{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:40:40Z","timestamp":1792784440268,"version":"4.5.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372236"],"award-info":[{"award-number":["62372236"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"},{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100006579","name":"Ministry of Industry and Information Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["IDPSA2025-002"],"award-info":[{"award-number":["IDPSA2025-002"]}],"id":[{"id":"10.13039\/501100006579","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109632","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T19:55:51Z","timestamp":1789502151000},"page":"109632","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["CALM: Fine-grained federated unlearning via CLIP-assisted LoRA-MoE memory editing"],"prefix":"10.1016","volume":"205","author":[{"given":"Mang","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1523-5020","authenticated-orcid":false,"given":"Yang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caiyun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongsheng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yansong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1632-5737","authenticated-orcid":false,"given":"Anmin","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109632_bib0001","series-title":"International conference on artificial intelligence and statistics","first-page":"2938","article-title":"How to backdoor federated learning","author":"Bagdasaryan","year":"2020"},{"key":"10.1016\/j.neunet.2026.109632_bib0002","first-page":"8632","article-title":"A little is enough: Circumventing defenses for distributed learning","volume":"32","author":"Baruch","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"9","key":"10.1016\/j.neunet.2026.109632_bib0003","doi-asserted-by":"crossref","first-page":"3203","DOI":"10.1007\/s10994-022-06178-9","article-title":"Machine unlearning: Linear filtration for logit-based classifiers","volume":"111","author":"Baumhauer","year":"2022","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2026.109632_bib0004","series-title":"2021\u202fIEEE symposium on security and privacy (SP)","first-page":"141","article-title":"Machine unlearning","author":"Bourtoule","year":"2021"},{"key":"10.1016\/j.neunet.2026.109632_bib0005","series-title":"2023\u202fIEEE symposium on security and privacy (SP)","first-page":"1366","article-title":"Fedrecover: Recovering from poisoning attacks in federated learning using historical information","author":"Cao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109632_bib0006","series-title":"International conference on machine learning","first-page":"4241","article-title":"Fast federated machine unlearning with nonlinear functional theory","author":"Che","year":"2023"},{"key":"10.1016\/j.neunet.2026.109632_bib0007","series-title":"Proceedings of the ACM web conference 2022","first-page":"2768","article-title":"Recommendation unlearning","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.109632_bib0008","unstructured":"Chen, K., Wang, Z., Mi, B., Liu, W., Wang, S., Ren, X., & Shen, J. (2024). Machine unlearning in large language models. arXiv: 2404.16841."},{"key":"10.1016\/j.neunet.2026.109632_bib0009","series-title":"Proceedings of the 2022\u202fACM SIGSAC conference on computer and communications security","first-page":"499","article-title":"Graph unlearning","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2026.109632_bib0010","unstructured":"Chowdhury, S. B. R., Choromanski, K., Sehanobish, A., Dubey, A., & Chaturvedi, S. (2024). Towards scalable exact machine unlearning using parameter-efficient fine-tuning. arXiv: 2406.16257."},{"key":"10.1016\/j.neunet.2026.109632_bib0011","unstructured":"Fan, C., Liu, J., Zhang, Y., Wong, E., Wei, D., & Liu, S. (2023). Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation. arXiv: 2310.12508."