{"total":98,"rows":[{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2110.13981","title":"CHIP: CHannel Independence-based Pruning for Compact Neural Networks","created":"2021-10-26","cited_by_count":78,"area":null},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50,"area":null},{"id":"2302.04089","title":"ZipLM: Inference-Aware Structured Pruning of Language Models","created":"2023-02-07","cited_by_count":49,"area":null},{"id":"2302.05071","title":"EVC: Towards Real-Time Neural Image Compression with Mask Decay","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2103.05861","title":"Manifold Regularized Dynamic Network Pruning","created":"2021-03-10","cited_by_count":43,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36,"area":null},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33,"area":null},{"id":"2106.02898","title":"Dynamic Resolution Network","created":"2021-06-05","cited_by_count":31,"area":null},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31,"area":null},{"id":"2102.03214","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","created":"2021-02-05","cited_by_count":30,"area":null},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2105.03193","title":"Network Pruning That Matters: A Case Study on Retraining Variants","created":"2021-05-07","cited_by_count":25,"area":null},{"id":"2110.08232","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23,"area":null},{"id":"2112.09852","title":"LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision","created":"2021-12-18","cited_by_count":20,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"id":"2105.14797","title":"RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks","created":"2021-05-31","cited_by_count":19,"area":null},{"id":"2110.01397","title":"RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging","created":"2021-09-30","cited_by_count":19,"area":null},{"id":"2111.03044","title":"A Unified Approach to Coreset Learning","created":"2021-11-04","cited_by_count":18,"area":null},{"id":"2207.12534","title":"Trainability Preserving Neural Pruning","created":"2022-07-25","cited_by_count":16,"area":null},{"id":"2212.03537","title":"Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning","created":"2022-12-07","cited_by_count":16,"area":null},{"id":"2301.05219","title":"Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning","created":"2023-01-12","cited_by_count":16,"area":null},{"id":"2105.10065","title":"A Probabilistic Approach to Neural Network Pruning","created":"2021-05-20","cited_by_count":15,"area":null},{"id":"2201.03297","title":"GhostNets on Heterogeneous Devices via Cheap Operations","created":"2022-01-10","cited_by_count":15,"area":null},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2303.05151","title":"Provable Data Subset Selection For Efficient Neural Network Training","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2106.12718","title":"Sparse Flows: Pruning Continuous-depth Models","created":"2021-06-24","cited_by_count":13,"area":null},{"id":"2209.02869","title":"Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2303.08595","title":"Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions","created":"2023-03-14","cited_by_count":11,"area":null},{"id":"2303.13097","title":"CP$^3$: Channel Pruning Plug-in for Point-based Networks","created":"2023-03-23","cited_by_count":10,"area":null},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10,"area":null},{"id":"2108.00065","title":"Model Preserving Compression for Neural Networks","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2206.02976","title":"Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2207.04089","title":"SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance","created":"2022-07-08","cited_by_count":9,"area":null},{"id":"2303.11923","title":"Performance-aware Approximation of Global Channel Pruning for Multitask CNNs","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2403.19490","title":"Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2301.07966","title":"Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions","created":"2023-01-19","cited_by_count":8,"area":null},{"id":"2307.15049","title":"Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models","created":"2023-07-27","cited_by_count":7,"area":"mllm"},{"id":"2203.03009","title":"Coresets for Data Discretization and Sine Wave Fitting","created":"2022-03-06","cited_by_count":6,"area":null},{"id":"2203.04075","title":"Obstacle Aware Sampling for Path Planning","created":"2022-03-08","cited_by_count":6,"area":null},{"id":"2504.16277","title":"DataS^3: Dataset Subset Selection for Specialization","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2209.11064","title":"Deep Learning on Home Drone: Searching for the Optimal Architecture","created":"2022-09-21","cited_by_count":5,"area":null},{"id":"2303.09736","title":"Dynamic Structure Pruning for Compressing CNNs","created":"2023-03-17","cited_by_count":5,"area":null},{"id":"2411.00147","title":"Mutual Information Preserving Neural Network Pruning","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2304.00280","title":"Progressive Channel-Shrinking Network","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2402.17862","title":"REPrune: Channel Pruning via Kernel Representative Selection","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2405.15006","title":"A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2104.02822","title":"Low-Regret Active learning","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2201.10520","title":"Adaptive