[{"status":"public","title":"SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion","year":"2026","author":[{"id":"97995","last_name":"Hotegni","first_name":"Sedjro Salomon","full_name":"Hotegni, Sedjro Salomon"},{"id":"47427","last_name":"Peitz","orcid":"0000-0002-3389-793X","first_name":"Sebastian","full_name":"Peitz, Sebastian"}],"date_updated":"2026-10-01T12:02:30Z","main_file_link":[{"open_access":"1","url":"https://openreview.net/pdf?id=4731mIqv89"}],"_id":"67307","language":[{"iso":"eng"}],"user_id":"47427","doi":"10.48550/arXiv.2509.21058","publication":"14th International Conference on Learning Representations (ICLR)","citation":{"mla":"Hotegni, Sedjro Salomon, and Sebastian Peitz. “SPREAD: Sampling-Based Pareto Front Refinement via Efficient Adaptive Diffusion.” <i>14th International Conference on Learning Representations (ICLR)</i>, 2026, doi:<a href=\"https://doi.org/10.48550/arXiv.2509.21058\">10.48550/arXiv.2509.21058</a>.","bibtex":"@inproceedings{Hotegni_Peitz_2026, title={SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion}, DOI={<a href=\"https://doi.org/10.48550/arXiv.2509.21058\">10.48550/arXiv.2509.21058</a>}, booktitle={14th International Conference on Learning Representations (ICLR)}, author={Hotegni, Sedjro Salomon and Peitz, Sebastian}, year={2026} }","ama":"Hotegni SS, Peitz S. SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion. In: <i>14th International Conference on Learning Representations (ICLR)</i>. ; 2026. doi:<a href=\"https://doi.org/10.48550/arXiv.2509.21058\">10.48550/arXiv.2509.21058</a>","ieee":"S. S. Hotegni and S. Peitz, “SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion,” 2026, doi: <a href=\"https://doi.org/10.48550/arXiv.2509.21058\">10.48550/arXiv.2509.21058</a>.","apa":"Hotegni, S. S., &#38; Peitz, S. (2026). SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion. <i>14th International Conference on Learning Representations (ICLR)</i>. <a href=\"https://doi.org/10.48550/arXiv.2509.21058\">https://doi.org/10.48550/arXiv.2509.21058</a>","short":"S.S. Hotegni, S. Peitz, in: 14th International Conference on Learning Representations (ICLR), 2026.","chicago":"Hotegni, Sedjro Salomon, and Sebastian Peitz. “SPREAD: Sampling-Based Pareto Front Refinement via Efficient Adaptive Diffusion.” In <i>14th International Conference on Learning Representations (ICLR)</i>, 2026. <a href=\"https://doi.org/10.48550/arXiv.2509.21058\">https://doi.org/10.48550/arXiv.2509.21058</a>."},"date_created":"2026-10-01T12:01:30Z","type":"conference","keyword":["own","own-conference"],"department":[{"_id":"655"}],"oa":"1"},{"citation":{"ama":"Hotegni SS, Peitz S. Enhancing Adversarial Robustness Through Multi-objective Representation Learning. In: Senn W, Sanguineti M, Saudargiene A, et al., eds. <i>Artificial Neural Networks and Machine Learning – ICANN 2025</i>. Springer Nature Switzerland; 2026:442–454. doi:<a href=\"https://doi.org/10.1007/978-3-032-04558-4_35\">10.1007/978-3-032-04558-4_35</a>","bibtex":"@inproceedings{Hotegni_Peitz_2026, place={Cham}, title={Enhancing Adversarial Robustness Through Multi-objective Representation Learning}, DOI={<a href=\"https://doi.org/10.1007/978-3-032-04558-4_35\">10.1007/978-3-032-04558-4_35</a>}, booktitle={Artificial Neural Networks and Machine Learning – ICANN 2025}, publisher={Springer Nature Switzerland}, author={Hotegni, Sedjro Salomon and Peitz, Sebastian}, editor={Senn, Walter and Sanguineti, Marcello and Saudargiene, Ausra and Tetko, Igor V. and Villa, Alessandro E. P. and