{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:08:16Z","timestamp":1767262096890,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["450987171"],"award-info":[{"award-number":["450987171"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,5,8]]},"DOI":"10.1145\/3578356.3592595","type":"proceedings-article","created":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T19:44:37Z","timestamp":1683229477000},"page":"87-93","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Robust and Tiny Binary Neural Networks using Gradient-based Explainability Methods"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2066-646X","authenticated-orcid":false,"given":"Muhammad","family":"Sabih","sequence":"first","affiliation":[{"name":"Department of Computer Science, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4134-952X","authenticated-orcid":false,"given":"Mikail","family":"Yayla","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Technische Universit\u00e4t Dortmund, Dortmund, Germany"},{"name":"Lamarr Institute for Machine Learning and Artificial Intelligence, Dortmund, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3663-6484","authenticated-orcid":false,"given":"Frank","family":"Hannig","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6285-5862","authenticated-orcid":false,"given":"J\u00fcrgen","family":"Teich","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8114-9760","authenticated-orcid":false,"given":"Jian-Jia","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Technische Universit\u00e4t Dortmund, Dortmund, Germany"},{"name":"Lamarr Institute for Machine Learning and Artificial Intelligence, Dortmund, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,5,8]]},"reference":[{"key":"e_1_3_2_1_1_1","article-title":"Structured pruning of deep convolutional neural networks","volume":"13","author":"Anwar S.","unstructured":"Anwar , S. , Hwang , K. , and Sung , W . Structured pruning of deep convolutional neural networks . J. Emerg. Technol. Comput. Syst. 13 , 3 (feb 2017). Anwar, S., Hwang, K., and Sung, W. Structured pruning of deep convolutional neural networks. J. Emerg. Technol. Comput. Syst. 13, 3 (feb 2017).","journal-title":"J. Emerg. Technol. Comput. Syst."},{"key":"e_1_3_2_1_2_1","first-page":"1","article-title":"Random forests","volume":"45","author":"Breiman L","year":"2001","unstructured":"Breiman , L . Random forests . Machine Learning 45 , 1 ( 2001 ), 5--32. Breiman, L. Random forests. Machine Learning 45, 1 (2001), 5--32.","journal-title":"Machine Learning"},{"key":"e_1_3_2_1_3_1","first-page":"4619","volume-title":"Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (June","author":"Chen T.","year":"2021","unstructured":"Chen , T. , Zhang , Z. , Ouyang , X. , Liu , Z. , Shen , Z. , and Wang , Z . \" bnn - bn = ?\": Training binary neural networks without batch normalization . In Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (June 2021 ), pp. 4619 -- 4629 . Chen, T., Zhang, Z., Ouyang, X., Liu, Z., Shen, Z., and Wang, Z. \"bnn - bn = ?\": Training binary neural networks without batch normalization. In Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (June 2021), pp. 4619--4629."},{"key":"e_1_3_2_1_4_1","first-page":"307","volume-title":"Approximate Computing Techniques for Deep Neural Networks","author":"Choi J.","year":"2019","unstructured":"Choi , J. , and Venkataramani , S . Approximate Computing Techniques for Deep Neural Networks . Springer , 2019 , pp. 307 -- 329 . Choi, J., and Venkataramani, S. Approximate Computing Techniques for Deep Neural Networks. Springer, 2019, pp. 307--329."},{"key":"e_1_3_2_1_5_1","volume-title":"How important is a neuron? CoRR","author":"Dhamdhere K.","year":"2018","unstructured":"Dhamdhere , K. , Sundararajan , M. , and Yan , Q . How important is a neuron? CoRR ( 2018 ). Dhamdhere, K., Sundararajan, M., and Yan, Q. How important is a neuron? CoRR (2018)."