures. arXiv preprint arXiv:2411.19128."},{"key":"6901_CR57","doi-asserted-by":"publisher","unstructured":"Zhao, C., Deng, C., Ruan, C., Dai, D., Gao, H., Li, J., Zhang, L., Huang, P., Zhou, S., Ma, S., Liang, W., He, Y., Wang, Y., Liu, Y., & Wei, Y. X. (2025). Insights into DeepSeek\u2011V3: Scaling challenges and reflections on hardware for AI architectures. In Proceedings of the 52nd Annual International Symposium on Computer Architecture (ISCA \u201925) (pp. 1731\u20131745). Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3695053.3731412","DOI":"10.1145\/3695053.3731412"},{"key":"6901_CR56","doi-asserted-by":"crossref","unstructured":"Zhong, W., Cui, R., Guo, Y., Liang, Y., Lu, S., Wang, Y., Saied, A., Chen, W., & Duan, N. (2023). AGIEval: A human-centric benchmark for evaluating foundation models. arXiv:2304.06364.","DOI":"10.18653\/v1\/2024.findings-naacl.149"},{"key":"6901_CR59","unstructured":"Zhu, L., Liu, Z., & Han, S. (2019). Deep leakage from gradients. In Advances in neural information processing systems (Vol. 32)."},{"key":"6901_CR61","doi-asserted-by":"crossref","unstructured":"Zou, Y., Qi, S., Yuan, Y., Wang, D., Shen, S., Wu, L., Guo, S., & Yu, D. (2024). FED-MOE: Efficient federated learning for mixture-of-experts models via empirical pruning. In International conference on parallel and distributed computing: Applications and technologies (pp. 128\u2013139). Springer.","DOI":"10.1007\/978-981-96-4207-6_12"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06901-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06901-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06901-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T18:43:37Z","timestamp":1776797017000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06901-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":61,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["6901"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06901-2","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"2 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"31"}}