{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:10:42Z","timestamp":1774717842953,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852172","type":"proceedings-article","created":{"date-parts":[[2019,9,30]],"date-time":"2019-09-30T23:44:32Z","timestamp":1569887072000},"page":"1-8","source":"Crossref","is-referenced-by-count":157,"title":["Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication"],"prefix":"10.1109","author":[{"given":"Felix","family":"Sattler","sequence":"first","affiliation":[{"name":"Dept. of Video Coding and Analytics, Fraunhofer HHI, Berlin, Germany"}]},{"given":"Simon","family":"Wiedemann","sequence":"additional","affiliation":[{"name":"Dept. of Video Coding and Analytics, Fraunhofer HHI, Berlin, Germany"}]},{"given":"Klaus-Robert","family":"Muller","sequence":"additional","affiliation":[{"name":"Machine Learning Group, TU Berlin, Berlin, Germany"}]},{"given":"Wojciech","family":"Samek","sequence":"additional","affiliation":[{"name":"Dept. of Video Coding and Analytics, Fraunhofer HHI, Berlin, Germany"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Compact and computationally efficient representation of deep neural networks","author":"wiedemann","year":"2018"},{"key":"ref38","article-title":"Robust and communication-efficient federated learning from non-iid data","author":"sattler","year":"2019"},{"key":"ref33","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2014"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref30","article-title":"The cifar-10 dataset","author":"krizhevsky","year":"2014"},{"key":"ref37","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref35","article-title":"Tying word vectors and word classifiers: A loss framework for language modeling","author":"inan","year":"2016"},{"key":"ref34","first-page":"313","article-title":"Building a large annotated corpus of english: The penn treebank","volume":"19","author":"marcus","year":"1993","journal-title":"Computational Linguistics"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1145\/2810103.2813687","article-title":"Privacy-preserving deep learning","author":"shokri","year":"2015","journal-title":"22nd ACM SIGSAC Conference on Computer and Communications Security"},{"key":"ref40","first-page":"39","article-title":"Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models","volume":"1","author":"samek","year":"2018","journal-title":"ITU Journal ICT Discoveries - Special Issue 1 - The Impact of Artificial Intelligence (AI) on Communication Networks and Services"},{"key":"ref11","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2016"},{"key":"ref12","article-title":"Scalable distributed dnn training using commodity gpu cloud computing","author":"strom","year":"2015","journal-title":"Annual Conference of the International Speech Communication Association"},{"key":"ref13","article-title":"Variance-based gradient compression for efficient distributed deep learning","author":"tsuzuku","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref15","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2017"},{"key":"ref16","first-page":"4452","article-title":"Sparsified sgd with memory","author":"stich","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"5977","article-title":"The convergence of sparsified gradient methods","author":"alistarh","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Federated learning: Strategies for improving communication efficiency","author":"konecn?y","year":"2016"},{"key":"ref19","article-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1966.1053907"},{"key":"ref3","article-title":"Sparknet: Training deep networks in spark","author":"moritz","year":"2015"},{"key":"ref6","first-page":"571","article-title":"Project adam: Building an efficient and scalable deep learning training system","volume":"14","author":"chilimbi","year":"2014","journal-title":"OSDI"},{"key":"ref29","article-title":"The mnist database of handwritten digits","author":"lecun","year":"1998"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref7","first-page":"2595","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"2010","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref2","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref9","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref1","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref20","article-title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns","author":"seide","year":"2014","journal-title":"Annual Conference of the International Speech Communication Association"},{"key":"ref22","first-page":"1707","article-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref21","article-title":"signsgd: compressed optimisation for non-convex problems","author":"bernstein","year":"2018"},{"key":"ref24","article-title":"signsgd with majority vote is communication efficient and byzantine fault tolerant","author":"bernstein","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08987-4"},{"key":"ref23","article-title":"Error feedback fixes signsgd and other gradient compression schemes","author":"karimireddy","year":"2019"},{"key":"ref26","author":"cormen","year":"2009","journal-title":"Introduction to Algorithms"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/978-3-642-35289-8_3","article-title":"Efficient backprop","author":"lecun","year":"2012","journal-title":"Neural Networks Tricks of the Trade"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","location":"Budapest, Hungary","start":{"date-parts":[[2019,7,14]]},"end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852172.pdf?arnumber=8852172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T17:51:27Z","timestamp":1658080287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852172","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}