},{"key":"e_1_3_2_1_6_1","first-page":"243","volume-title":"Annual International Symposium on Computer Architecture (ISCA)","author":"Han S.","year":"2016","unstructured":"Han , S. , Liu , X. , Mao , H. , Pu , J. , Pedram , A. , Horowitz , M. A. , and Dally , W. J . Eie: Efficient inference engine on compressed deep neural network . In Annual International Symposium on Computer Architecture (ISCA) ( 2016 ), IEEE, pp. 243 -- 254 . Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., and Dally, W. J. Eie: Efficient inference engine on compressed deep neural network. In Annual International Symposium on Computer Architecture (ISCA) (2016), IEEE, pp. 243--254."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/978-3-031-15074-6_18","volume-title":"Proc. of the International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation","volume":"13511","author":"Heidorn C.","year":"2022","unstructured":"Heidorn , C. , Meyerh\u00f6fer , N. , Schinabeck , C. , Hannig , F. , and Teich , J . Hardware-aware evolutionary filter pruning . In Proc. of the International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation ( 2022 ), vol. 13511 of LNCS, Springer , pp. 283 -- 299 . Heidorn, C., Meyerh\u00f6fer, N., Schinabeck, C., Hannig, F., and Teich, J. Hardware-aware evolutionary filter pruning. In Proc. of the International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (2022), vol. 13511 of LNCS, Springer, pp. 283--299."},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. of the International Conference on Artificial Intelligence Circuits and Systems","author":"Hirtzlin T.","year":"2019","unstructured":"Hirtzlin , T. , Bocqet , M. , Klein , J. , Nowak , E. , Vianello , E. , Portal , J. M. , and Querlioz , D . Outstanding bit error tolerance of resistive RAM-based binarized neural networks . In Proc. of the International Conference on Artificial Intelligence Circuits and Systems ( 2019 ). Hirtzlin, T., Bocqet, M., Klein, J., Nowak, E., Vianello, E., Portal, J. M., and Querlioz, D. Outstanding bit error tolerance of resistive RAM-based binarized neural networks. In Proc. of the International Conference on Artificial Intelligence Circuits and Systems (2019)."},{"key":"e_1_3_2_1_9_1","first-page":"4107","volume-title":"Proc. of the Conference on Advances in Neural Information Processing Systems","author":"Hubara I.","year":"2016","unstructured":"Hubara , I. , Courbariaux , M. , Soudry , D. , El-Yaniv , R. , and Bengio , Y . Binarized neural networks . In Proc. of the Conference on Advances in Neural Information Processing Systems ( 2016 ), pp. 4107 -- 4115 . Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., and Bengio, Y. Binarized neural networks. In Proc. of the Conference on Advances in Neural Information Processing Systems (2016), pp. 4107--4115."},{"key":"e_1_3_2_1_10_1","first-page":"166","volume-title":"International Symposium on Microarchitecture","author":"Koppula S.","year":"2019","unstructured":"Koppula , S. , Orosa , L. , Ya\u011flik\u00e7i , A. G. , Azizi , R. , Shahroodi , T. , Kanellopoulos , K. , and Mutlu , O . Eden: Enabling energy-efficient, high-performance deep neural network inference using approximate DRAM . In International Symposium on Microarchitecture ( 2019 ), pp. 166 -- 181 . Koppula, S., Orosa, L., Ya\u011flik\u00e7i, A. G., Azizi, R., Shahroodi, T., Kanellopoulos, K., and Mutlu, O. Eden: Enabling energy-efficient, high-performance deep neural network inference using approximate DRAM. In International Symposium on Microarchitecture (2019), pp. 166--181."