Jirsa, Viktor and Bengio, Yoshua}, year={2026}, pages={442–454} }","mla":"Hotegni, Sedjro Salomon, and Sebastian Peitz. “Enhancing Adversarial Robustness Through Multi-Objective Representation Learning.” <i>Artificial Neural Networks and Machine Learning – ICANN 2025</i>, edited by Walter Senn et al., Springer Nature Switzerland, 2026, pp. 442–454, doi:<a href=\"https://doi.org/10.1007/978-3-032-04558-4_35\">10.1007/978-3-032-04558-4_35</a>.","chicago":"Hotegni, Sedjro Salomon, and Sebastian Peitz. “Enhancing Adversarial Robustness Through Multi-Objective Representation Learning.” In <i>Artificial Neural Networks and Machine Learning – ICANN 2025</i>, edited by Walter Senn, Marcello Sanguineti, Ausra Saudargiene, Igor V. Tetko, Alessandro E. P. Villa, Viktor Jirsa, and Yoshua Bengio, 442–454. Cham: Springer Nature Switzerland, 2026. <a href=\"https://doi.org/10.1007/978-3-032-04558-4_35\">https://doi.org/10.1007/978-3-032-04558-4_35</a>.","short":"S.S. Hotegni, S. Peitz, in: W. Senn, M. Sanguineti, A. Saudargiene, I.V. Tetko, A.E.P. Villa, V. Jirsa, Y. Bengio (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2025, Springer Nature Switzerland, Cham, 2026, pp. 442–454.","apa":"Hotegni, S. S., &#38; Peitz, S. (2026). Enhancing Adversarial Robustness Through Multi-objective Representation Learning. In W. Senn, M. Sanguineti, A. Saudargiene, I. V. Tetko, A. E. P. Villa, V. Jirsa, &#38; Y. Bengio (Eds.), <i>Artificial Neural Networks and Machine Learning – ICANN 2025</i> (pp. 442–454). Springer Nature Switzerland. <a href=\"https://doi.org/10.1007/978-3-032-04558-4_35\">https://doi.org/10.1007/978-3-032-04558-4_35</a>","ieee":"S. S. Hotegni and S. Peitz, “Enhancing Adversarial Robustness Through Multi-objective Representation Learning,” in <i>Artificial Neural Networks and Machine Learning – ICANN 2025</i>, 2026, pp. 442–454, doi: <a href=\"https://doi.org/10.1007/978-3-032-04558-4_35\">10.1007/978-3-032-04558-4_35</a>."},"place":"Cham","status":"public","editor":[{"full_name":"Senn, Walter","last_name":"Senn","first_name":"Walter"},{"full_name":"Sanguineti, Marcello","first_name":"Marcello","last_name":"Sanguineti"},{"full_name":"Saudargiene, Ausra","first_name":"Ausra","last_name":"Saudargiene"},{"full_name":"Tetko, Igor V.","first_name":"Igor V.","last_name":"Tetko"},{"last_name":"Villa","first_name":"Alessandro E. P.","full_name":"Villa, Alessandro E. P."},{"full_name":"Jirsa, Viktor","last_name":"Jirsa","first_name":"Viktor"},{"first_name":"Yoshua","last_name":"Bengio","full_name":"Bengio, Yoshua"}],"user_id":"47427","_id":"67300","publisher":"Springer Nature Switzerland","page":"442–454","abstract":[{"text":"Deep neural networks (DNNs) are vulnerable to small adversarial perturbations, which are tiny changes to the input data that appear insignificant but cause the model to produce drastically different outputs. Many defense methods require modifying model architectures during evaluation or performing test-time data purification. This not only introduces additional complexity but is often architecture-dependent. We show, however, that robust feature learning during training can significantly enhance DNN robustness. We propose MOREL, a multi-objective approach that aligns natural and adversarial features using cosine similarity and multi-positive contrastive losses to encourage similar features for same-class inputs. Extensive experiments demonstrate that MOREL significantly improves robustness against both white-box and black-box attacks. Our code is available