{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:05Z","timestamp":1750220165328,"version":"3.41.0"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2022,12,24]],"date-time":"2022-12-24T00:00:00Z","timestamp":1671840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2023,3,31]]},"abstract":"<jats:p>Supervised machine learning requires large amounts of labeled data for training. In power, performance, and area (PPA) estimation of embedded memories, every new memory compiler version is considered independently of previous compiler versions. Since the data of different memory compilers originate from similar domains, transfer learning may reduce the amount of supervised data required by pre-training PPA estimation neural networks on related domains. We show that provisioning times of PPA models for new compiler versions can be reduced significantly by exploiting similarities among different compilers, versions, and technology nodes. Through transfer learning, we shorten the time to provision PPA models for new compiler versions, which speeds up time-critical periods of the design cycle. Using only 901 training samples (10%) is sufficient to achieve an almost worst-case (98th percentile) estimation error of 2.67% and allows us to shorten model provisioning times from 40 days to less than one week without sacrificing accuracy. To enable a diverse set of source domains for transfer learning, we devise a new, application-independent method for overcoming structural domain differences through domain equalization that attains competitive results when compared to domain-free transfer. A high degree of automation necessitates the efficient assessment of the best source domains. We propose using various metrics to accurately identify four of the five best among 45 datasets with low computational effort.<\/jats:p>","DOI":"10.1145\/3556539","type":"journal-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T11:28:56Z","timestamp":1660303736000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Training PPA Models for Embedded Memories on a Low-data Diet"],"prefix":"10.1145","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4852-4500","authenticated-orcid":false,"given":"Felix","family":"Last","sequence":"first","affiliation":[{"name":"Technical University of Munich, Munich, Germany and Intel Deutschland GmbH, Neubiberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4431-7619","authenticated-orcid":false,"given":"Ulf","family":"Schlichtmann","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,12,24]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1080\/713827181"},{"key":"e_1_3_2_3_2","volume-title":"On the Opportunities and Risks of Foundation Models","author":"Bommasani Rishi","year":"2021","unstructured":"Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, et\u00a0al. 2021. On the Opportunities and Risks of Foundation Models. Technical Report. arXiv:2108.07258."},{"key":"e_1_3_2_4_2","volume-title":"Advances in Neural Information Processing Systems","author":"Caruana Rich","year":"2001","unstructured":"Rich Caruana, Steve Lawrence, and C. Lee Giles. 2001. Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping. In Advances in Neural Information Processing Systems, 402\u2013408."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252544"},{"key":"e_1_3_2_6_2","article-title":"Translated learning: Transfer learning across different feature spaces","volume":"21","author":"Dai Wenyuan","year":"2008","unstructured":"Wenyuan Dai, Yuqiang Chen, Gui-Rong Xue, Qiang Yang, and Yong Yu. 2008. Translated learning: Transfer learning across different feature spaces. In Advances in Neural Information Processing Systems, Vol. 21, Curran Associates, Inc., Red Hooks, NY, USA.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2618765"},{"key":"e_1_3_2_8_2","volume-title":"Proceedings of the 13th AISTATS Conference","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th AISTATS Conference. JMLR Workshop and Conference Proceedings, 249\u2013256."},{"key":"e_1_3_2_9_2","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS\u201914)","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS\u201914), arXiv.1406.2661."},{"issue":"2","key":"e_1_3_2_10_2","article-title":"Comparison of values of Pearson\u2019s and Spearman\u2019s correlation coefficients on the same sets of data","volume":"30","author":"Hauke Jan","year":"2011","unstructured":"Jan Hauke and Tomasz Kossowski. 2011. Comparison of values of Pearson\u2019s and Spearman\u2019s correlation coefficients on the same sets of data. Quaest. Geogr. 30, 2 (2011), 87\u201393.","journal-title":"Quaest. Geogr."},{"key":"e_1_3_2_11_2","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In Proceeding of the IEEE International Conference on Computer Vision (ICCV\u201915) 1026\u20131034."},{"issue":"5","key":"e_1_3_2_12_2","article-title":"Machine learning for electronic design automation: A survey","volume":"26","author":"Huang Guyue","year":"2021","unstructured":"Guyue Huang, Jingbo Hu, Yifan He, Jialong Liu, Mingyuan Ma, Zhaoyang Shen, Juejian Wu, Yuanfan Xu, Hengrui Zhang, Kai Zhong, Xuefei Ning, Yuzhe Ma, Haoyu Yang, Bei Yu, Huazhong Yang, and Yu Wang. 2021. Machine learning for electronic design automation: A survey. ACM Trans. Des. Autom. Electr. Syst. 26, 5 (June2021), 40:1\u201340:46.","journal-title":"ACM Trans. Des. Autom. Electr. Syst."