{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:28:46Z","timestamp":1775082526114,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584048","type":"print"},{"value":"9789819584055","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-8405-5_26","type":"book-chapter","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:15:14Z","timestamp":1775074514000},"page":"478-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HACompBench: Co-designed Multimodal DNN Compression Evaluation for\u00a0Edge Devices"],"prefix":"10.1007","author":[{"given":"Zhengyu","family":"Gan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haohua","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengquan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haisheng","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles, IEEE Trans. Mobile Comput. (2020)","DOI":"10.1109\/TMC.2020.2999956"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Chong, P., Ilin, A.I., Rehg, J.M.: Multimodal Deep Learning with Boosted Trees for Edge Inference, In: 2023 IEEE 23rd International Conference on Data Mining (ICDM), pp. 1\u201310 (2023)","DOI":"10.1109\/ICDMW60847.2023.00021"},{"issue":"4","key":"26_CR3","first-page":"1","volume":"6","author":"F Hohman","year":"2023","unstructured":"Hohman, F., Kery, M.B., Ren, D., Moritz, D.: Model Compression in Practice: lessons learned from practitioners creating on-device machine learning experiences, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 6(4), 1\u201319 (2023)","journal-title":"ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"26_CR4","unstructured":"Smith, J., Gupta, P., Johnson, M.: Hardware-aware compression with Random Operation Access Specific Tile (ROAST) hashing, In: Proceeding ICLR (2023)"},{"issue":"10","key":"26_CR5","first-page":"1","volume":"56","author":"PP Liang","year":"2024","unstructured":"Liang, P.P., Zadeh, A., Morency, L.-P.: Foundations & trends in multimodal machine learning: principles, challenges, and open questions. ACM Comput. Surv. 56(10), 1\u201336 (2024)","journal-title":"ACM Comput. Surv."},{"issue":"3","key":"26_CR6","first-page":"123","volume":"58","author":"S Lee","year":"2025","unstructured":"Lee, S., Kim, J., Park, H.: Edge deep learning in computer vision and medical diagnostics: a comprehensive survey. Artif. Intell. Rev. 58(3), 123\u2013145 (2025)","journal-title":"Artif. Intell. Rev."},{"key":"26_CR7","unstructured":"C. Banbury et al., MLPerf Tiny Benchmark, MLSys (2021)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: MCUNet: Tiny Deep Learning on IoT Devices, Nature (2020)","DOI":"10.1109\/IPCCC50635.2020.9391558"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Yuan, G., et al.: Mobile or FPGA? A Comprehensive evaluation on energy efficiency and a unified optimization framework, ACM Trans. Embed. Comput. Syst. (2022)","DOI":"10.1145\/3528578"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Tian, Y., et al.: Finding deviated behaviors of the compressed DNN models for image classifications, ACM Trans. Softw. Eng. Methodol. (2023)","DOI":"10.1145\/3583564"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Qi, P., et al.: Accelerating framework of transformer by hardware design and model compression co-optimization, ICCAD (2021)","DOI":"10.1109\/ICCAD51958.2021.9643586"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Ni, Y., et al.: Algorithm-Hardware co-design for efficient hyperdimensional learning on edge, DATE (2022)","DOI":"10.23919\/DATE54114.2022.9774524"},{"key":"26_CR13","unstructured":"Shi, W., et al.: Edge computing: state-of-the-art and future directions, J. Comput. Res. Dev. (2019)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Mohammed, T., et al.: Distributed inference acceleration with adaptive DNN partitioning and offloading, IEEE INFOCOM (2020)","DOI":"10.1109\/INFOCOM41043.2020.9155237"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Russo, E., et al.: DNN model compression for IoT Domain-specific hardware accelerators, IEEE IoT J. (2021)","DOI":"10.1109\/JIOT.2021.3111723"},{"key":"26_CR16","volume-title":"Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey","author":"L Deng","year":"2020","unstructured":"Deng, L., et al.: Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey. IEEE, Proc (2020)"},{"key":"26_CR17","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210337","volume-title":"On-Demand Deep Model Compression for Mobile Devices","author":"S Liu","year":"2018","unstructured":"Liu, S., et al.: On-Demand Deep Model Compression for Mobile Devices. Proc, ACM MobiSys (2018)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Choudhary, T., et al.: A Comprehensive Survey on Model Compression and Acceleration, Artif. Intell. Rev. (2020)","DOI":"10.1007\/s10462-020-09816-7"},{"key":"26_CR19","unstructured":"Qualcomm, Snapdragon 888 Mobile HDK Product Brief (2020)"},{"key":"26_CR20","unstructured":"Qualcomm, Snapdragon 765G 5G Mobile Platform Brief (2020)"},{"key":"26_CR21","unstructured":"Reddi, V.J., et al.: MLPerf Inference Benchmark, In: 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA), IEEE (2020)"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"26_CR23","unstructured":"TensorFlow Model Optimization Toolkit, Pruning in Keras example (2023). https:\/\/www.tensorflow.org\/model_optimization\/guide\/pruning"},{"key":"26_CR24","unstructured":"Scikit-learn, KMeans clustering (2023). https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.cluster.KMeans.html"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Ramesh, K., et al.: A comparative study on the impact of model compression techniques on fairness in language models, In: Proceeding Annual Meeting Association Computing Linguistics, pp. 15762\u201315782 (2023)","DOI":"10.18653\/v1\/2023.acl-long.878"},{"issue":"9","key":"26_CR26","first-page":"5001","volume":"22","author":"L Wang","year":"2022","unstructured":"Wang, L., et al.: Accelerating decentralized federated learning in heterogeneous edge computing. IEEE Trans. Mobile Comput. 22(9), 5001\u20135016 (2022)","journal-title":"IEEE Trans. Mobile Comput."},{"issue":"1","key":"26_CR27","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1109\/TNNLS.2022.3172941","volume":"35","author":"Z Wang","year":"2022","unstructured":"Wang, Z., et al.: EDCompress: energy-aware model compression for dataflows. IEEE Trans. Neural Netw. Learn. Syst. 35(1), 208\u2013220 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"26_CR28","unstructured":"Luo, C., et al.: Comparison and benchmarking of AI models and frameworks on mobile devices, arXiv preprint arXiv:2005.05085 (2020)"},{"issue":"3","key":"26_CR29","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/MCI.2021.3084393","volume":"16","author":"Z Wang","year":"2021","unstructured":"Wang, Z., et al.: Evolutionary multi-objective model compression for deep neural networks. IEEE Comput. Intell. Mag. 16(3), 10\u201321 (2021)","journal-title":"IEEE Comput. Intell. Mag."},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Z., Tan, H.: Towards efficient inference on mobile device via pruning (2024). In: 10th International Conference on Big Data Computing and Communications (BigCom), IEEE, 2024","DOI":"10.1109\/BIGCOM65357.2024.00013"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: TinyBERT: Distilling BERT for Natural Language Understanding, arXiv preprint arXiv:1909.10351 (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"26_CR32","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"Baevski, A., et al.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural. Inf. Process. Syst. 33, 12449\u201312460 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR33","unstructured":"Cheng, Y., et al.: A survey of model compression and acceleration for deep neural networks, arXiv preprint arXiv:1710.09282 (2017)"},{"key":"26_CR34","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., et al.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $$<0.5$$ MB model size, arXiv preprint arXiv:1602.07360 (2016)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8405-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:15:17Z","timestamp":1775074517000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8405-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584048","9789819584055"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8405-5_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}