at https://github.com/salomonhotegni/MOREL.","lang":"eng"}],"publication":"Artificial Neural Networks and Machine Learning – ICANN 2025","department":[{"_id":"655"}],"type":"conference","keyword":["own","own-conference"],"date_created":"2026-10-01T11:53:11Z","date_updated":"2026-10-01T11:53:46Z","author":[{"full_name":"Hotegni, Sedjro Salomon","first_name":"Sedjro Salomon","last_name":"Hotegni","id":"97995"},{"last_name":"Peitz","orcid":"0000-0002-3389-793X","first_name":"Sebastian","full_name":"Peitz, Sebastian","id":"47427"}],"publication_identifier":{"isbn":["978-3-032-04558-4"]},"title":"Enhancing Adversarial Robustness Through Multi-objective Representation Learning","year":"2026","doi":"10.1007/978-3-032-04558-4_35","language":[{"iso":"eng"}]},{"department":[{"_id":"655"}],"keyword":["own","own-journal"],"type":"journal_article","date_created":"2026-10-01T12:05:57Z","citation":{"chicago":"Peitz, Sebastian, and Sedjro Salomon Hotegni. “Multi-Objective Deep Learning: Taxonomy and Survey of the State of the Art.” <i>Machine Learning with Applications</i>, no. 100700 (2025). <a href=\"https://doi.org/10.1016/j.mlwa.2025.100700\">https://doi.org/10.1016/j.mlwa.2025.100700</a>.","short":"S. Peitz, S.S. Hotegni, Machine Learning with Applications (2025).","apa":"Peitz, S., &#38; Hotegni, S. S. (2025). Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art. <i>Machine Learning with Applications</i>, <i>100700</i>. <a href=\"https://doi.org/10.1016/j.mlwa.2025.100700\">https://doi.org/10.1016/j.mlwa.2025.100700</a>","ieee":"S. Peitz and S. S. Hotegni, “Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art,” <i>Machine Learning with Applications</i>, no. 100700, 2025, doi: <a href=\"https://doi.org/10.1016/j.mlwa.2025.100700\">10.1016/j.mlwa.2025.100700</a>.","ama":"Peitz S, Hotegni SS. Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art. <i>Machine Learning with Applications</i>. 2025;(100700). doi:<a href=\"https://doi.org/10.1016/j.mlwa.2025.100700\">10.1016/j.mlwa.2025.100700</a>","bibtex":"@article{Peitz_Hotegni_2025, title={Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art}, DOI={<a href=\"https://doi.org/10.1016/j.mlwa.2025.100700\">10.1016/j.mlwa.2025.100700</a>}, number={100700}, journal={Machine Learning with Applications}, author={Peitz, Sebastian and Hotegni, Sedjro Salomon}, year={2025} }","mla":"Peitz, Sebastian, and Sedjro Salomon Hotegni. “Multi-Objective Deep Learning: Taxonomy and Survey of the State of the Art.” <i>Machine Learning with Applications</i>, no. 100700, 2025, doi:<a href=\"https://doi.org/10.1016/j.mlwa.2025.100700\">10.1016/j.mlwa.2025.100700</a>."},"issue":"100700","publication":"Machine Learning with Applications","user_id":"47427","doi":"10.1016/j.mlwa.2025.100700","_id":"67316","language":[{"iso":"eng"}],"date_updated":"2026-10-01T12:06:04Z","author":[{"id":"47427","orcid":"0000-0002-3389-793X","last_name":"Peitz","first_name":"Sebastian","full_name":"Peitz, Sebastian"},{"id":"97995","full_name":"Hotegni, Sedjro Salomon","last_name":"Hotegni","first_name":"Sedjro Salomon"}],"status":"public","year":"2025","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art"},{"oa":"1","place":"Yokohama, Japan","citation":{"chicago":"Hotegni, Sedjro Salomon, Manuel Bastian Berkemeier, and Sebastian Peitz. “Multi-Objective Optimization for Sparse Deep Multi-Task Learning.” In <i>2024 International Joint Conference on Neural Networks (IJCNN)</i>, 9. Yokohama, Japan: IEEE, 2024. <a