Source Codes for Felix's Publications
Share Your Feedback
- Performance Prediction:
- newGraph Isomorphism Network-based Multitask robustness Analysis System >> GIN-MAS
- A multitask learning approach is taken to learn the network robustness metrics, including connectivity robustness, controllability robustness, destruction threshold, and the maximum number of connected components.
- A destruction-based robustness metric that is both practical and computationally efficient is formulated and used to measure network robustness in this work.
- References:
- A Multitask Network Robustness Analysis System Based on the Graph Isomorphism Network in IEEE Transactions on Cybernetics [Link]
- newSpatial Pyramid Pooling Convolutional Neural Network >> SPP-CNN
- A spatial pyramid pooling (SPP) is installed between the convolutional layers and fully-connected layer of CNN.
- SPP-CNN has a wider tolerance to different input-data sizes, while maintaining fast approximation speed.
- References:
- SPP-CNN: An Efficient Framework for Network Robustness Prediction in IEEE Transactions on Circuits and Systems I: Regular Papers [Link]
- Learning Feature Representation-based Convolutional Neural Network >> LFR-CNN
- Higher-dimensional network data are compressed to lower-dimensional representations, and then passed to a CNN to perform robustness prediction.
- It is insensitive to input size, thus, the applicability is significantly extended.
- References:
- A Learning Convolutional Neural Network Approach for Network Robustness Prediction in IEEE Transactions on Cybernetics [Link]
- Controllability Robustness Prediction >> PCR [Data]
- A convolutional neural network (CNN) is used to predict the controllability robustness of complex networks under malicious attacks.
- References:
- Predicting Network Controllability Robustness: A Convolutional Neural Network Approach in IEEE Transactions on Cybernetics [Link]
- Knowledge-based Controllability Robustness Prediction >> iPCR [Data]
- An improved version of PCR.
- Prior knowledge and multiple CNNs are used to predict the controllability robustness of complex networks.
- References:
- Knowledge-Based Prediction of Network Controllability Robustness in IEEE Transactions on Neural Networks and Learning Systems [Link]
- Controllability Robustness:
- q-snapback model >> QSN
- References:
- Toward Stronger Robustness of Network Controllability: A Snapback Network Model in IEEE Transactions on Circuits and Systems I: Regular Papers 2018
- Controllability Robustness Comparison >> CRCMP
- References:
- A Comparative Study on Controllability Robustness of Complex Networks in IEEE Transactions on Circuits and Systems II: Express Briefs 2019
- Empirical Necessary Condition >> ENC
- References:
- Towards Optimal Robustness of Network Controllability: An Empirical Necessary Condition in IEEE Transactions on Circuits and Systems I: Regular Papers 2020
- Henneberg-growth Networks >> HG
- References:
- Controllability Robustness of Henneberg-growth Complex Networks in IEEE Access 2022
- Evolutionary Benchmark Generator >> HFEBG
- HFEBG (Hierarchical Fitness Evolutionary Benchmark Generator)
- Both Kruskal-Wallis and Mann-Whitney tests are included
- ver. 3.0
- References:
- On Constructing Alternative Benchmark Suite for Evolutionary Algorithms in Swarm and Evolutionary Computation 2019
- Evolving Benchmark Functions for Optimization Algorithms in From Parallel to Emergent Computing 2019
- Evolving Benchmark Functions Using Kruskal-Wallis Test in GECCO 2018
- Non-revisiting Genetic Algorithm with Constant Memory >> cNrGACM
- cNrGA CM (Non-revisiting Genetic Algorithm with Constant Memory)
- References:
- Non-revisiting Genetic Algorithm with Adaptive Mutation Using Constant Memory in Memetic Computing 2016
- History-assisted Restart CMA-ES >> HRCMAES
- HRCMAES (History-assisted Restart Covariance Matrix Adaptation Evolution Strategy)
- ver. CEC 2019
- References:
- On-line Search History-assisted Restart Strategy for Covariance Matrix Adaptation Evolution Strategy in CEC 2019