{"list":"other","total":68,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1906.00091","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","created":"2019-05-31","cited_by_count":327},{"id":"1906.05433","title":"Tackling Climate Change with Machine Learning","created":"2019-06-10","cited_by_count":265},{"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":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"id":"2107.07566","title":"Internet-Augmented Dialogue Generation","created":"2021-07-15","cited_by_count":217},{"id":"1806.00187","title":"Scaling Neural Machine Translation","created":"2018-06-01","cited_by_count":204},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"1911.02549","title":"MLPerf Inference Benchmark","created":"2019-11-06","cited_by_count":199},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"2104.10201","title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","created":"2021-04-20","cited_by_count":148},{"id":"1910.10252","title":"Federated Evaluation of On-device Personalization","created":"2019-10-22","cited_by_count":147},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1906.04329","title":"Federated Learning for Emoji Prediction in a Mobile Keyboard","created":"2019-06-11","cited_by_count":118},{"id":"1910.01500","title":"MLPerf Training Benchmark","created":"2019-10-02","cited_by_count":115},{"id":"2104.13963","title":"Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples","created":"2021-04-28","cited_by_count":114},{"id":"1910.05446","title":"On Empirical Comparisons of Optimizers for Deep Learning","created":"2019-10-11","cited_by_count":103},{"id":"1904.02877","title":"Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours","created":"2019-04-05","cited_by_count":87},{"id":"1906.03109","title":"The Architectural Implications of Facebook's DNN-based Personalized Recommendation","created":"2019-06-06","cited_by_count":83},{"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":"2104.05158","title":"Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models","created":"2021-04-12","cited_by_count":78},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"2011.02839","title":"Chasing Carbon: The Elusive Environmental Footprint of Computing","created":"2020-10-28","cited_by_count":72},{"id":"2003.05622","title":"Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems","created":"2020-03-12","cited_by_count":60},{"id":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58},{"id":"2005.04305","title":"Measuring the Algorithmic Efficiency of Neural Networks","created":"2020-05-08","cited_by_count":52},{"id":"2010.06537","title":"Can Federated Learning Save The Planet?","created":"2020-10-13","cited_by_count":52},{"id":"1912.12953","title":"RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing","created":"2019-12-30","cited_by_count":49},{"id":"2010.09435","title":"An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage","created":"2020-10-14","cited_by_count":45},{"id":"1911.08354","title":"Energy Usage Reports: Environmental awareness as part of algorithmic accountability","created":"2019-11-19","cited_by_count":44},{"id":"2011.05497","title":"Understanding Training Efficiency of Deep Learning Recommendation Models at Scale","created":"2020-11-11","cited_by_count":43},{"id":"2106.11750","title":"Carbon-Aware Computing for Datacenters","created":"2021-06-11","cited_by_count":41},{"id":"1907.04471","title":"Neural Input Search for Large Scale Recommendation Models","created":"2019-07-10","cited_by_count":39},{"id":"2107.08147","title":"AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning","created":"2021-07-16","cited_by_count":39},{"id":"2010.10784","title":"Learning to Embed Categorical Features without Embedding Tables for Recommendation","created":"2020-10-21","cited_by_count":38},{"id":"2007.06434","title":"Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction","created":"2020-06-29","cited_by_count":37},{"id":"2102.00075","title":"RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference","created":"2021-01-29","cited_by_count":35},{"id":"2011.02084","title":"Understanding Capacity-Driven Scale-Out Neural Recommendation Inference","created":"2020-11-04","cited_by_count":29},{"id":"2109.07437","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","created":"2021-09-15","cited_by_count":26},{"id":"2102.11245","title":"Silent Data Corruptions at Scale","created":"2021-02-22","cited_by_count":23},{"id":"1808.01550","title":"Designing Adaptive Neural Networks for Energy-Constrained Image Classification","created":"2018-08-05","cited_by_count":18},{"id":"1902.04610","title":"Salus: Fine-Grained GPU Sharing Primitives for Deep Learning Applications","created":"2019-02-12","cited_by_count":17},{"id":"2106.11890","title":"Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization","created":"2021-06-22","cited_by_count":15},{"id":"2107.04984","title":"SVP-CF: Selection via Proxy for Collaborative Filtering Data","created":"2021-07-11","cited_by_count":14},{"id":"2104.00031","title":"NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization","created":"2021-03-31","cited_by_count":13},{"id":"2011.02999","title":"CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery","created":"2020-11-05","cited_by_count":11},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7},{"id":"2108.06738","title":"Socio-Technological Challenges and Opportunities: Paths Forward","created":"2021-08-15","cited_by_count":2}],"next_cursor":null}