{"total":73,"rows":[{"id":"2102.03322","title":"CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks","created":"2021-02-05","cited_by_count":119,"area":null},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110,"area":null},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84,"area":null},{"id":"2105.01571","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","created":"2021-05-03","cited_by_count":45,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"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":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2210.12089","title":"A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges","created":"2022-10-21","cited_by_count":30,"area":null},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30,"area":null},{"id":"2109.02220","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","created":"2021-09-06","cited_by_count":29,"area":null},{"id":"2308.10134","title":"AutoReP: Automatic ReLU Replacement for Fast Private Network Inference","created":"2023-08-20","cited_by_count":29,"area":null},{"id":"2309.14331","title":"LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference","created":"2023-09-25","cited_by_count":27,"area":null},{"id":"2106.09857","title":"Effective Model Sparsification by Scheduled Grow-and-Prune Methods","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2211.10575","title":"Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants","created":"2022-11-19","cited_by_count":24,"area":null},{"id":"2105.04319","title":"A Bregman Learning Framework for Sparse Neural Networks","created":"2021-05-10","cited_by_count":15,"area":null},{"id":"2206.04662","title":"DiSparse: Disentangled Sparsification for Multitask Model Compression","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"area":"moe"},{"id":"2103.12002","title":"On the Robustness of Monte Carlo Dropout Trained with Noisy Labels","created":"2021-03-22","cited_by_count":11,"area":null},{"id":"2410.01434","title":"Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2104.08700","title":"Lottery Jackpots Exist in Pre-trained Models","created":"2021-04-18","cited_by_count":10,"area":null},{"id":"2210.01910","title":"Learning Signal Temporal Logic through Neural Network for Interpretable Classification","created":"2022-10-04","cited_by_count":10,"area":null},{"id":"2311.02104","title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2209.14881","title":"Sequential Attention for Feature Selection","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2405.06670","title":"TLINet: Differentiable Neural Network Temporal Logic Inference","created":"2024-05-03","cited_by_count":9,"area":null},{"id":"2204.03227","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2302.14670","title":"Balanced Training for Sparse GANs","created":"2023-02-28","cited_by_count":8,"area":null},{"id":"2406.10576","title":"Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient","created":"2024-06-15","cited_by_count":6,"area":null},{"id":"2104.05435","title":"Neural Network for Weighted Signal Temporal Logic","created":"2021-04-08","cited_by_count":5,"area":null},{"id":"2107.05330","title":"Sparse Personalized Federated Learning","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2201.06776","title":"Pruning-aware Sparse Regularization for Network Pruning","created":"2022-01-18","cited_by_count":5,"area":null},{"id":"2209.09688","title":"Sparse Vicious Attacks on Graph Neural Networks","created":"2022-09-20","cited_by_count":5,"area":null},{"id":"2503.16916","title":"Temporal Action Detection Model Compression by Progressive Block Drop","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2103.15767","title":"[Reproducibility Report] Rigging the Lottery: Making All Tickets Winners","created":"2021-03-29","cited_by_count":4,"area":null},{"id":"2203.13517","title":"Sparse Federated Learning with Hierarchical Personalized Models","created":"2022-03-25","cited_by_count":4,"area":null},{"id":"2208.06029","title":"Interaction Decompositions for Tensor Network Regression","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2209.01173","title":"Optimal bump functions for shallow ReLU networks: Weight decay, depth separation and the curse of dimensionality","created":"2022-09-02","cited_by_count":4,"area":null},{"id":"2211.03721","title":"Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition","created":"2022-11-07","cited_by_count":4,"area":null},{"id":"2307.08771","title":"UPSCALE: Unconstrained Channel Pruning","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2407.21407","title":"Deep Fr\\'echet Regression","created":"2024-07-31","cited_by_count":4,"area":null},{"id":"2312.13211","title":"DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2406.08804","title":"DIET: Customized Slimming for Incompatible Networks in Sequential Recommendation","created":"2024-06-13","cited_by_count":3,"area":null},{"id":"2503.22764","title":"Boosting Large Language Models with Mask Fine-Tuning","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2110.03298","title":"End-to-End Supermask Pruning: Learning to Prune Image Captioning Models","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2304.11237","title":"Effective Neural Network $L_0$ Regularization With BinMask","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2401.11664","title":"Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM","created":"2024-01-22","cited_by_count":2,"area":null},{"id":"2408.02839","title":"Mini-batch Estimation for Deep Cox Models: Statistical Foundations and Practical Guidance","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2505.17542","title":"Graph Inverse Style Transfer for Counterfactual Explainability","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2305.10964","title":"Learning Activation Functions for Sparse Neural Networks","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2306.13515","title":"Binary domain generalization for sparsifying binary neural networks","created":"2023-06-23","cited_by_count":1,"area":null},{"id":"2312.05828","title":"Sparse Multitask Learning for Efficient Neural Representation of Motor Imagery and Execution","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2409.03489","title":"Sparsifying Parametric Models with L0 Regularization","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2409.19391","title":"Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training","created":"2024-09-28","cited_by_count":1,"area":null},{"id":"2502.03658","title":"Advancing Weight and Channel Sparsification with Enhanced Saliency","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2505.03923","title":"SAND: One-Shot Feature Selection with Additive Noise Distortion","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2101.09492","title":"MinConvNets: A new class of multiplication-less Neural Networks","created":"2021-01-23","cited_by_count":0,"area":null},{"id":"2102.09727","title":"Learning Dynamic BERT via Trainable Gate Variables and a Bi-modal Regularizer","created":"2021-02-19","cited_by_count":0,"area":null},{"id":"2103.10629","title":"Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2103.16013","title":"Training Sparse Neural Network by Constraining Synaptic Weight on Unit Lp Sphere","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2108.02313","title":"BEANNA: A Binary-Enabled Architecture for Neural Network Acceleration","created":"2021-08-04","cited_by_count":0,"area":null},{"id":"2112.03487","title":"Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers","created":"2021-12-07","cited_by_count":0,"area":null},{"id":"2207.04974","title":"Sparsifying Binary Networks","created":"2022-07-11","cited_by_count":0,"area":null},{"id":"2304.00935","title":"Learning Sparsity of Representations with Discrete Latent Variables","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2304.08411","title":"Evil from Within: Machine Learning Backdoors through Hardware Trojans","created":"2023-04-17","cited_by_count":0,"area":null},{"id":"2312.01653","title":"An End-to-End Network Pruning Pipeline with Sparsity Enforcement","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2403.08265","title":"Random Search as a Baseline for Sparse Neural Network Architecture Search","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2405.20623","title":"Sparse-ProxSkip: Accelerated Sparse-to-Sparse Training in Federated Learning","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2411.01238","title":"Efficient Sparse Training with Structured Dropout","created":"2024-11-02","cited_by_count":0,"area":null},{"id":"2505.21791","title":"Global Minimizers of $\\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2508.06551","title":"Slice or the Whole Pie? Utility Control for AI Models","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2511.09901","title":"Explore and Establish Synergistic Effects Between Weight Pruning and Coreset Selection in Neural Network Training","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2603.19939","title":"Timestep-Aware Block Masking for Efficient Diffusion Model Inference","created":"2026-03-20","cited_by_count":0,"area":"diffusion"},{"id":"2605.28762","title":"Deep Neural Networks for Doubly Robust Estimation with Nonprobability Survey Samples","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}