Ecole - Experience based
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 766186. EU Flag
Repository Content
FriessCEC2020 ·        Representing Experience in Continuous Evolutionary Optimisation through Problem-tailored Search Operators (Friess, Tiňo, Menzel, Sendhoff & Yao, 2020)

·        Friess, S., Tiňo, P., Menzel, S., Sendhoff, B. and Yao, X., 2020, July. Representing Experience in Continuous Evolutionary Optimisation through Problem-tailored Search Operators. In 2020 IEEE Congress on Evolutionary Computation (CEC) (pp. 1-7). IEEE.
NguyenSSCI2021 ·        Efficient AutoML via Combinational Sampling (Nguyen, Kononova, Menzel, Sendhoff and Bäck, 2021)

·        Citation for this repository – Duc Anh Nguyen, Anna V. Kononova, Stefan Menzel, Bernhard Sendhoff and Thomas Bäck. Efficient AutoML via Combinational Sampling. IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2021).
 NguyenDSAA2021

 

 ·        Improved Automated CASH Optimization with Tree Parzen Estimators for Class Imbalance Problems (Nguyen, Kong, Wang, Menzel, Sendhoff, Kononova and Bäck, 2021)

·        Citation for this repository – Duc Anh Nguyen, Jiawen Kong, Hao Wang, Stefan Menzel, Bernhard Sendhoff, Anna V. Kononova and Thomas Bäck. Improved Automated CASH Optimization with Tree Parzen Estimators for Class Imbalance Problems. The 8th IEEE International Conference on Data Science and Advanced Analytics (DSAA2021).

 
FriessSSCI2021

 

 ·        Predicting CMA-ES Operators as Inductive Biases for Shape Optimization Problems (Friess, Tiňo, Menzel, Sendhoff & Yao, 2022)

·        Citation for this repository –  Friess, S., Tiňo, P.,Menzel, S., Sendhoff, B. and Yao, X., 2022, January. Predicting CMA-ES Operators as Inductive Biases for Shape Optimization Problems. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1-7). IEEE.
Kong2020PPSN ·        Improving Imbalanced Classification by Anomaly Detection (Kong, Kowalczyk, Menzel & Bäck, 2020).

·        Citation for this repository – Kong, J., Kowalczyk, W., Menzel, S. and Bäck, T., 2020, September. Improving imbalanced classification by anomaly detection. In International Conference on Parallel Problem Solving from Nature (pp. 512-523). Springer, Cham.
UllahSSCI2019 ·        An Empirical Comparison of Meta-Modeling Techniques for Robust Design Optimization (Ullah, Wang, Menzel, Sendhoff & Bäck, 2019).

·        Citation for this repository –  S. Ullah, H. Wang, S. Menzel, B. Sendhoff and T. Bäck, “An Empirical Comparison of Meta-Modeling Techniques for Robust Design Optimization,” 2019 IEEE Symposium Series on Computational Intelligence (SSCI), 2019, pp. 819-828.
 UllahIJCNN2020 ·        Exploring Clinical Time Series Forecasting with Meta-Features in Variational Recurrent Models (Ullah, Xu, Wang, Menzel, Sendhoff & Bäck, 2020).

·        References used –  [1] Chung, Junyoung, et al. “A recurrent latent variable model for sequential data.” Advances in neural information processing systems. 2015.

·        [2] Harutyunyan, Hrayr, et al. “Multitask learning and benchmarking with clinical time series data.” arXiv preprint arXiv:1703.07771 (2017).

·        Citation for this repository – S. Ullah, Z. Xu, H. Wang, S. Menzel, B. Sendhoff and T. Bäck, “Exploring Clinical Time Series Forecasting with Meta-Features in Variational Recurrent Models,” 2020 International Joint Conference on Neural Networks (IJCNN), 2020, pp. 1-9.
 UllahSSCI2020 ·        Exploring Dimensionality Reduction Techniques for Efficient Surrogate-Assisted Optimization (Ullah, Nguyen, Wang, Menzel, Sendhoff & Bäck, 2020).

·        Citation for this repository –  S. Ullah, D. A. Nguyen, H. Wang, S. Menzel, B. Sendhoff and T. Bäck, “Exploring Dimensionality Reduction Techniques for Efficient Surrogate-Assisted optimization,” 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 2020, pp. 2965-2974.
UllahGECCO2021 ·        A New Acquisition Function for Robust Bayesian Optimization of Unconstrained Problems (Ullah, Wang, Menzel, Sendhoff & Bäck, 2021).

·        Citation for this repository –  Sibghat Ullah, Hao Wang, Stefan Menzel, Bernhard Sendhoff, and Thomas Bäck. 2021. A New Acquisition Function for Robust Bayesian Optimization of Unconstrained Problems. In 2021 Genetic and Evolutionary Computation Conference Companion (GECCO ’21 Companion), July 10–14, 2021, Lille, France.
Geometric Deep Learning for Design Applications (GDL4DesignApps) This repository is a very well summarizing repository for the software developed on geometric deep learning for compact accessibiliy and improved usability. Publications of ESR1 and ESR2 are based on these codes. Following papers use corresponding parts of this repository:

·        T. Rios, P. Wollstadt, B. van Stein, T. Bäck, Z. Xu, B. Sendhoff and S. Menzel, “Scalability of Learning Tasks on 3D CAE Models Using Point Cloud Autoencoders,” 2019 IEEE Symposium Series on Computational Intelligence (SSCI), 2019, pp. 1367-1374, doi: 10.1109/SSCI44817.2019.9002982.

