{"list":"other","total":71,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"2102.02079","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","created":"2021-02-03","cited_by_count":568},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"id":"1911.00222","title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","created":"2019-11-01","cited_by_count":536},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2006.04088","title":"An Efficient Framework for Clustered Federated Learning","created":"2020-06-07","cited_by_count":511},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"2105.10056","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","created":"2021-05-20","cited_by_count":383},{"id":"2003.13461","title":"Adaptive Personalized Federated Learning","created":"2020-03-30","cited_by_count":358},{"id":"2105.00243","title":"FedProto: Federated Prototype Learning across Heterogeneous Clients","created":"2021-05-01","cited_by_count":352},{"id":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"id":"2007.03797","title":"Personalized Cross-Silo Federated Learning on Non-IID Data","created":"2020-07-07","cited_by_count":283},{"id":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"2305.05644","title":"Towards Building the Federated GPT: Federated Instruction Tuning","created":"2023-05-09","cited_by_count":185},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149},{"id":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147},{"id":"2002.04758","title":"Salvaging Federated Learning by Local Adaptation","created":"2020-02-12","cited_by_count":142},{"id":"2402.08562","title":"Higher Layers Need More LoRA Experts","created":"2024-02-13","cited_by_count":102},{"id":"2308.06522","title":"SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models","created":"2023-08-12","cited_by_count":93},{"id":"2402.11505","title":"Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources","created":"2024-02-18","cited_by_count":93},{"id":"2212.10025","title":"When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods","created":"2022-12-20","cited_by_count":75},{"id":"2406.17706","title":"FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model","created":"2024-06-25","cited_by_count":74},{"id":"2006.16765","title":"Federated Mutual Learning","created":"2020-06-27","cited_by_count":71},{"id":"2310.15080","title":"Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization","created":"2023-10-23","cited_by_count":65},{"id":"2308.12305","title":"FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning","created":"2023-08-21","cited_by_count":60},{"id":"2406.07925","title":"FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning","created":"2024-06-12","cited_by_count":59},{"id":"2312.06353","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","created":"2023-12-11","cited_by_count":55},{"id":"2403.19211","title":"Dual-Personalizing Adapter for Federated Foundation Models","created":"2024-03-28","cited_by_count":55},{"id":"2308.15367","title":"Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation","created":"2023-08-29","cited_by_count":54},{"id":"2110.08394","title":"Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning","created":"2021-10-15","cited_by_count":53},{"id":"2204.05011","title":"FederatedScope: A Flexible Federated Learning Platform for Heterogeneity","created":"2022-04-11","cited_by_count":53},{"id":"2310.13283","title":"pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning","created":"2023-10-20","cited_by_count":40},{"id":"2406.12433","title":"LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations","created":"2024-06-18","cited_by_count":40},{"id":"2402.17702","title":"The SCIP Optimization Suite 9.0","created":"2024-02-27","cited_by_count":37},{"id":"1912.06733","title":"Private Federated Learning with Domain Adaptation","created":"2019-12-13","cited_by_count":36},{"id":"2310.09130","title":"Split-and-Denoise: Protect large language model inference with local differential privacy","created":"2023-10-13","cited_by_count":32},{"id":"2107.06724","title":"Federated Mixture of Experts","created":"2021-07-14","cited_by_count":28},{"id":"2408.11304","title":"FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts","created":"2024-08-21","cited_by_count":27},{"id":"2402.01350","title":"pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning","created":"2024-02-02","cited_by_count":24},{"id":"2010.02056","title":"Specialized federated learning using a mixture of experts","created":"2020-10-05","cited_by_count":23},{"id":"2012.15589","title":"PFL-MoE: Personalized Federated Learning Based on Mixture of Experts","created":"2020-12-31","cited_by_count":21},{"id":"2308.09160","title":"FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning","created":"2023-08-17","cited_by_count":21},{"id":"2410.10114","title":"Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models","created":"2024-10-14","cited_by_count":17},{"id":"2302.06637","title":"PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees","created":"2023-02-13","cited_by_count":15},{"id":"2404.13238","title":"Personalized Wireless Federated Learning for Large Language Models","created":"2024-04-20","cited_by_count":11},{"id":"2411.02115","title":"FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained Aggregation","created":"2024-11-04","cited_by_count":11},{"id":"2410.10926","title":"Federated Data-Efficient Instruction Tuning for Large Language Models","created":"2024-10-14","cited_by_count":10},{"id":"2409.13931","title":"On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists","created":"2024-09-20","cited_by_count":6},{"id":"2206.07832","title":"Adaptive Expert Models for Personalization in Federated Learning","created":"2022-06-15","cited_by_count":4},{"id":"2402.16919","title":"Personalized Federated Instruction Tuning via Neural Architecture Search","created":"2024-02-26","cited_by_count":3},{"id":"2410.03497","title":"Collaborative and Efficient Personalization with Mixtures of Adaptors","created":"2024-10-04","cited_by_count":1}],"next_cursor":null}