{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1606.06357","title":"Complex Embeddings for Simple Link Prediction","created":"2016-06-20","cited_by_count":902},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2109.01050","title":"Characterizing possible failure modes in physics-informed neural networks","created":"2021-09-02","cited_by_count":643},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1905.07953","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","created":"2019-05-20","cited_by_count":541},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1803.00885","title":"Essentially No Barriers in Neural Network Energy Landscape","created":"2018-03-02","cited_by_count":330},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"1406.2572","title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","created":"2014-06-10","cited_by_count":289},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"1901.09005","title":"Revisiting Self-Supervised Visual Representation Learning","created":"2019-01-25","cited_by_count":251},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"2008.03156","title":"Better Fine-Tuning by Reducing Representational Collapse","created":"2020-08-06","cited_by_count":157},{"id":"1806.07297","title":"Canonical Tensor Decomposition for Knowledge Base Completion","created":"2018-06-19","cited_by_count":150},{"id":"2010.05627","title":"Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning","created":"2020-10-12","cited_by_count":126},{"id":"1802.06175","title":"An Alternative View: When Does SGD Escape Local Minima?","created":"2018-02-17","cited_by_count":115},{"id":"1810.13243","title":"A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation","created":"2018-10-29","cited_by_count":110},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"1902.00744","title":"Asymmetric Valleys: Beyond Sharp and Flat Local Minima","created":"2019-02-02","cited_by_count":90},{"id":"2001.00939","title":"Relative Flatness and Generalization","created":"2020-01-03","cited_by_count":88},{"id":"1806.05594","title":"There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average","created":"2018-06-14","cited_by_count":82},{"id":"1906.04724","title":"Large Scale Structure of Neural Network Loss Landscapes","created":"2019-06-11","cited_by_count":68},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63},{"id":"1901.04653","title":"Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis","created":"2019-01-15","cited_by_count":59},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57},{"id":"1910.05552","title":"Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction","created":"2019-10-12","cited_by_count":54},{"id":"2012.03801","title":"A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization","created":"2020-12-07","cited_by_count":44},{"id":"2106.01939","title":"Causal Effect Inference for Structured Treatments","created":"2021-06-03","cited_by_count":39},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39},{"id":"2110.02834","title":"Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations","created":"2021-10-06","cited_by_count":37},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34},{"id":"2201.00519","title":"Stochastic Weight Averaging Revisited","created":"2022-01-03","cited_by_count":26},{"id":"2012.06898","title":"Revisiting \"Qualitatively Characterizing Neural Network Optimization Problems\"","created":"2020-12-12","cited_by_count":24},{"id":"2007.08949","title":"Probabilistic Active Meta-Learning","created":"2020-07-17","cited_by_count":23},{"id":"1810.01021","title":"Large batch size training of neural networks with adversarial training and second-order information","created":"2018-10-02","cited_by_count":18},{"id":"2008.09020","title":"Training Sensitivity in Graph Isomorphism Network","created":"2020-08-19","cited_by_count":2}],"next_cursor":null}