·        T. Rios, B. Sendhoff, S. Menzel, T. Bäck and B. van Stein, “On the Efficiency of a Point Cloud Autoencoder as a Geometric Representation for Shape Optimization,” 2019 IEEE Symposium Series on Computational Intelligence (SSCI), 2019, pp. 791-798, doi: 10.1109/SSCI44817.2019.9003161.

·        T. Rios, B. van Stein, S. Menzel, T. Back, B. Sendhoff and P. Wollstadt, “Feature Visualization for 3D Point Cloud Autoencoders,” 2020 International Joint Conference on Neural Networks (IJCNN), 2020, pp. 1-9, doi: 10.1109/IJCNN48605.2020.9207326.

·        T. Rios, J. Kong, B. van Stein, T. Bäck, P. Wollstadt, B. Sendhoff and S. Menzel, “Back To Meshes: Optimal Simulation-ready Mesh Prototypes For Autoencoder-based 3D Car Point Clouds,” 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 2020, pp. 942-949, doi: 10.1109/SSCI47803.2020.9308400.

·        T. Rios, B. van Stein, P. Wollstadt, T. Bäck, B. Sendhoff and S. Menzel, “Exploiting Local Geometric Features in Vehicle Design Optimization with 3D Point Cloud Autoencoders,” 2021 IEEE Congress on Evolutionary Computation (CEC), 2021, pp. 514-521, doi: 10.1109/CEC45853.2021.9504746.

·        T. Rios, B. van Stein, T. Bäck, B. Sendhoff and S. Menzel, “Multi-Task Shape Optimization Using a 3D Point Cloud Autoencoder as Unified Representation,” in IEEE Transactions on Evolutionary Computation, doi: 10.1109/TEVC.2021.3086308. (Early Access)

·        T. Rios, B. Van Stein, T. Bäck, B. Sendhoff and S. Menzel, “Point2FFD: Learning Shape Representations of Simulation-Ready 3D Models for Engineering Design Optimization,” 2021 International Conference on 3D Vision (3DV), 2021, pp. 1024-1033, doi: 10.1109/3DV53792.2021.00110.

·        S. Saha, S. Menzel, L. L. Minku, X. Yao, B. Sendhoff, and P. Wollstadt, “Quantifying The Generative Capabilities Of Variational Autoencoders For 3D Car Point Clouds”, in Symposium Series on Computational Intelligence (SSCI) 2020 (pp. 1469-1477)

·        S. Saha, L. L. Minku, X. Yao, Z. Xu, B. Sendhoff, and S. Menzel, “Exploiting Linear Interpolation of Variational Autoencoders for Satisfying Preferences in Evolutionary Design Optimization”, in IEEE Congress on Evolutionary Computation (CEC) 2021.

·        S. Saha, T. Rios,   L. L. Minku, B. Stein. P. Wollstadt,  X. Yao, B. Sendhoff, and S. Menzel, “Exploiting Generative Models for Performance Predictions of 3D Car Designs”, in Symposium Series on Computational Intelligence (SSCI) 2021.

·        S. Saha, L. L. Minku, X. Yao, B. Sendhoff, and S. Menzel, “Exploiting 3D Variational Autoencoders For Interactive Vehicle Design”, in International Design Conference 2022 (Accepted).

·        S. Saha, L. L. Minku, X. Yao, B. Sendhoff, and S. Menzel, “Split-AE: An Autoencoder-based Disentanglement Framework for 3D Shape-to-shape Feature Transfer”, in International Joint Conference on Neural Networks (IJCNN) 2022 (Submitted)

There is also already 1 journal publication which refer to GDL software developed within ECOLE: P. Wollstadt, M. Bujny, S. Ramnath, J.J. Shah, D. Detwiler, S. Menzel, “CarHoods10k: An Industry-grade Data Set for Representation Learning and Design Optimization in Engineering Applications”, in IEEE Transactions on Evolutionary Computation Special Issue on Benchmarking Sampling-Based Optimization Heuristics: Methodology and Software (BENCH), 2022, doi: 10.1109/TEVC.2022.3147013 (Early Access)
FriessIJCNN2021

 

 ·        Artificial Neural Networks as Feature Extractors in Continuous Evolutionary Optimization
SerraIJCNN2021

 

 ·        Interpreting Node Embedding with Text-labeled Graphs (Serra, Xu, Lawrence, Niepert, Tino & Yao, IJCNN 2021).

·        This repository contains code for the paper ‘Interpreting Node Embedding with Text-labeled Graphs’ (Serra, Xu, Niepert, Lawrence, Tino & Yao, IJCNN 2021).
RuanORAN2021 ·        Code and data corresponding to the work on “Evolutionary Optimization for Proactive and Dynamic Computing Resource Allocation in Open Radio Access Network.”
RuanSSCI2019 ·        This package contains the source codes of the paper % “Ruan, G., Minku, L. L., Menzel, S., Sendhoff, B., & Yao, X. (2019, December). When and how % to transfer knowledge in dynamic multi-objective optimisation. In 2019 IEEE Symposium Series % on Computational Intelligence (SSCI) (pp. 2034-2041). IEEE,” % which is modified from the code of the paper % “Jiang M, Huang Z, Qiu L, et al. Transfer Learning based Dynamic Multiobjective Optimization Algorithms” https://zenodo.org/record/5509255#.Yi9sRXrP1PY.

·        Codes used in the paper “When and How to Transfer Knowledge in Dynamic Multi-Objective Optimization” published at SSCI 2019.
RuanCEC2020 ·        Code related to CEC 2020 paper on “Computational Study on Effectiveness of Knowledge Transfer in Dynamic Multi-objective Optimization”
Deliverables PDF copies of all public deliverables submitted to EU Funder