},{"volume-title":"Cifar10","author":"Krizhevsky A.","key":"e_1_3_2_1_11_1","unstructured":"Krizhevsky , A. , Nair , V. , and Hinton , G . Cifar10 . Krizhevsky, A., Nair, V., and Hinton, G. Cifar10."},{"key":"e_1_3_2_1_12_1","first-page":"598","volume-title":"Proc. of the Conference on Advances in Neural Information Processing Systems","author":"LeCun Y.","year":"1989","unstructured":"LeCun , Y. , Denker , J. , and Solla , S . Optimal brain damage . In Proc. of the Conference on Advances in Neural Information Processing Systems ( 1989 ), pp. 598 -- 605 . LeCun, Y., Denker, J., and Solla, S. Optimal brain damage. In Proc. of the Conference on Advances in Neural Information Processing Systems (1989), pp. 598--605."},{"key":"e_1_3_2_1_13_1","first-page":"306","volume-title":"Proc. of the International Symposium on Quality Electronic Design","author":"Li Y.","year":"2020","unstructured":"Li , Y. , and Ren , F . Bnn pruning: Pruning binary neural network guided by weight flipping frequency . In Proc. of the International Symposium on Quality Electronic Design ( 2020 ), pp. 306 -- 311 . Li, Y., and Ren, F. Bnn pruning: Pruning binary neural network guided by weight flipping frequency. In Proc. of the International Symposium on Quality Electronic Design (2020), pp. 306--311."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning","author":"Liu Z.","year":"2021","unstructured":"Liu , Z. , Shen , Z. , Li , S. , Helwegen , K. , Huang , D. , and Cheng , K . -T. How do Adam and training strategies help BNNs optimization? In International Conference on Machine Learning ( 2021 ). Liu, Z., Shen, Z., Li, S., Helwegen, K., Huang, D., and Cheng, K.-T. How do Adam and training strategies help BNNs optimization? In International Conference on Machine Learning (2021)."},{"key":"e_1_3_2_1_15_1","volume-title":"Non-structured dnn weight pruning-is it beneficial in any platform? IEEE Trans. on Neural Networks","author":"Ma X.","year":"2021","unstructured":"Ma , X. , Lin , S. , Ye , S. , He , Z. , Zhang , L. , Yuan , G. , Tan , S. , Li , Z. , Fan , D. , Qian , X. , Lin , X. , Ma , K. , and Wang , Y . Non-structured dnn weight pruning-is it beneficial in any platform? IEEE Trans. on Neural Networks ( 2021 ). Ma, X., Lin, S., Ye, S., He, Z., Zhang, L., Yuan, G., Tan, S., Li, Z., Fan, D., Qian, X., Lin, X., Ma, K., and Wang, Y. Non-structured dnn weight pruning-is it beneficial in any platform? IEEE Trans. on Neural Networks (2021)."},{"key":"e_1_3_2_1_16_1","first-page":"193","volume-title":"-R. Layer-Wise Relevance Propagation: An Overview","author":"Montavon G.","year":"2019","unstructured":"Montavon , G. , Binder , A. , Lapuschkin , S. , Samek , W. , and M\u00fcller , K . -R. Layer-Wise Relevance Propagation: An Overview . Springer , 2019 , pp. 193 -- 209 . Montavon, G., Binder, A., Lapuschkin, S., Samek, W., and M\u00fcller, K.-R. Layer-Wise Relevance Propagation: An Overview. Springer, 2019, pp. 193--209."},{"key":"e_1_3_2_1_17_1","unstructured":"Nagel M. Fournarakis M. Amjad R. A. Bondarenko Y. van Baalen M. and Blankevoort T. A white paper on neural network quantization. CoRR. -  Nagel M. Fournarakis M. Amjad R. A. Bondarenko Y. van Baalen M. and Blankevoort T. A white paper on neural network quantization. CoRR. -"},{"key":"e_1_3_2_1_18_1","unstructured":"Sabih M. Hannig F. and Teich J. Utilizing explainable AI for quantization and pruning of deep neural networks. CoRR.  Sabih M. Hannig F. and Teich J. Utilizing explainable AI for quantization and pruning of deep neural networks. CoRR."},{"key":"e_1_3_2_1_19_1","first-page":"166","volume-title":"Proc. of the Workshop on Dependable and Secure Machine Learning","author":"Sabih M.","year":"2021","unstructured":"Sabih , M. , Hannig , F. , and Teich , J . Fault-tolerant low-precision DNNs using explainable AI . In Proc. of the Workshop on Dependable and Secure Machine Learning ( 2021 ), IEEE, pp. 166 -- 174 . Sabih, M., Hannig, F., and Teich, J. Fault-tolerant low-precision DNNs using explainable AI. In Proc. of the Workshop on Dependable and Secure Machine Learning (2021), IEEE, pp. 166--174."