 MDP: Multidimensional Vision Model Pruning with Latency ConstraintComputer Vision and Pattern Recognition (CVPR), 2025 |
 Advancing Weight and Channel Sparsification with Enhanced SaliencyIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2025 |
 Enhanced Sparsification via Stimulative TrainingEuropean Conference on Computer Vision (ECCV), 2024 |
 A Proximal Algorithm for Network SlimmingInternational Conference on Machine Learning, Optimization, and Data Science (MOD), 2023 |
 Magnitude Attention-based Dynamic PruningExpert systems with applications (ESWA), 2023 |
 Low Rank Optimization for Efficient Deep Learning: Making A Balance
between Compact Architecture and Fast TrainingJournal of Systems Engineering and Electronics (JSEE), 2023 |
 Learning to Unlearn: Instance-wise Unlearning for Pre-trained
ClassifiersAAAI Conference on Artificial Intelligence (AAAI), 2023 |
 Statistical guarantees for sparse deep learningAStA Advances in Statistical Analysis (AStA), 2022 |
 Soft Masking for Cost-Constrained Channel PruningEuropean Conference on Computer Vision (ECCV), 2022 |
 Structural Pruning via Latency-Saliency KnapsackNeural Information Processing Systems (NeurIPS), 2022 |
 Double Attention-based Lightweight Network for Plant Pest RecognitionInternational Conference on Neural Information Processing (ICONIP), 2022 |
 Sequential Attention for Feature SelectionInternational Conference on Learning Representations (ICLR), 2022 |
 Learning sparse auto-encoders for green AI image codingIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 Entropy Induced Pruning Framework for Convolutional Neural NetworksAAAI Conference on Artificial Intelligence (AAAI), 2022 |
 DropNet: Reducing Neural Network Complexity via Iterative PruningInternational Conference on Machine Learning (ICML), 2020 |
 Scaling Private Deep Learning with Low-Rank and Sparse GradientsJournal of Information Processing (JIP), 2022 |
 Optimal channel selection with discrete QCQPInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 |
 Pruning-aware Sparse Regularization for Network PruningMachine Intelligence Research (MIR), 2022 |
 Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIIEEE Transactions on Knowledge and Data Engineering (TKDE), 2021 Jiangchao Yao Shengyu Zhang Yang Yao Feng Wang Jianxin Ma ...Kun Kuang Chao-Xiang Wu Leilei Gan Jingren Zhou Hongxia Yang |
 When to Prune? A Policy towards Early Structural PruningComputer Vision and Pattern Recognition (CVPR), 2021 |
 Searching for Minimal Optimal Neural NetworksStatistics and Probability Letters (Stat. Probab. Lett.), 2021 |
 Layer-wise Model Pruning based on Mutual InformationConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