},{"key":"e_1_3_2_13_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980v9."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Jihye Kwon and Luca P. Carloni. 2020. Transfer learning for design-space exploration with high-level synthesis. In Proceedings of the ACM\/IEEE Workshop on Machine Learning for CAD (MLCAD\u201920). ACM New York NY 163\u2013168.","DOI":"10.1145\/3380446.3430636"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.23919\/IFIPNetworking52078.2021.9472818"},{"issue":"5","key":"e_1_3_2_17_2","article-title":"Predicting memory compiler performance outputs using feed-forward neural networks","volume":"25","author":"Last Felix","year":"2020","unstructured":"Felix Last, Max Haeberlein, and Ulf Schlichtmann. 2020. Predicting memory compiler performance outputs using feed-forward neural networks. ACM Trans. Des. Autom. Electr. Syst. 25, 5 (July2020), 39:1\u201339:19.","journal-title":"ACM Trans. Des. Autom. Electr. Syst."},{"key":"e_1_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Felix Last and Ulf Schlichtmann. 2020. Partial sharing neural networks for multi-target regression on power and performance of embedded memories. InProceedings of the ACM\/IEEE Workshop on Machine Learning for CAD (MLCAD\u201920). ACM New York NY 123\u2013128.","DOI":"10.1145\/3380446.3430642"},{"key":"e_1_3_2_19_2","article-title":"Transfer learning using computational intelligence: A survey","volume":"80","author":"Lu Jie","year":"2015","unstructured":"Jie Lu, Vahid Behbood, Peng Hao, Hua Zuo, Shan Xue, and Guangquan Zhang. 2015. Transfer learning using computational intelligence: A survey. Knowl.-Bas. Syst. 80 (May2015), 4\u201323.","journal-title":"Knowl.-Bas. Syst."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3287624.3288756"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413270"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1002\/2017SW001669"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/e19020047"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1142\/S012906571950014X"},{"key":"e_1_3_2_27_2","unstructured":"Marcel Simon Erik Rodner and Joachim Denzler. 2016. Imagenet pre-trained models with batch normalization. arXiv:1612.01452."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS\u201996)","volume":"8","author":"Thrun Sebastian","year":"1996","unstructured":"Sebastian Thrun. 1996. Is learning the n-th thing any easier than learning the first? In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS\u201996), Vol. 8. MIT Press."},{"key":"e_1_3_2_30_2","volume-title":"A Better Measure of Relative Prediction Accuracy for Model Selection and Model Estimation","author":"Tofallis Chris","year":"2014","unstructured":"Chris Tofallis. 2014. A Better Measure of Relative Prediction Accuracy for Model Selection and Model Estimation. SSRN Scholarly Paper ID 2635088. Social Science Research Network, Rochester, NY."},{"key":"e_1_3_2_31_2","volume-title":"Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques","author":"Torrey Lisa","year":"2010","unstructured":"Lisa Torrey and Jude Shavlik. 2010. Transfer learning. In Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques. IGI Global, 242\u2013264."},{"key":"e_1_3_2_32_2","volume-title":"Automated Machine Learning: Methods, Systems, Challenges","author":"Vanschoren Joaquin","year":"2019","unstructured":"Joaquin Vanschoren. 2019. Meta-learning. In Automated Machine Learning: Methods, Systems, Challenges. Springer International Publishing, Cham, 35\u201361."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Zirui Wang Zihang Dai Barnabas Poczos and Jaime Carbonell. 2019. Characterizing and avoiding negative transfer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 11293\u201311302.","DOI":"10.1109\/CVPR.2019.01155"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2021.108095"},{"key":"e_1_3_2_36_2","article-title":"A novel transfer learning framework for time series forecasting","volume":"156","author":"Ye Rui","year":"2018","unstructured":"Rui Ye and Qun Dai. 2018. A novel transfer learning framework for time series forecasting. Knowl.-Bas. Syst. 156 (Sept.2018), 74\u201399.","journal-title":"Knowl.-Bas. Syst."},{"key":"e_1_3_2_37_2","unstructured":"Cunxi Yu and Wang Zhou. 2020. Decision making in synthesis cross technologies using LSTMs and transfer learning. In Proceedings of the ACM\/IEEE Workshop on Machine Learning for CAD (MLCAD\u201920). ACM New York NY 55\u201360."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3556539","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3556539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:32Z","timestamp":1750186832000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3556539"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,24]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,3,31]]}},"alternative-id":["10.1145\/3556539"],"URL":"https:\/\/doi.org\/10.1145\/3556539","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"type":"print","value":"1084-4309"},{"type":"electronic","value":"1557-7309"}],"subject":[],"published":{"date-parts":[[2022,12,24]]},"assertion":[{"value":"2022-03-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-15","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}