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1145\/3517207.3526982","volume-title":"Proc. of the 2nd European Workshop on Machine Learning and Systems (EuroMLSys)","author":"Sabih M.","year":"2022","unstructured":"Sabih , M. , Hannig , F. , and Teich , J . Dyfip: Explainable ai-based dynamic filter pruning of convolutional neural networks . In Proc. of the 2nd European Workshop on Machine Learning and Systems (EuroMLSys) ( 2022 ), ACM, pp. 109 -- 115 . Sabih, M., Hannig, F., and Teich, J. Dyfip: Explainable ai-based dynamic filter pruning of convolutional neural networks. In Proc. of the 2nd European Workshop on Machine Learning and Systems (EuroMLSys) (2022), ACM, pp. 109--115."},{"key":"e_1_3_2_1_21_1","volume-title":"How does batch normalization help binary training? arXiv:1909.09139","author":"Sari E.","year":"2019","unstructured":"Sari , E. , Belbahri , M. , and Nia , V. P . How does batch normalization help binary training? arXiv:1909.09139 ( 2019 ). Sari, E., Belbahri, M., and Nia, V. P. How does batch normalization help binary training? arXiv:1909.09139 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"Learning important features through propagating activation differences. CoRR","author":"Shrikumar A.","year":"2017","unstructured":"Shrikumar , A. , Greenside , P. , and Kundaje , A . Learning important features through propagating activation differences. CoRR ( 2017 ). Shrikumar, A., Greenside, P., and Kundaje, A. Learning important features through propagating activation differences. CoRR (2017)."},{"key":"e_1_3_2_1_23_1","first-page":"5","volume-title":"Machine Learning","author":"Statistics L. B.","year":"2001","unstructured":"Statistics , L. B. , and Breiman , L . Random forests . In Machine Learning ( 2001 ), pp. 5 -- 32 . Statistics, L. B., and Breiman, L. Random forests. In Machine Learning (2001), pp. 5--32."},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. of Machine Learning and Systems (MLSys)","author":"Stutz D.","year":"2021","unstructured":"Stutz , D. , Chandramoorthy , N. , Hein , M. , and Schiele , B . Bit error robustness for energy-efficient DNN accelerators . In Proc. of Machine Learning and Systems (MLSys) ( 2021 ), mlsys.org. Stutz, D., Chandramoorthy, N., Hein, M., and Schiele, B. Bit error robustness for energy-efficient DNN accelerators. In Proc. of Machine Learning and Systems (MLSys) (2021), mlsys.org."},{"key":"e_1_3_2_1_25_1","volume-title":"Axiomatic attribution for deep networks. CoRR","author":"Sundararajan M.","year":"2017","unstructured":"Sundararajan , M. , Taly , A. , and Yan , Q . Axiomatic attribution for deep networks. CoRR ( 2017 ). Sundararajan, M., Taly, A., and Yan, Q. Axiomatic attribution for deep networks. CoRR (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"A survey on explainable artificial intelligence (XAI): Towards medical XAI. CoRR","author":"Tjoa E.","year":"2019","unstructured":"Tjoa , E. , and Guan , C . A survey on explainable artificial intelligence (XAI): Towards medical XAI. CoRR ( 2019 ). Tjoa, E., and Guan, C. A survey on explainable artificial intelligence (XAI): Towards medical XAI. CoRR (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","first-page":"63280","DOI":"10.1109\/ACCESS.2022.3182659","article-title":"Methods for pruning deep neural networks","volume":"10","author":"Vadera S.","year":"2022","unstructured":"Vadera , S. , and Ameen , S . Methods for pruning deep neural networks . IEEE Access 10 ( 2022 ), 63280 -- 63300 . Vadera, S., and Ameen, S. Methods for pruning deep neural networks. IEEE Access 10 (2022), 63280--63300.","journal-title":"IEEE Access"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/978-3-642-41136-6_11","volume-title":"Empirical Inference","author":"Vovk V.","year":"2013","unstructured":"Vovk , V. Kernel ridge regression . In Empirical Inference . Springer , 2013 , pp. 105 -- 116 . Vovk, V. Kernel ridge regression. In Empirical Inference. Springer, 2013, pp. 105--116."