{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T06:32:34Z","timestamp":1784615554057,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tvcg.2024.3456371","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:06:21Z","timestamp":1725995181000},"page":"809-819","source":"Crossref","is-referenced-by-count":12,"title":["Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments"],"prefix":"10.1109","volume":"31","author":[{"given":"Angie","family":"Boggust","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Venkatesh","family":"Sivaraman","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yannick","family":"Assogba","sequence":"additional","affiliation":[{"name":"Apple, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghao","family":"Ren","sequence":"additional","affiliation":[{"name":"Apple, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominik","family":"Moritz","sequence":"additional","affiliation":[{"name":"Apple, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-844X","authenticated-orcid":false,"given":"Fred","family":"Hohman","sequence":"additional","affiliation":[{"name":"Apple, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502102"},{"key":"ref2","article-title":"SiPPing neural networks: Sensitivity-informed provable pruning of neural networks","author":"Baykal","year":"2019","journal-title":"arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2307\/1269768"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511122"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581268"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref11","article-title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Frankle","year":"2019"},{"key":"ref12","first-page":"10323","article-title":"SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","volume":"202","author":"Frantar"},{"key":"ref13","volume-title":"Introducing github copilot: your ai pair programmer","author":"Friedman","year":"2022"},{"key":"ref14","article-title":"The State of Sparsity in Deep Neural Networks","author":"Gale","year":"2019","journal-title":"arXiv"},{"key":"ref15","article-title":"Campfire: Compressible, Regularization-Free, Structured Sparse Training for Hardware Accelerators","author":"Gamboa","year":"2020","journal-title":"arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref17","article-title":"Artificial intelligence","author":"Giattino","year":"2023","journal-title":"Our World in Data"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744199"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13972"},{"key":"ref20","article-title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Han","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2843369"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642109"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642628"},{"key":"ref26","article-title":"What Do Compressed Deep Neural Networks Forget?","author":"Hooker","year":"2019","journal-title":"arXiv"},{"key":"ref27","article-title":"Characterising Bias in Compressed Models","author":"Hooker","year":"2020","journal-title":"arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744718"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3470918"},{"key":"ref30","article-title":"Visualizing and Understanding Recurrent Networks","author":"Karpathy","year":"2015","journal-title":"arXiv"},{"key":"ref31","article-title":"SNIP: single-shot network pruning based on connection sensitivity","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Lee","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030461"},{"key":"ref33","first-page":"5958","article-title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","volume":"119","author":"Li"},{"key":"ref34","first-page":"93","article-title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Liebenwein","year":"2021"},{"key":"ref35","first-page":"12037","article-title":"Pareto Multi-Task Learning","volume":"32","author":"Lin","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref37","article-title":"Rethinking the Value of Network Pruning","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Liu","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2019.2919033"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450658"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00007","article-title":"Feature Visualization","author":"Olah","year":"2017","journal-title":"Distill"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030361"},{"key":"ref44","year":"2024","journal-title":"Hello gpt-4o"},{"key":"ref45","first-page":"8024","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref46","first-page":"140:1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1264"},{"key":"ref48","first-page":"8592","article-title":"Visualizing and Measuring the Geometry of BERT","volume":"32","author":"Reif","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref49","article-title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Renda","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580790"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"key":"ref52","article-title":"Automatically Tracking Metadata and Provenance of Machine Learning Experiments","volume-title":"Workshop on ML Systems at Advances in Neural Information Processing Systems (NIPS)","author":"Schelter","year":"2017"},{"key":"ref53","first-page":"13","article-title":"ViNNPruner: Visual Interactive Pruning for Deep Learning","volume-title":"Machine Learning Methods in Visualisation for Big Data (MLVis@EuroVis)","author":"Schlegel"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511137"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093546"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581482"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00577"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/int.22354"},{"key":"ref59","article-title":"Machine Learning Model Sizes and the Parameter Gap","author":"Villalobos","year":"2022","journal-title":"arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3357065"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377538"},{"key":"ref62","author":"Welsh","year":"2023","journal-title":"Data and Network Introspection Kit"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1073"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3165347"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref66","article-title":"Unified Visual Transformer Compression","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Yu","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-020-0191-7"},{"issue":"4","key":"ref68","first-page":"39","article-title":"Accelerating the Machine Learning Lifecycle with MLflow","volume":"41","author":"Zaharia","year":"2018","journal-title":"IEEE Data Engineering Bulletin"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref70","article-title":"To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression","author":"Zhu","year":"2017","journal-title":"arXiv"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/10766346\/10672545.pdf?arnumber=10672545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:37:41Z","timestamp":1732667861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10672545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":70,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2024.3456371","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}