{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:30:01Z","timestamp":1743121801900,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434143"},{"type":"electronic","value":"9783031434150"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43415-0_19","type":"book-chapter","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T08:01:51Z","timestamp":1694851311000},"page":"313-329","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["REST: Enhancing Group Robustness in\u00a0DNNs Through Reweighted Sparse Training"],"prefix":"10.1007","author":[{"given":"Jiaxu","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Lu","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Shiwei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Meng","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Mykola","family":"Pechenizkiy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,17]]},"reference":[{"unstructured":"Agarwal, A., Beygelzimer, A., Dud\u00edk, M., Langford, J., Wallach, H.: A reductions approach to fair classification. In: International Conference on Machine Learning, pp. 60\u201369. PMLR (2018)","key":"19_CR1"},{"unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant risk minimization. arXiv preprint arXiv:1907.02893 (2019)","key":"19_CR2"},{"doi-asserted-by":"crossref","unstructured":"Beery, S., Van Horn, G., Perona, P.: Recognition in terra incognita. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 456\u2013473 (2018)","key":"19_CR3","DOI":"10.1007\/978-3-030-01270-0_28"},{"issue":"2","key":"19_CR4","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1287\/mnsc.1120.1641","volume":"59","author":"A Ben-Tal","year":"2013","unstructured":"Ben-Tal, A., Den Hertog, D., De Waegenaere, A., Melenberg, B., Rennen, G.: Robust solutions of optimization problems affected by uncertain probabilities. Manag. Sci. 59(2), 341\u2013357 (2013)","journal-title":"Manag. Sci."},{"unstructured":"Byrd, J., Lipton, Z.: What is the effect of importance weighting in deep learning? In: International Conference on Machine Learning, pp. 872\u2013881. PMLR (2019)","key":"19_CR5"},{"unstructured":"Dettmers, T., Zettlemoyer, L.: Sparse networks from scratch: faster training without losing performance. arXiv preprint arXiv:1907.04840 (2019)","key":"19_CR6"},{"unstructured":"Dietrich, A., Gressmann, F., Orr, D., Chelombiev, I., Justus, D., Luschi, C.: Towards structured dynamic sparse pre-training of bert. arXiv preprint arXiv:2108.06277 (2021)","key":"19_CR7"},{"unstructured":"Duchi, J., Glynn, P., Namkoong, H.: Statistics of robust optimization: a generalized empirical likelihood approach. arXiv preprint arXiv:1610.03425 (2016)","key":"19_CR8"},{"unstructured":"Duchi, J.C., Hashimoto, T., Namkoong, H.: Distributionally robust losses against mixture covariate shifts (2019)","key":"19_CR9"},{"unstructured":"Evci, U., Gale, T., Menick, J., Castro, P.S., Elsen, E.: Rigging the lottery: making all tickets winners. In: International Conference on Machine Learning, pp. 2943\u20132952. PMLR (2020)","key":"19_CR10"},{"unstructured":"Gale, T., Elsen, E., Hooker, S.: The state of sparsity in deep neural networks. arXiv preprint arXiv:1902.09574 (2019)","key":"19_CR11"},{"unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)","key":"19_CR12"},{"unstructured":"Goel, K., Gu, A., Li, Y., R\u00e9, C.: Model patching: closing the subgroup performance gap with data augmentation. arXiv preprint arXiv:2008.06775 (2020)","key":"19_CR13"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"19_CR14","DOI":"10.1109\/CVPR.2016.90"},{"unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)","key":"19_CR15"},{"unstructured":"Huang, T., Liu, S., Shen, L., He, F., Lin, W., Tao, D.: On heterogeneously distributed data, sparsity matters. In: Submitted to The Tenth International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=AT0K-SZ3QGq","key":"19_CR16"},{"doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","key":"19_CR17","DOI":"10.1109\/ICCV.2017.167"},{"unstructured":"Izmailov, P., Kirichenko, P., Gruver, N., Wilson, A.G.: On feature learning