href=\"https://doi.org/10.1109/IJCNN60899.2024.10650994\">https://doi.org/10.1109/IJCNN60899.2024.10650994</a>.","ama":"Hotegni SS, Berkemeier MB, Peitz S. Multi-Objective Optimization for Sparse Deep Multi-Task Learning. In: <i>2024 International Joint Conference on Neural Networks (IJCNN)</i>. IEEE; 2024:9. doi:<a href=\"https://doi.org/10.1109/IJCNN60899.2024.10650994\">10.1109/IJCNN60899.2024.10650994</a>","short":"S.S. Hotegni, M.B. Berkemeier, S. Peitz, in: 2024 International Joint Conference on Neural Networks (IJCNN), IEEE, Yokohama, Japan, 2024, p. 9.","bibtex":"@inproceedings{Hotegni_Berkemeier_Peitz_2024, place={Yokohama, Japan}, title={Multi-Objective Optimization for Sparse Deep Multi-Task Learning}, DOI={<a href=\"https://doi.org/10.1109/IJCNN60899.2024.10650994\">10.1109/IJCNN60899.2024.10650994</a>}, booktitle={2024 International Joint Conference on Neural Networks (IJCNN)}, publisher={IEEE}, author={Hotegni, Sedjro Salomon and Berkemeier, Manuel Bastian and Peitz, Sebastian}, year={2024}, pages={9} }","apa":"Hotegni, S. S., Berkemeier, M. B., &#38; Peitz, S. (2024). Multi-Objective Optimization for Sparse Deep Multi-Task Learning. <i>2024 International Joint Conference on Neural Networks (IJCNN)</i>, 9. <a href=\"https://doi.org/10.1109/IJCNN60899.2024.10650994\">https://doi.org/10.1109/IJCNN60899.2024.10650994</a>","mla":"Hotegni, Sedjro Salomon, et al. “Multi-Objective Optimization for Sparse Deep Multi-Task Learning.” <i>2024 International Joint Conference on Neural Networks (IJCNN)</i>, IEEE, 2024, p. 9, doi:<a href=\"https://doi.org/10.1109/IJCNN60899.2024.10650994\">10.1109/IJCNN60899.2024.10650994</a>.","ieee":"S. S. Hotegni, M. B. Berkemeier, and S. Peitz, “Multi-Objective Optimization for Sparse Deep Multi-Task Learning,” in <i>2024 International Joint Conference on Neural Networks (IJCNN)</i>, Yokohama, Japan, 2024, p. 9, doi: <a href=\"https://doi.org/10.1109/IJCNN60899.2024.10650994\">10.1109/IJCNN60899.2024.10650994</a>."},"user_id":"97995","page":"9","_id":"46649","publisher":"IEEE","has_accepted_license":"1","status":"public","conference":{"location":"Yokohama, Japan","start_date":"2024-06-30","name":"2024 International Joint Conference on Neural Networks (IJCNN)","end_date":"2024-07-05"},"type":"conference","department":[{"_id":"655"}],"date_created":"2023-08-24T07:44:36Z","abstract":[{"text":"Different conflicting optimization criteria arise naturally in various Deep\r\nLearning scenarios. These can address different main tasks (i.e., in the\r\nsetting of Multi-Task Learning), but also main and secondary tasks such as loss\r\nminimization versus sparsity. The usual approach is a simple weighting of the\r\ncriteria, which formally only works in the convex setting. In this paper, we\r\npresent a Multi-Objective Optimization algorithm using a modified Weighted\r\nChebyshev scalarization for training Deep Neural Networks (DNNs) with respect\r\nto several tasks. By employing this scalarization technique, the algorithm can\r\nidentify all optimal solutions of the original problem while reducing its\r\ncomplexity to a sequence of single-objective problems. The simplified problems\r\nare then solved using an Augmented Lagrangian method, enabling the use of\r\npopular optimization techniques such as Adam and Stochastic Gradient Descent,\r\nwhile efficaciously handling constraints. Our work aims to address the\r\n(economical and also ecological) sustainability issue of DNN models, with a\r\nparticular focus on Deep Multi-Task models, which are typically designed with a\r\nvery large