{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"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":"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":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"1906.00091","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","created":"2019-05-31","cited_by_count":327},{"id":"1802.05799","title":"Horovod: fast and easy distributed deep learning in TensorFlow","created":"2018-02-15","cited_by_count":279},{"id":"2104.07857","title":"ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning","created":"2021-04-16","cited_by_count":256},{"id":"1810.05934","title":"A System for Massively Parallel Hyperparameter Tuning","created":"2018-10-13","cited_by_count":202},{"id":"1807.05358","title":"Beyond Data and Model Parallelism for Deep Neural Networks","created":"2018-07-14","cited_by_count":179},{"id":"2006.02464","title":"Serving DNNs like Clockwork: Performance Predictability from the Bottom Up","created":"2020-06-03","cited_by_count":120},{"id":"1806.03377","title":"PipeDream: Fast and Efficient Pipeline Parallel DNN Training","created":"2018-06-08","cited_by_count":117},{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116},{"id":"1802.04730","title":"Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions","created":"2018-02-13","cited_by_count":85},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82},{"id":"1901.05758","title":"Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads","created":"2019-01-17","cited_by_count":79},{"id":"2102.07988","title":"TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models","created":"2021-02-16","cited_by_count":75},{"id":"2008.12260","title":"Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning","created":"2020-08-27","cited_by_count":72},{"id":"1706.03292","title":"Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters","created":"2017-06-11","cited_by_count":57},{"id":"1904.10631","title":"Low-Memory Neural Network Training: A Technical Report","created":"2019-04-24","cited_by_count":57},{"id":"2008.09213","title":"Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads","created":"2020-08-20","cited_by_count":56},{"id":"1910.05124","title":"PipeMare: Asynchronous Pipeline Parallel DNN Training","created":"2019-10-09","cited_by_count":55},{"id":"2110.14222","title":"Sample Selection for Fair and Robust Training","created":"2021-10-27","cited_by_count":48},{"id":"1907.01484","title":"Themis: Fair and Efficient GPU Cluster Scheduling","created":"2019-07-02","cited_by_count":43},{"id":"2011.05497","title":"Understanding Training Efficiency of Deep Learning Recommendation Models at Scale","created":"2020-11-11","cited_by_count":43},{"id":"1312.7651","title":"Petuum: A New Platform for Distributed Machine Learning on Big Data","created":"2013-12-30","cited_by_count":35},{"id":"2010.12438","title":"Transferable Graph Optimizers for ML Compilers","created":"2020-10-21","cited_by_count":29},{"id":"2004.09910","title":"torchgpipe: On-the-fly Pipeline Parallelism for Training Giant Models","created":"2020-04-21","cited_by_count":26},{"id":"1909.02976","title":"SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle","created":"2019-09-06","cited_by_count":20},{"id":"2210.08803","title":"Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference","created":"2022-10-17","cited_by_count":20},{"id":"2103.09055","title":"OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learning","created":"2021-03-13","cited_by_count":18},{"id":"2103.10891","title":"Accelerating SLIDE Deep Learning on Modern CPUs: Vectorization, Quantizations, Memory Optimizations, and More","created":"2021-03-06","cited_by_count":15},{"id":"1909.06040","title":"DL2: A Deep Learning-driven Scheduler for Deep Learning Clusters","created":"2019-09-13","cited_by_count":14},{"id":"1610.09451","title":"KeystoneML: Optimizing Pipelines for Large-Scale Advanced Analytics","created":"2016-10-29","cited_by_count":13},{"id":"1801.00829","title":"On Optimizing Operator Fusion Plans for Large-Scale Machine Learning in SystemML","created":"2018-01-02","cited_by_count":13},{"id":"2204.05436","title":"Heterogeneous Acceleration Pipeline for Recommendation System Training","created":"2022-04-11","cited_by_count":13},{"id":"1807.02037","title":"TFLMS: Large Model Support in TensorFlow by Graph Rewriting","created":"2018-07-05","cited_by_count":12},{"id":"1802.04819","title":"SLAQ: Quality-Driven Scheduling for Distributed Machine Learning","created":"2018-02-13","cited_by_count":10},{"id":"1801.00936","title":"Online Job Scheduling in Distributed Machine Learning Clusters","created":"2018-01-03","cited_by_count":9},{"id":"2011.01112","title":"Scheduling Real-time Deep Learning Services as Imprecise Computations","created":"2020-11-02","cited_by_count":8},{"id":"2102.08481","title":"THIA: Accelerating Video Analytics using Early Inference and Fine-Grained Query Planning","created":"2021-02-16","cited_by_count":8},{"id":"2112.02905","title":"Parameter Efficient Deep Probabilistic Forecasting","created":"2021-12-06","cited_by_count":8},{"id":"2103.06124","title":"Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems","created":"2021-02-24","cited_by_count":7},{"id":"2104.00501","title":"NuPS: A Parameter Server for Machine Learning with Non-Uniform Parameter Access","created":"2021-04-01","cited_by_count":7},{"id":"2107.06469","title":"Model-Parallel Model Selection for Deep Learning Systems","created":"2021-07-14","cited_by_count":6},{"id":"2205.03960","title":"Neural Architecture Search using Property Guided Synthesis","created":"2022-05-08","cited_by_count":4},{"id":"2301.02691","title":"Systems for Parallel and Distributed Large-Model Deep Learning Training","created":"2023-01-06","cited_by_count":4},{"id":"2002.02885","title":"Understanding and Optimizing Packed Neural Network Training for Hyper-Parameter Tuning","created":"2020-02-07","cited_by_count":3},{"id":"2108.13732","title":"Deep Learning on Edge TPUs","created":"2021-08-31","cited_by_count":3},{"id":"2308.08500","title":"InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models","created":"2023-08-13","cited_by_count":3},{"id":"2110.07029","title":"Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers","created":"2021-10-13","cited_by_count":2},{"id":"1909.11985","title":"Elastic deep learning in multi-tenant GPU cluster","created":"2019-09-26","cited_by_count":1}],"next_cursor":null}