Sedjro Salomon Hotegni

Sedjro Salomon Hotegni

PhD student in Computer Science (Multi-criteria Machine Learning), Safe Autonomous Systems group, TU Dortmund University

Posts by Collection

portfolio

publications

Approximation Algorithms for Fair Range Clustering

Published in ICML 2023, Hawaii, USA, 2023

Approximation Algorithms for Fair Range Clustering Read more

Recommended citation: Hotegni, S.S., Mahabadi, S. and Vakilian, A., 2023, July. Approximation Algorithms for Fair Range Clustering. In International Conference on Machine Learning (pp. 13270-13284). PMLR.

Multi-Objective Optimization for Sparse Deep Multi-Task Learning

Published in IJCNN 2024, Yokohama, Japan, 2024

Multi-Objective Optimization for Sparse Deep Multi-Task Learning Read more

Recommended citation: S. S. Hotegni, M. Berkemeier and S. Peitz, "Multi-Objective Optimization for Sparse Deep Multi-Task Learning," 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan, 2024, pp. 1-9, doi: 10.1109/IJCNN60899.2024.10650994.

Multi-objective deep learning: Taxonomy and survey of the state of the art

Published in Machine Learning with Applications, 2025

Multi-objective deep learning: Taxonomy and survey of the state of the art Read more

Recommended citation: Sebastian Peitz, Sèdjro Salomon Hotegni, Multi-objective deep learning: Taxonomy and survey of the state of the art, Machine Learning with Applications, Volume 21, 2025, 100700, ISSN 2666-8270, https://doi.org/10.1016/j.mlwa.2025.100700.

Enhancing Adversarial Robustness through Multi-Objective Representation Learning

Published in ICANN 2025, Kaunas, Lithuania, 2025

Enhancing Adversarial Robustness through Multi-Objective Representation Learning Read more

Recommended citation: Hotegni, S.S., Peitz, S. (2026). Enhancing Adversarial Robustness Through Multi-objective Representation Learning. In: Senn, W., et al. Artificial Neural Networks and Machine Learning – ICANN 2025. ICANN 2025. Lecture Notes in Computer Science, vol 16068. Springer, Cham. https://doi.org/10.1007/978-3-032-04558-4_35

SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion

Published in ICLR 2026, Rio de Janeiro, Brazil , 2026

SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion Read more

Recommended citation: Hotegni, S.S., Peitz, S. (2026). SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion. In: 14th International Conference on Learning Representations, ICLR 2026. International Conference on Learning Representations, ICLR.

talks

Multi-Objective Optimization for Deep Neural Network Training using Weighted Chebyshev Scalarization Permalink

Published:

6th European Conference on Computational Optimization (EUCCO): The EUCCO conference series aims to bring scientists from computational optimization, algorithms for large-scale optimization problems and related applications together. The 2023 edition especially emphasized optimization with partial differential equations, large-scale optimization, as well as numerical optimization algorithms and software. More information here Read more

Multi-Objective Optimization for Sparse Deep Multi-Task Learning Permalink

Published:

IEEE WCCI 2024 is the world’s largest technical event on computational intelligence, featuring the three flagship conferences of the IEEE Computational Intelligence Society (CIS) under one roof: The International Joint Conference on Neural Networks (IJCNN), the IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) and the IEEE Congress on Evolutionary Computation (IEEE CEC). More information here Read more

MOREL: Enhancing Adversarial Robustness through Multi-Objective Representation Learning Permalink

Published:

The Sorrento Meeting is a special version of the DALI meeting held in Sorrento. Conceived with the same spirit of DALI, there’s also the opportunity to submit a single-authored paper for potential presentation during the plenary session. The idea of DALI (Data, Learning and Inference) is to combine the special qualities of the former Snowbird meetings (intimate atmosphere, very good people, plenty of time to interact) with attractive aspects of larger conferences that rarely take place in Europe. We use a three-day format with two days of workshops and one day of plenary talks in the middle, including a poster session. We pick a location that limits jet lag and / or travel times for many of us who normally travel to meetings in the US. The workshops feature research topics of current interest, and workshop participants are nominated by the workshop organizers. DALI is small and (geographically) biased towards European researchers. Participation is by invitation only. More information here Read more

A Diffusion-Driven Generative Framework for Pareto Front Learning Permalink

Published:

34th European Conference on Operational Research (EURO 2025): The EURO-k Conferences serve as vibrant hubs for European Operational Researchers to connect, collaborate, and share their brilliance. With a wide-reaching focus, these conferences bring together OR enthusiasts from all corners of the discipline, from theory to practice, for a lively exchange of ideas, knowledge, and groundbreaking results. Over the past 50 years, the EURO-k series has hopped around 23 different countries – proving that good research knows no borders (and neither do conference organisers)! More information here Read more