},{"key":"e_1_3_2_1_29_1","unstructured":"Warden P. Speech commands: A dataset for limited-vocabulary speech recognition. CoRR.  Warden P. Speech commands: A dataset for limited-vocabulary speech recognition. CoRR."},{"key":"e_1_3_2_1_30_1","volume-title":"Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. CoRR","author":"Xiao H.","year":"2017","unstructured":"Xiao , H. , Rasul , K. , and Vollgraf , R . Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. CoRR ( 2017 ). Xiao, H., Rasul, K., and Vollgraf, R. Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. CoRR (2017)."},{"key":"e_1_3_2_1_31_1","first-page":"7","volume-title":"Proc. of the International Symposium on Quality Electronic Design","author":"Yang L.","year":"2017","unstructured":"Yang , L. , and Murmann , B . SRAM voltage scaling for energy-efficient convolutional neural networks . In Proc. of the International Symposium on Quality Electronic Design ( 2017 ), pp. 7 -- 12 . Yang, L., and Murmann, B. SRAM voltage scaling for energy-efficient convolutional neural networks. In Proc. of the International Symposium on Quality Electronic Design (2017), pp. 7--12."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TC.2021.3104736","article-title":"Fefet-based binarized neural networks under temperature-dependent bit errors","volume":"71","author":"Yayla M.","year":"2022","unstructured":"Yayla , M. , Buschjager , S. , Gupta , A. , Chen , J.-J. , Henkel , J. , Morik , K. , Chen , K.-H. , and Amrouch , H . Fefet-based binarized neural networks under temperature-dependent bit errors . IEEE Trans. on Computers 71 , 7 ( 2022 ), 1681--1695. Yayla, M., Buschjager, S., Gupta, A., Chen, J.-J., Henkel, J., Morik, K., Chen, K.-H., and Amrouch, H. Fefet-based binarized neural networks under temperature-dependent bit errors. IEEE Trans. on Computers 71, 7 (2022), 1681--1695.","journal-title":"IEEE Trans. on Computers"},{"key":"e_1_3_2_1_33_1","volume-title":"Pruning by explaining: A novel criterion for deep neural network pruning. Pattern Recognition","author":"Yeom S.-K.","year":"2021","unstructured":"Yeom , S.-K. , Seegerer , P. , Lapuschkin , S. , Binder , A. , Wiedemann , S. , M\u00fcller , K.-R. , and Samek , W . Pruning by explaining: A novel criterion for deep neural network pruning. Pattern Recognition ( 2021 ), 107899. Yeom, S.-K., Seegerer, P., Lapuschkin, S., Binder, A., Wiedemann, S., M\u00fcller, K.-R., and Samek, W. Pruning by explaining: A novel criterion for deep neural network pruning. Pattern Recognition (2021), 107899."}],"event":{"name":"EuroMLSys '23: 3rd Workshop on Machine Learning and Systems","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"],"location":"Rome Italy","acronym":"EuroMLSys '23"},"container-title":["Proceedings of the 3rd Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578356.3592595","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:51Z","timestamp":1750178811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578356.3592595"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":33,"alternative-id":["10.1145\/3578356.3592595","10.1145\/3578356"],"URL":"https:\/\/doi.org\/10.1145\/3578356.3592595","relation":{},"subject":[],"published":{"date-parts":[[2023,5,8]]},"assertion":[{"value":"2023-05-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}