},{"key":"10.1016\/j.neunet.2026.109632_bib0012","series-title":"29th USENIX security symposium (USENIX security 20)","first-page":"1605","article-title":"Local model poisoning attacks to {Byzantine-Robust} federated learning","author":"Fang","year":"2020"},{"issue":"120","key":"10.1016\/j.neunet.2026.109632_bib0013","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.109632_bib0014","series-title":"2004 Conference on computer vision and pattern recognition workshop","article-title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories","author":"Fei-Fei","year":"2004"},{"key":"10.1016\/j.neunet.2026.109632_bib0015","series-title":"2020 International symposium on reliable distributed systems (SRDS)","first-page":"91","article-title":"End-to-end evaluation of federated learning and split learning for internet of things","author":"Gao","year":"2020"},{"key":"10.1016\/j.neunet.2026.109632_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9304","article-title":"Eternal sunshine of the spotless net: Selective forgetting in deep networks","author":"Golatkar","year":"2020"},{"key":"10.1016\/j.neunet.2026.109632_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11516","article-title":"Amnesiac machine learning","volume":"vol. 35","author":"Graves","year":"2021"},{"key":"10.1016\/j.neunet.2026.109632_bib0018","doi-asserted-by":"crossref","unstructured":"Gu, H., Zhu, G., Zhang, J., Zhao, X., Han, Y., Fan, L., & Yang, Q. (2024). Unlearning during learning: An efficient federated machine unlearning method. arXiv: 2405.15474.","DOI":"10.24963\/ijcai.2024\/446"},{"key":"10.1016\/j.neunet.2026.109632_bib0019","doi-asserted-by":"crossref","first-page":"47230","DOI":"10.1109\/ACCESS.2019.2909068","article-title":"Badnets: Evaluating backdooring attacks on deep neural networks","volume":"7","author":"Gu","year":"2019","journal-title":"Ieee Access"},{"key":"10.1016\/j.neunet.2026.109632_bib0020","unstructured":"Guo, C., Goldstein, T., Hannun, A., & Van Der Maaten, L. (2019). Certified data removal from machine learning models. arXiv: 1911.03030."},{"key":"10.1016\/j.neunet.2026.109632_bib0021","unstructured":"Halimi, A., Kadhe, S., Rawat, A., & Baracaldo, N. (2022). Federated unlearning: How to efficiently erase a client in fl?arXiv: 2207.05521."},{"key":"10.1016\/j.neunet.2026.109632_bib0022","unstructured":"Hsu, T.-M. H., Qi, H., & Brown, M. (2019). Measuring the effects of non-identical data distribution for federated visual classification. arXiv: 1909.06335."},{"issue":"2","key":"10.1016\/j.neunet.2026.109632_bib0023","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.neunet.2026.109632_bib0024","series-title":"International conference on artificial intelligence and statistics","first-page":"2008","article-title":"Approximate data deletion from machine learning models","author":"Izzo","year":"2021"},{"key":"10.1016\/j.neunet.2026.109632_bib0025","unstructured":"Krizhevsky, A. (2009). Learning multiple layers of features from tiny images. Technical report, University of Toronto."},{"key":"10.1016\/j.neunet.2026.109632_bib0026","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"227","article-title":"Fast-NTK: Parameter-efficient unlearning for large-scale models","author":"Li","year":"2024"},{"issue":"1","key":"10.1016\/j.neunet.2026.109632_bib0027","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/1097198X.2019.1569186","article-title":"The impact of GDPR on global technology development","volume":"22","author":"Li","year":"2019","journal-title":"Journal of Global Information Technology Management"},{"key":"10.1016\/j.neunet.2026.109632_bib0028","unstructured":"Liu, G., Ma, X., Yang, Y., Wang, C., & Liu, J. (2020). Federated unlearning. arXiv: 2012.13891."},{"key":"10.1016\/j.neunet.2026.109632_bib0029","series-title":"2021\u202fIEEE\/ACM 29th international symposium on quality of service (IWQOS)","first-page":"1","article-title":"Federaser: Enabling efficient client-level data removal from federated learning models","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109632_bib0030","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1038\/s42256-025-00985-0","article-title":"Rethinking machine unlearning for large language models","volume":"7","author":"Liu","year":"2025","journal-title":"Nature Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109632_bib0031","series-title":"IEEE infocom 2022-IEEE conference on computer communications","first-page":"1749","article-title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining","author":"Liu","year":"2022"},{"issue":"1","key":"10.1016\/j.neunet.2026.109632_bib0032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3679014","article-title":"A survey on federated unlearning: Challenges, methods, and future directions","volume":"57","author":"Liu","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.109632_bib0033","series-title":"Artificial intelligence and statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.neunet.2026.109632_bib0034","unstructured":"Nguyen, T. T., Huynh, T. T., Ren, Z., Nguyen, P. L., Liew, A. W.