{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:36:55Z","timestamp":1763203015863,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819682973","type":"print"},{"value":"9789819682980","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-8298-0_32","type":"book-chapter","created":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T18:22:15Z","timestamp":1749925335000},"page":"402-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TRAWL: Tensor Reduced and\u00a0Approximated Weights for\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Yiran","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Het","family":"Patel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawon","family":"Ahn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelos E.","family":"Papalexakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,15]]},"reference":[{"key":"32_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR2","doi-asserted-by":"publisher","unstructured":"De-Arteaga, M., et al.: Bias in bios: a case study of semantic representation bias in a high-stakes setting. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, pp. 120\u2013128. FAT* 2019, Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3287560.3287572","DOI":"10.1145\/3287560.3287572"},{"key":"32_CR3","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"32_CR4","first-page":"3","volume":"1","author":"EJ Hu","year":"2021","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. ICLR 1, 3 (2021)","journal-title":"ICLR"},{"key":"32_CR5","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models (2020)"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Kossaifi, J., Khanna, A., Lipton, Z., Furlanello, T., Anandkumar, A.: Tensor contraction layers for parsimonious deep nets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 26\u201332 (2017)","DOI":"10.1109\/CVPRW.2017.243"},{"issue":"26","key":"32_CR7","first-page":"1","volume":"20","author":"J Kossaifi","year":"2019","unstructured":"Kossaifi, J., Panagakis, Y., Anandkumar, A., Pantic, M.: Tensorly: Tensor learning in python. J. Mach. Learn. Res. (JMLR) 20(26), 1\u201316 (2019)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"32_CR8","unstructured":"Lebedev, V., Ganin, Y., Rakhuba, M., Oseledets, I., Lempitsky, V.: Speeding-up convolutional neural networks using fine-tuned CP-decomposition. arXiv preprint arXiv:1412.6553 (2014)"},{"key":"32_CR9","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized Bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"issue":"5","key":"32_CR10","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"IV Oseledets","year":"2011","unstructured":"Oseledets, I.V.: Tensor-train decomposition. SIAM J. Sci. Comput. 33(5), 2295\u20132317 (2011)","journal-title":"SIAM J. Sci. Comput."},{"key":"32_CR11","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training (2018)"},{"issue":"8","key":"32_CR12","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"32_CR13","unstructured":"Saha, R., Sagan, N., Srivastava, V., Goldsmith, A.J., Pilanci, M.: Compressing large language models using low rank and low precision decomposition. arXiv preprint arXiv:2405.18886 (2024)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Samsi, S., et al.: From words to watts: benchmarking the energy costs of large language model inference (2023)","DOI":"10.1109\/HPEC58863.2023.10363447"},{"key":"32_CR15","unstructured":"Sharma, P., Ash, J.T., Misra, D.: The truth is in there: Improving reasoning in language models with layer-selective rank reduction. arXiv preprint arXiv:2312.13558 (2023)"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Shiao, W., Papalexakis, E.E.: Frappe:fast rank approximation with explainable features for tensors. arXiv preprint arXiv:2206.09316 (2024)","DOI":"10.1007\/s10618-024-01071-6"},{"issue":"13","key":"32_CR17","doi-asserted-by":"publisher","first-page":"3551","DOI":"10.1109\/TSP.2017.2690524","volume":"65","author":"ND Sidiropoulos","year":"2017","unstructured":"Sidiropoulos, N.D., De Lathauwer, L., Fu, X., Huang, K., Papalexakis, E.E., Faloutsos, C.: Tensor decomposition for signal processing and machine learning. IEEE Trans. Signal Process. 65(13), 3551\u20133582 (2017)","journal-title":"IEEE Trans. Signal Process."},{"key":"32_CR18","unstructured":"Srivastava, A., et\u00a0al.: Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615 (2022)"},{"key":"32_CR19","unstructured":"Touvron, H., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"32_CR20","unstructured":"Wang, B., Komatsuzaki, A.: GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model, May 2021. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhou, J., Wong, N., Zhang, Z.: Loretta: Low-rank economic tensor-train adaptation for ultra-low-parameter fine-tuning of large language models. arXiv preprint arXiv:2402.11417 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.174"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Hotpotqa: A dataset for diverse, explainable multi-hop question answering (2018). https:\/\/arxiv.org\/abs\/1809.09600","DOI":"10.18653\/v1\/D18-1259"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Yu, H., Wu, J.: Compressing transformers: features are low-rank, but weights are not! In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 11007\u201311015 (2023)","DOI":"10.1609\/aaai.v37i9.26304"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, D., et al.: A green (ER) world for AI. In: 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 742\u2013750. IEEE (2022)","DOI":"10.1109\/IPDPSW55747.2022.00126"},{"key":"32_CR25","unstructured":"Zhao, Q., Zhou, G., Xie, S., Zhang, L., Cichocki, A.: Tensor ring decomposition. arXiv preprint arXiv:1606.05535 (2016)"}],"container-title":["Lecture Notes in Computer Science","Data Science: Foundations and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8298-0_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T18:22:23Z","timestamp":1749925343000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8298-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819682973","9789819682980"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8298-0_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}