{"list":"other","total":106,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2011.02260","title":"Graph Neural Networks in Recommender Systems: A Survey","created":"2020-11-04","cited_by_count":494},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1608.00367","title":"Accelerating the Super-Resolution Convolutional Neural Network","created":"2016-08-01","cited_by_count":394},{"id":"1804.09458","title":"Dynamic Few-Shot Visual Learning without Forgetting","created":"2018-04-25","cited_by_count":385},{"id":"1707.09835","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","created":"2017-07-31","cited_by_count":379},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"1906.00091","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","created":"2019-05-31","cited_by_count":327},{"id":"2008.13535","title":"DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems","created":"2020-08-19","cited_by_count":327},{"id":"1811.00855","title":"Session-based Recommendation with Graph Neural Networks","created":"2018-11-01","cited_by_count":312},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274},{"id":"1602.05352","title":"Recommendations as Treatments: Debiasing Learning and Evaluation","created":"2016-02-17","cited_by_count":248},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177},{"id":"2007.15801","title":"Finite Versus Infinite Neural Networks: an Empirical Study","created":"2020-07-31","cited_by_count":157},{"id":"2110.07580","title":"Graph Condensation for Graph Neural Networks","created":"2021-10-14","cited_by_count":150},{"id":"2204.08499","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","created":"2022-04-18","cited_by_count":147},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111},{"id":"2009.07999","title":"Distilled One-Shot Federated Learning","created":"2020-09-17","cited_by_count":109},{"id":"1910.02551","title":"Soft-Label Dataset Distillation and Text Dataset Distillation","created":"2019-10-06","cited_by_count":107},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105},{"id":"1910.08233","title":"Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data","created":"2019-10-18","cited_by_count":104},{"id":"1912.07768","title":"Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data","created":"2019-12-17","cited_by_count":104},{"id":"2206.02916","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","created":"2022-06-06","cited_by_count":104},{"id":"2206.07746","title":"Condensing Graphs via One-Step Gradient Matching","created":"2022-06-15","cited_by_count":100},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"1905.03375","title":"Embarrassingly Shallow Autoencoders for Sparse Data","created":"2019-05-08","cited_by_count":94},{"id":"2006.08572","title":"Flexible Dataset Distillation: Learn Labels Instead of Images","created":"2020-06-15","cited_by_count":91},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81},{"id":"1703.06476","title":"Practical Coreset Constructions for Machine Learning","created":"2017-03-19","cited_by_count":78},{"id":"2002.11603","title":"DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation","created":"2020-02-26","cited_by_count":78},{"id":"2204.07513","title":"Synthesizing Informative Training Samples with GAN","created":"2022-04-15","cited_by_count":77},{"id":"2011.02839","title":"Chasing Carbon: The Elusive Environmental Footprint of Computing","created":"2020-10-28","cited_by_count":72},{"id":"1803.02021","title":"Understanding Short-Horizon Bias in Stochastic Meta-Optimization","created":"2018-03-06","cited_by_count":69},{"id":"2207.09639","title":"DC-BENCH: Dataset Condensation Benchmark","created":"2022-07-20","cited_by_count":67},{"id":"2207.09653","title":"FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning","created":"2022-07-20","cited_by_count":66},{"id":"2006.09438","title":"Off-policy Bandits with Deficient Support","created":"2020-06-16","cited_by_count":61},{"id":"2206.13697","title":"Graph Condensation via Receptive Field Distribution Matching","created":"2022-06-28","cited_by_count":60},{"id":"2008.04489","title":"Federated Learning via Synthetic Data","created":"2020-08-11","cited_by_count":54},{"id":"2111.01177","title":"Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence","created":"2021-11-01","cited_by_count":54},{"id":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52},{"id":"2104.02857","title":"Soft-Label Anonymous Gastric X-ray Image Distillation","created":"2021-04-07","cited_by_count":51},{"id":"2208.11311","title":"Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments","created":"2022-08-24","cited_by_count":49},{"id":"1802.04023","title":"Fair and Diverse DPP-based Data Summarization","created":"2018-02-12","cited_by_count":39},{"id":"2108.00261","title":"ECLARE: Extreme Classification with Label Graph Correlations","created":"2021-07-31","cited_by_count":38},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38},{"id":"2103.15851","title":"Distilled Replay: Overcoming Forgetting through Synthetic Samples","created":"2021-03-29","cited_by_count":36},{"id":"2209.14635","title":"Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing","created":"2022-09-29","cited_by_count":35},{"id":"2208.10494","title":"Dataset Condensation with Latent Space Knowledge Factorization and Sharing","created":"2022-08-21","cited_by_count":34},{"id":"2211.04446","title":"Private Set Generation with Discriminative Information","created":"2022-11-07","cited_by_count":34},{"id":"1811.09975","title":"Sequential Variational Autoencoders for Collaborative Filtering","created":"2018-11-25","cited_by_count":31},{"id":"2204.01273","title":"FedSynth: Gradient Compression via Synthetic Data in Federated Learning","created":"2022-04-04","cited_by_count":31},{"id":"2206.11849","title":"Sample Condensation in Online Continual Learning","created":"2022-06-23","cited_by_count":31},{"id":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30},{"id":"2209.14851","title":"Meta Knowledge Condensation for Federated Learning","created":"2022-09-29","cited_by_count":26},{"id":"2005.12210","title":"How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements","created":"2020-05-25","cited_by_count":24}],"next_cursor":"100"}