-C., Yin, H., & Nguyen, Q. V. H. (2022). A survey of machine unlearning. arXiv: 2209.02299."},{"key":"10.1016\/j.neunet.2026.109632_bib0035","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2026.109632_bib0036","series-title":"11th USENIX workshop on hot topics in cloud computing (hotcloud 19)","article-title":"The seven sins of {Personal-Data} processing systems under {GDPR}","author":"Shastri","year":"2019"},{"key":"10.1016\/j.neunet.2026.109632_bib0037","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":"10.1016\/j.neunet.2026.109632_bib0038","series-title":"NDSS","article-title":"Manipulating the byzantine: Optimizing model poisoning attacks and defenses for federated learning","author":"Shejwalkar","year":"2021"},{"key":"10.1016\/j.neunet.2026.109632_bib0039","series-title":"2022\u202fIEEE symposium on security and privacy (SP)","first-page":"1354","article-title":"Back to the drawing board: A critical evaluation of poisoning attacks on production federated learning","author":"Shejwalkar","year":"2022"},{"issue":"9","key":"10.1016\/j.neunet.2026.109632_bib0040","doi-asserted-by":"crossref","first-page":"13046","DOI":"10.1109\/TNNLS.2023.3266233","article-title":"Fast yet effective machine unlearning","volume":"35","author":"Tarun","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109632_bib0041","unstructured":"Torkzadehmahani, R., Nasirigerdeh, R., Kaissis, G., Rueckert, D., Dziugaite, G. K., & Triantafillou, E. (2024). Improved localized machine unlearning through the lens of memorization. arXiv: 2412.02432."},{"key":"10.1016\/j.neunet.2026.109632_bib0042","series-title":"Proceedings of the ACM web conference 2022","first-page":"622","article-title":"Federated unlearning via class-discriminative pruning","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109632_bib0043","series-title":"Proceedings of the 2023\u202fACM Asia conference on computer and communications security","first-page":"567","article-title":"BFU: Bayesian federated unlearning with parameter self-sharing","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109632_bib0044","unstructured":"Warnecke, A., Pirch, L., Wressnegger, C., & Rieck, K. (2021). Machine unlearning of features and labels. arXiv: 2108.11577."},{"key":"10.1016\/j.neunet.2026.109632_bib0045","unstructured":"Wu, C., Zhu, S., & Mitra, P. (2022a). Federated unlearning with knowledge distillation. arXiv: 2201.09441."},{"issue":"5","key":"10.1016\/j.neunet.2026.109632_bib0046","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/MNET.001.2200198","article-title":"Federated unlearning: Guarantee the right of clients to forget","volume":"36","author":"Wu","year":"2022","journal-title":"IEEE Network"},{"key":"10.1016\/j.neunet.2026.109632_bib0047","series-title":"International conference on learning representations","article-title":"DBA: Distributed backdoor attacks against federated learning","author":"Xie","year":"2019"},{"key":"10.1016\/j.neunet.2026.109632_bib0048","series-title":"2023\u202fIEEE international conference on data mining (ICDM)","first-page":"1439","article-title":"Exact-fun: An exact and efficient federated unlearning approach","author":"Xiong","year":"2023"},{"key":"10.1016\/j.neunet.2026.109632_bib0049","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"237","article-title":"Machine unlearning for image retrieval: A generative scrubbing approach","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109632_bib0050","series-title":"Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"2545","article-title":"Fldetector: Defending federated learning against model poisoning attacks via detecting malicious clients","author":"Zhang","year":"2022"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026010889?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026010889?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T17:45:35Z","timestamp":1792518335000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026010889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":50,"alternative-id":["S0893608026010889"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109632","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CALM: Fine-grained federated unlearning via CLIP-assisted LoRA-MoE memory editing","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109632","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109632"}}