{"list":"other","total":61,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2012.04221","title":"Ditto: Fair and Robust Federated Learning Through Personalization","created":"2020-12-08","cited_by_count":672},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"2012.08565","title":"Personalized Federated Learning with First Order Model Optimization","created":"2020-12-15","cited_by_count":201},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103},{"id":"1906.02773","title":"One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers","created":"2019-06-06","cited_by_count":102},{"id":"2012.06908","title":"The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models","created":"2020-12-12","cited_by_count":91},{"id":"1911.09723","title":"Fast Sparse ConvNets","created":"2019-11-21","cited_by_count":86},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74},{"id":"2006.09081","title":"Progressive Skeletonization: Trimming more fat from a network at initialization","created":"2020-06-16","cited_by_count":64},{"id":"2310.10049","title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models","created":"2023-10-16","cited_by_count":63},{"id":"2008.03371","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","created":"2020-08-07","cited_by_count":60},{"id":"2106.04502","title":"Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing","created":"2021-06-08","cited_by_count":58},{"id":"1908.09979","title":"DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures","created":"2019-08-27","cited_by_count":56},{"id":"2112.09824","title":"Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better","created":"2021-12-18","cited_by_count":55},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49},{"id":"2302.04089","title":"ZipLM: Inference-Aware Structured Pruning of Language Models","created":"2023-02-07","cited_by_count":49},{"id":"2209.15328","title":"Sparse Random Networks for Communication-Efficient Federated Learning","created":"2022-09-30","cited_by_count":32},{"id":"2303.10464","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","created":"2023-03-18","cited_by_count":28},{"id":"2005.10761","title":"rTop-k: A Statistical Estimation Approach to Distributed SGD","created":"2020-05-21","cited_by_count":27},{"id":"2105.00562","title":"Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity","created":"2021-05-02","cited_by_count":27},{"id":"2112.15579","title":"Single-Shot Pruning for Offline Reinforcement Learning","created":"2021-12-31","cited_by_count":21},{"id":"2110.14205","title":"FedPrune: Towards Inclusive Federated Learning","created":"2021-10-27","cited_by_count":12},{"id":"2208.13092","title":"Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge","created":"2022-08-27","cited_by_count":12},{"id":"2104.12501","title":"Communication-Efficient and Personalized Federated Lottery Ticket Learning","created":"2021-04-26","cited_by_count":10},{"id":"2310.00247","title":"Bridging the Gap Between Foundation Models and Heterogeneous Federated Learning","created":"2023-09-30","cited_by_count":9},{"id":"1912.03896","title":"Explicit Group Sparse Projection with Applications to Deep Learning and NMF","created":"2019-12-09","cited_by_count":6},{"id":"2106.14126","title":"AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning","created":"2021-06-27","cited_by_count":4},{"id":"2303.16999","title":"PopSparse: Accelerated block sparse matrix multiplication on IPU","created":"2023-03-29","cited_by_count":3},{"id":"2304.07488","title":"SalientGrads: Sparse Models for Communication Efficient and Data Aware Distributed Federated Training","created":"2023-04-15","cited_by_count":1}],"next_cursor":null}