in the presence of spurious correlations. arXiv preprint arXiv:2210.11369 (2022)","key":"19_CR18"},{"key":"19_CR19","first-page":"20744","volume":"33","author":"S Jayakumar","year":"2020","unstructured":"Jayakumar, S., Pascanu, R., Rae, J., Osindero, S., Elsen, E.: Top-kast: Top-k always sparse training. Adv. Neural Inf. Process. Syst. 33, 20744\u201320754 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","key":"19_CR20","DOI":"10.1109\/CVPR.2019.00453"},{"doi-asserted-by":"crossref","unstructured":"Kepner, J., Robinett, R.: Radix-net: structured sparse matrices for deep neural networks. In: 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 268\u2013274. IEEE (2019)","key":"19_CR21","DOI":"10.1109\/IPDPSW.2019.00051"},{"unstructured":"Khani, F., Raghunathan, A., Liang, P.: Maximum weighted loss discrepancy. arXiv preprint arXiv:1906.03518 (2019)","key":"19_CR22"},{"doi-asserted-by":"crossref","unstructured":"Kim, E., Lee, J., Choo, J.: Biaswap: removing dataset bias with bias-tailored swapping augmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14992\u201315001 (2021)","key":"19_CR23","DOI":"10.1109\/ICCV48922.2021.01472"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)","key":"19_CR24"},{"issue":"11","key":"19_CR25","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"19_CR26","first-page":"25123","volume":"34","author":"J Lee","year":"2021","unstructured":"Lee, J., Kim, E., Lee, J., Lee, J., Choo, J.: Learning debiased representation via disentangled feature augmentation. Adv. Neural Inf. Process. Syst. 34, 25123\u201325133 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"unstructured":"Liu, E.Z., et al.: Just train twice: improving group robustness without training group information. In: International Conference on Machine Learning, pp. 6781\u20136792. PMLR (2021)","key":"19_CR27"},{"unstructured":"Liu, S., et al.: Deep ensembling with no overhead for either training or testing: the all-round blessings of dynamic sparsity. arXiv preprint arXiv:2106.14568 (2021)","key":"19_CR28"},{"key":"19_CR29","first-page":"9908","volume":"34","author":"S Liu","year":"2021","unstructured":"Liu, S., et al.: Sparse training via boosting pruning plasticity with neuroregeneration. Adv. Neural Inf. Process. Syst. 34, 9908\u20139922 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"unstructured":"Liu, S., Yin, L., Mocanu, D.C., Pechenizkiy, M.: Do we actually need dense over-parameterization? in-time over-parameterization in sparse training. In: International Conference on Machine Learning, pp. 6989\u20137000. PMLR (2021)","key":"19_CR30"},{"issue":"2","key":"19_CR31","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s10994-016-5570-z","volume":"104","author":"DC Mocanu","year":"2016","unstructured":"Mocanu, D.C., Mocanu, E., Nguyen, P.H., Gibescu, M., Liotta, A.: A topological insight into restricted boltzmann machines. Mach. Learn. 104(2), 243\u2013270 (2016)","journal-title":"Mach. Learn."},{"issue":"1","key":"19_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-04316-3","volume":"9","author":"DC Mocanu","year":"2018","unstructured":"Mocanu, D.C., Mocanu, E., Stone, P., Nguyen, P.H., Gibescu, M., Liotta, A.: Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature Commun. 9(1), 1\u201312 (2018)","journal-title":"Nature Commun."},{"unstructured":"Mostafa, H., Wang, X.: Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In: International Conference on Machine Learning (2019)","key":"19_CR33"},{"key":"19_CR34","first-page":"20673","volume":"33","author":"J Nam","year":"2020","unstructured":"Nam, J., Cha, H., Ahn, S., Lee, J., Shin, J.: Learning from failure: de-biasing classifier from biased classifier. Adv. Neural Inf. Process. Syst. 33, 20673\u201320684 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"unstructured":"Park, G.Y., Lee, S., Lee, S.W., Ye, J.C.: Efficient debiasing with contrastive weight pruning. arXiv preprint arXiv:2210.05247 (2022)","key":"19_CR35"},{"doi-asserted-by":"crossref","unstructured":"Prabhu, A., Varma, G., Namboodiri, A.: Deep expander networks: efficient deep networks from graph theory. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 20\u201335 (2018)","key":"19_CR36","DOI":"10.1007\/978-3-030-01261-8_2"},{"unstructured":"Sagawa, S., Koh, P.W., Hashimoto, T.B., Liang, P.: Distributionally robust neural networks for group shifts: on the importance of regularization for worst-case generalization. arXiv preprint arXiv:1911.08731 (2019)","key":"19_CR37"},{"unstructured":"Sagawa, S., Raghunathan, A., Koh, P.W., Liang, P.: An investigation of why overparameterization exacerbates spurious correlations. In: International Conference on Machine Learning, pp. 8346\u20138356. PMLR (2020)","key":"19_CR38"},{"issue":"2","key":"19_CR39","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0378-3758(00)00115-4","volume":"90","author":"H Shimodaira","year":"2000","unstructured":"Shimodaira, H.: Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Plan. Inference 90(2), 227\u2013244 (2000)","journal-title":"J. Stat. Plan. Inference"},{"unstructured":"Tanaka, H., Kunin, D., Yamins, D.L., Ganguli, S.: Pruning neural networks without any data by iteratively conserving synaptic flow. In: Advances in Neural Information Processing Systems. arXiv:2006.05467 (2020)","key":"19_CR40"},{"unstructured":"Yao, H., et al.: Improving out-of-distribution robustness via selective augmentation. arXiv preprint arXiv:2201.00299 (2022)","key":"19_CR41"},{"unstructured":"Yin, L., Menkovski, V., Fang, M., Huang, T., Pei, Y., Pechenizkiy, M.: Superposing many tickets into one: a performance booster for sparse neural network training. In: Uncertainty in Artificial Intelligence, pp. 2267\u20132277. PMLR (2022)","key":"19_CR42"},{"unstructured":"Yuan, G., et al.: Mest: accurate and fast memory-economic sparse training framework on the edge. Adv. Neural Inf. Process. Syst. 34 (2021)","key":"19_CR43"},{"doi-asserted-by":"crossref","unstructured":"Zhang, D., Ahuja, K., Xu, Y., Wang, Y., Courville, A.: Can subnetwork structure be the key to out-of-distribution generalization? In: International Conference on Machine Learning, pp. 12356\u201312367. PMLR (2021)","key":"19_CR44","DOI":"10.1109\/CVPR46437.2021.00533"},{"doi-asserted-by":"crossref","unstructured":"Zhao, J., Fang, M., Shi, Z., Li, Y., Chen, L., Pechenizkiy, M.: Chbias: bias evaluation and mitigation of Chinese conversational language models. In: Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Toronto (2023)","key":"19_CR45","DOI":"10.18653\/v1\/2023.acl-long.757"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43415-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T08:06:39Z","timestamp":1694851599000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43415-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434143","9783031434150"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43415-0_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"As researchers in the field of deep neural networks, we recognize the importance of developing methods that improve the generalization capabilities of these models, particularly for minority groups that may be underrepresented in training data. Our proposed reweighted sparse training framework, REST, aims to tackle the issue of bias-conflicting correlations in DNNs by reducing reliance on spurious correlations. We believe that this work has the potential to enhance the robustness of DNNs and improve their performance on out-of-distribution samples, which may have significant implications for various applications such as healthcare and criminal justice. However, we acknowledge that there may be ethical considerations associated with the development and deployment of machine learning algorithms, particularly those that may impact human lives. As such, we encourage the responsible use and evaluation of our proposed framework to ensure that it aligns with ethical standards and does not perpetuate biases or harm vulnerable populations.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Statement"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"196","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}