number of weights to perform equally well on multiple tasks. Through\r\nexperiments conducted on two Machine Learning datasets, we demonstrate the\r\npossibility of adaptively sparsifying the model during training without\r\nsignificantly impacting its performance, if we are willing to apply\r\ntask-specific adaptations to the network weights. Code is available at\r\nhttps://github.com/salomonhotegni/MDMTN.","lang":"eng"}],"publication":"2024 International Joint Conference on Neural Networks (IJCNN)","doi":"10.1109/IJCNN60899.2024.10650994","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10650994","open_access":"1"}],"language":[{"iso":"eng"}],"publication_status":"published","date_updated":"2024-09-27T10:24:22Z","title":"Multi-Objective Optimization for Sparse Deep Multi-Task Learning","year":"2024","publication_identifier":{"eissn":[" 2161-4407"],"eisbn":["979-8-3503-5931-2"]},"author":[{"id":"97995","last_name":"Hotegni","first_name":"Sedjro Salomon","full_name":"Hotegni, Sedjro Salomon"},{"id":"51701","first_name":"Manuel Bastian","last_name":"Berkemeier","full_name":"Berkemeier, Manuel Bastian"},{"id":"47427","full_name":"Peitz, Sebastian","first_name":"Sebastian","last_name":"Peitz","orcid":"0000-0002-3389-793X"}]},{"department":[{"_id":"655"}],"oa":"1","type":"conference","keyword":["Fair range clustering"],"date_created":"2023-06-20T22:29:33Z","citation":{"short":"S.S. Hotegni, S. Mahabadi, A. Vakilian, in: Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023., n.d.","chicago":"Hotegni, Sedjro Salomon, Sepideh Mahabadi, and Ali Vakilian. “Approximation Algorithms for Fair Range Clustering.” In <i>Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.</i>, n.d.","ieee":"S. S. Hotegni, S. Mahabadi, and A. Vakilian, “Approximation Algorithms for Fair Range Clustering,” presented at the International Conference on Machine Learning, Honolulu, Hawaii, USA.","apa":"Hotegni, S. S., Mahabadi, S., &#38; Vakilian, A. (n.d.). Approximation Algorithms for Fair Range Clustering. <i>Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.</i> International Conference on Machine Learning, Honolulu, Hawaii, USA.","bibtex":"@inproceedings{Hotegni_Mahabadi_Vakilian, title={Approximation Algorithms for Fair Range Clustering}, booktitle={Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.}, author={Hotegni, Sedjro Salomon and Mahabadi, Sepideh and Vakilian, Ali} }","ama":"Hotegni SS, Mahabadi S, Vakilian A. Approximation Algorithms for Fair Range Clustering. In: <i>Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.</i>","mla":"Hotegni, Sedjro Salomon, et al. “Approximation Algorithms for Fair Range Clustering.” <i>Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.</i>"},"publication":"Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.","user_id":"97995","language":[{"iso":"eng"}],"_id":"45695","main_file_link":[{"url":"https://openreview.net/forum?id=gBoKJT5JhM","open_access":"1"}],"publication_status":"accepted","date_updated":"2023-06-20T23:03:12Z","author":[{"full_name":"Hotegni, Sedjro Salomon","first_name":"Sedjro Salomon","last_name":"Hotegni","id":"97995"},{"full_name":"Mahabadi, Sepideh","first_name":"Sepideh","last_name":"Mahabadi"},{"last_name":"Vakilian","first_name":"Ali","full_name":"Vakilian, Ali"}],"conference":{"name":"International Conference on Machine Learning","start_date":"2023-07-23","location":"Honolulu, Hawaii, USA","end_date":"2023-07-29"},"title":"Approximation Algorithms for Fair Range Clustering","status":"public","year":"2023"}]