| Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware S Liu, DC Mocanu, ARR Matavalam, Y Pei, M Pechenizkiy Neural Computing and Applications 33, 2589-2604, 2021 | 60 | 2021 |
| Do we actually need dense over-parameterization? in-time over-parameterization in sparse training S Liu, L Yin, DC Mocanu, M Pechenizkiy ICML2021, International Conference on Machine Learning, 2021 | 44 | 2021 |
| Sparse Training via Boosting Pruning Plasticity with Neuroregeneration S Liu, T Chen, X Chen, Z Atashgahi, L Yin, H Kou, L Shen, M Pechenizkiy, ... NeurIPS2021, Advances in Neural Information Processing Systems, 2021 | 38 | 2021 |
| Efficient and effective training of sparse recurrent neural networks S Liu, I Nimah, V Menkovski, DC Mocanu, M Pechenizkiy Neural Computing and Applications, 1-12, 2021 | 27* | 2021 |
| Selfish sparse RNN training S Liu, DC Mocanu, Y Pei, M Pechenizkiy ICML2021, International Conference on Machine Learning, 2021 | 23 | 2021 |
| Topological Insights into Sparse Neural Networks S Liu, T Van der Lee, A Yaman, Z Atashgahi, D Ferraro, G Sokar, ... ECML2020, European Conference on Machine Learning, 2020 | 18 | 2020 |
| The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training S Liu, T Chen, X Chen, L Shen, DC Mocanu, Z Wang, M Pechenizkiy ICLR2022, The International Conference on Learning Representations, 2022 | 15 | 2022 |
| Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity S Liu, T Chen, Z Atashgahi, X Chen, G Sokar, E Mocanu, M Pechenizkiy, ... ICLR2022, The International Conference on Learning Representations, 2021 | 15 | 2021 |
| More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity S Liu, T Chen, X Chen, X Chen, Q Xiao, B Wu, M Pechenizkiy, D Mocanu, ... ICLR2023, The International Conference on Learning Representations, 2022 | 11 | 2022 |
| A Brain-inspired Algorithm for Training Highly Sparse Neural Networks Z Atashgahi, J Pieterse, S Liu, DC Mocanu, R Veldhuis, M Pechenizkiy Machine Learning Journal (ECML-PKDD 2022 journal track), 2019 | 11* | 2019 |
| Learning Sparse Neural Networks for Better Generalization S Liu IJCAI2020 Doctoral Consortium, International Joint Conference on Artificial
, 2020 | 7 | 2020 |
| Achieving personalized federated learning with sparse local models T Huang, S Liu, L Shen, F He, W Lin, D Tao arXiv preprint arXiv:2201.11380, 2022 | 5 | 2022 |
| On improving deep learning generalization with adaptive sparse connectivity S Liu, DC Mocanu, M Pechenizkiy ICML 2019 workshop of Understanding and Improving Generalization in Deep
, 2019 | 5 | 2019 |
| Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance S Liu, Y Tian, T Chen, L Shen arXiv preprint arXiv:2203.02770, 2022 | 2 | 2022 |
| Hierarchical semantic segmentation using psychometric learning L Yin, V Menkovski, S Liu, M Pechenizkiy arXiv preprint arXiv:2107.03212, 2021 | 2 | 2021 |
| FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity S Liu, T Chen, Z Atashgahi, X Chen, G Sokar, E Mocanu, M Pechenizkiy, ... arXiv preprint arXiv:2106.14568, 2021 | 2 | 2021 |
| Dynamic Sparse Network for Time Series Classification: Learning What to See Q Xiao, B Wu, Y Zhang, S Liu, M Pechenizkiy, E Mocanu, DC Mocanu NeurIPS2022, 36th Annual Conference on Neural Information Processing Systems, 2022 | 1 | 2022 |
| Sparse Neural Network Training with In-Time Over-Parameterization S Liu PhD thesis, UT Eindhoven, 2022 | 1 | 2022 |
| You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets T Huang, T Chen, M Fang, V Menkovski, J Zhao, L Yin, Y Pei, DC Mocanu, ... LoG2022, Learning on Graphs Conference (Best Paper Award), 2022 | | 2022 |
| Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost L Yin, S Liu, F Meng, T Huang, V Menkovski, M Pechenizkiy AAAI2023, Thirty-Seventh AAAI Conference on Artificial Intelligence, 2022 | | 2022 |
Mykola PechenizkiyEindhoven University of TechnologyPatvirtintas el. paštas tue.nl
