{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T22:00:56Z","timestamp":1772834456320,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543830","type":"print"},{"value":"9789819543847","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-4384-7_6","type":"book-chapter","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T15:42:45Z","timestamp":1762357365000},"page":"69-83","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Parameter-Efficient Fine-Tuning Based on Decomposed Convolutional Kernel in Mixture-of-Experts Architecture"],"prefix":"10.1007","author":[{"given":"Hewei","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,6]]},"reference":[{"key":"6_CR1","unstructured":"Cohen, N., Sharir, O., Shashua, A.: On the expressive power of deep learning: a tensor analysis. In: Conference on Learning Theory, pp. 698\u2013728. PMLR (2016)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. (2020)"},{"key":"6_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Others: language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR5","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774. (2023)"},{"key":"6_CR6","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971. (2023)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Dai, D., et al.: Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066. (2024)","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"6_CR8","unstructured":"Xu, Y., et al.: Qa-lora: quantization-aware low-rank adaptation of large language models. arXiv preprint arXiv:2309.14717. (2023)"},{"key":"6_CR9","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Others: Lora: low-rank adaptation of large language models. ICLR. 1, 3 (2022)","journal-title":"ICLR."},{"key":"6_CR10","unstructured":"Chen, W., Miao, Z., Qiu, Q.: Large convolutional model tuning via filter subspace. In: International Conference on Learning Representations (2025)"},{"key":"6_CR11","first-page":"85","volume":"30","author":"IJ Brown","year":"2009","unstructured":"Brown, I.J.: A wavelet tour of signal processing: the sparse way. Investigacion Operacional. 30, 85\u201387 (2009)","journal-title":"Investigacion Operacional."},{"key":"6_CR12","doi-asserted-by":"publisher","first-page":"5017","DOI":"10.1109\/TIP.2015.2475625","volume":"24","author":"T-H Chan","year":"2015","unstructured":"Chan, T.-H., Jia, K., Gao, S., Lu, J., Zeng, Z., Ma, Y.: PCANet: a simple deep learning baseline for image classification? IEEE Trans. Image Process. 24, 5017\u20135032 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR13","doi-asserted-by":"publisher","first-page":"4311","DOI":"10.1109\/TSP.2006.881199","volume":"54","author":"M Aharon","year":"2006","unstructured":"Aharon, M., Elad, M., Bruckstein, A.: K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54, 4311\u20134322 (2006)","journal-title":"IEEE Trans. Signal Process."},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1109\/34.93808","volume":"13","author":"WT Freeman","year":"1991","unstructured":"Freeman, W.T., Adelson, E.H.: Others: The design and use of steerable filters. IEEE Trans. Pattern Anal. Mach. Intell. 13, 891\u2013906 (1991)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR15","doi-asserted-by":"publisher","first-page":"1553","DOI":"10.1109\/TSP.2009.2036477","volume":"58","author":"R Rubinstein","year":"2009","unstructured":"Rubinstein, R., Zibulevsky, M., Elad, M.: Double sparsity: learning sparse dictionaries for sparse signal approximation. IEEE Trans. Signal Process. 58, 1553\u20131564 (2009)","journal-title":"IEEE Trans. Signal Process."},{"key":"6_CR16","unstructured":"Qiu, Q., Cheng, X., Sapiro, G., et al: DCFNet: deep neural network with decomposed convolutional filters. In: International Conference on Machine Learning, pp. 4198\u20134207. PMLR (2018)"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Z., Miao, Z., Hu, J., Qiu, Q.: Adaptive convolutions with per-pixel dynamic filter atom. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12302\u201312311 (2021)","DOI":"10.1109\/ICCV48922.2021.01208"},{"key":"6_CR18","unstructured":"Miao, Z., Wang, Z., Chen, W., Qiu, Q.: Continual learning with filter atom swapping. In: International Conference on Learning Representations (2021)"},{"key":"6_CR19","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3, 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"6_CR20","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1162\/neco.1994.6.2.181","volume":"6","author":"MI Jordan","year":"1994","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. Neural Comput. 6, 181\u2013214 (1994)","journal-title":"Neural Comput."},{"key":"6_CR21","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1162\/089976602753633402","volume":"14","author":"R Collobert","year":"2002","unstructured":"Collobert, R., Bengio, S., Bengio, Y.: A parallel mixture of SVMs for very large scale problems. Neural Comput. 14, 1105\u20131114 (2002)","journal-title":"Neural Comput."},{"key":"6_CR22","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538. (2017)"},{"key":"6_CR23","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23, 1\u201339 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"6_CR24","unstructured":"Wang, X., et al.: Deep mixture of experts via shallow embedding. In: Uncertainty in Artificial Intelligence, pp. 552\u2013562. PMLR (2020)"},{"key":"6_CR25","first-page":"8583","volume":"34","author":"C Riquelme","year":"2021","unstructured":"Riquelme, C., et al.: Scaling vision with sparse mixture of experts. Adv. Neural. Inf. Process. Syst. 34, 8583\u20138595 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR26","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., Kamath, A., R\u00fcckl\u00e9, A., Cho, K., Gurevych, I.: AdapterFusion: non-destructive task composition for transfer learning. In: Merlo, P., Tiedemann, J., Tsarfaty, R. (eds.) Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 487\u2013503. Association for Computational Linguistics, Online (2021)","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"6_CR28","unstructured":"Edalati, A., Tahaei, M., Kobyzev, I., Nia, V.P., Clark, J.J., Rezagholizadeh, M.: Krona: parameter efficient tuning with kronecker adapter. arXiv preprint arXiv:2212.10650. (2022)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Chronopoulou, A., Peters, M.E., Fraser, A., Dodge, J.: Adaptersoup: Weight averaging to improve generalization of pretrained language models. arXiv preprint arXiv:2302.07027. (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.153"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Z.-R., Tan, C., Xu, H., Wang, C., Huang, J., Huang, S.: Towards adaptive prefix tuning for parameter-efficient language model fine-tuning. arXiv preprint arXiv:2305.15212. (2023)","DOI":"10.18653\/v1\/2023.acl-short.107"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691. (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Zhu, W., Tan, M.: SPT: Learning to selectively insert prompts for better prompt tuning. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 11862\u201311878 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.727"},{"key":"6_CR33","unstructured":"Krizhevsky, A., Hinton, G., et al: Learning multiple layers of features from tiny images (2009)"},{"key":"6_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Others: imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"6_CR35","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980. (2014)"},{"key":"6_CR36","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine LEARNING, pp. 448\u2013456. PMLR (2015)"},{"key":"6_CR37","doi-asserted-by":"publisher","first-page":"73995","DOI":"10.52202\/075280-3238","volume":"36","author":"W Chen","year":"2023","unstructured":"Chen, W., Miao, Z., Qiu, Q.: Inner product-based neural network similarity. Adv. Neural. Inf. Process. Syst. 36, 73995\u201374020 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR38","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vision 128, 336\u2013359 (2020)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4384-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T14:07:17Z","timestamp":1772806037000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4384-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,6]]},"ISBN":["9789819543830","9789819543847"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4384-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,6]]},"assertion":[{"value":"6 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}