Activation-based Structured Pruning","created":"2022-01-21","cited_by_count":3,"area":null},{"id":"2205.04650","title":"Robust Learning of Parsimonious Deep Neural Networks","created":"2022-05-10","cited_by_count":3,"area":null},{"id":"2304.06305","title":"Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution","created":"2023-04-13","cited_by_count":3,"area":null},{"id":"2312.12483","title":"SCoTTi: Save Computation at Training Time with an adaptive framework","created":"2023-12-19","cited_by_count":3,"area":null},{"id":"2405.03089","title":"Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Composition","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2508.13836","title":"One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2607.06915","title":"Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2310.06344","title":"Filter Pruning For CNN With Enhanced Linear Representation Redundancy","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2407.15875","title":"Shapley Pruning for Neural Network Compression","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2605.30337","title":"Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.02721","title":"Provable Pruning for Efficient 3D Gaussian Splatting via Coresets","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2110.12477","title":"Exploring Gradient Flow Based Saliency for DNN Model Compression","created":"2021-10-24","cited_by_count":1,"area":null},{"id":"2110.15192","title":"RGP: Neural Network Pruning through Its Regular Graph Structure","created":"2021-10-28","cited_by_count":1,"area":null},{"id":"2112.04905","title":"i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2204.07412","title":"End-to-End Sensitivity-Based Filter Pruning","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2309.13077","title":"A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.06218","title":"SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2312.10181","title":"Integrating Fairness and Model Pruning Through Bi-level Optimization","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2509.11711","title":"The Quest for Universal Master Key Filters in DS-CNNs","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2510.20800","title":"Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2511.19566","title":"ModHiFi: Identifying High Fidelity predictive components for Model Modification","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2512.02967","title":"Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2512.06288","title":"Theoretical Compression Bounds for Wide Multilayer Perceptrons","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2601.03658","title":"Group and Exclusive Sparse Regularization-based Continual Learning of CNNs","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2106.02914","title":"Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2108.13591","title":"AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks","created":"2021-08-31","cited_by_count":0,"area":null},{"id":"2111.14302","title":"Self-supervised Feature-Gate Coupling for Dynamic Network Pruning","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2112.00954","title":"Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2209.03534","title":"CWP: Instance complexity weighted channel-wise soft masks for network pruning","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2210.06299","title":"SeKron: A Decomposition Method Supporting Many Factorization Structures","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2210.11114","title":"Pruning by Active Attention Manipulation","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2301.11063","title":"Rewarded meta-pruning: Meta Learning with Rewards for Channel Pruning","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2303.17061","title":"A Tensor-based Convolutional Neural Network for Small Dataset Classification","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2305.18448","title":"Neural Network Reduction with Guided Regularizers","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2308.04470","title":"D-Score: A Synapse-Inspired Approach for Filter Pruning","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2311.04158","title":"Computing Approximate $\\ell_p$ Sensitivities","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2311.10549","title":"Archtree: on-the-fly tree-structured exploration for latency-aware pruning of deep neural networks","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2312.11555","title":"CR-SFP: Learning Consistent Representation for Soft Filter Pruning","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2405.10802","title":"Reduced storage direct tensor ring decomposition for convolutional neural networks compression","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2409.03777","title":"A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2507.14170","title":"Catalyst: a Novel Regularizer for Structured Pruning with Auxiliary Extension of Parameter Space","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2509.10526","title":"Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning","created":"2025-09-04","cited_by_count":0,"area":"deeprl"},{"id":"2607.06982","title":"EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.11473","title":"Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.21752","title":"Width-Independent Compressibility of Deep Neural Networks","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":null}