{"list":"other","total":58,"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":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"2007.08663","title":"TUDataset: A collection of benchmark datasets for learning with graphs","created":"2020-07-16","cited_by_count":728},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"id":"1910.12430","title":"Differentiable Convex Optimization Layers","created":"2019-10-28","cited_by_count":465},{"id":"1507.00504","title":"Optimal Transport for Domain Adaptation","created":"2015-07-02","cited_by_count":463},{"id":"1904.08082","title":"Self-Attention Graph Pooling","created":"2019-04-17","cited_by_count":421},{"id":"1609.07152","title":"Input Convex Neural Networks","created":"2016-09-22","cited_by_count":414},{"id":"1711.01558","title":"Wasserstein Auto-Encoders","created":"2017-11-05","cited_by_count":373},{"id":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","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":"1511.06391","title":"Order Matters: Sequence to sequence for sets","created":"2015-11-19","cited_by_count":237},{"id":"1705.09634","title":"Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration","created":"2017-05-26","cited_by_count":223},{"id":"1310.4375","title":"Fast Computation of Wasserstein Barycenters","created":"2013-10-16","cited_by_count":216},{"id":"1908.10962","title":"Optimal transport mapping via input convex neural networks","created":"2019-08-28","cited_by_count":206},{"id":"2106.05819","title":"Adversarial Graph Augmentation to Improve Graph Contrastive Learning","created":"2021-06-10","cited_by_count":200},{"id":"1506.05439","title":"Learning with a Wasserstein Loss","created":"2015-06-17","cited_by_count":196},{"id":"1802.08665","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","created":"2018-02-23","cited_by_count":175},{"id":"1805.09114","title":"Optimal Transport for structured data with application on graphs","created":"2018-05-23","cited_by_count":172},{"id":"1911.07979","title":"ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations","created":"2019-11-18","cited_by_count":156},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138},{"id":"1901.06003","title":"Gromov-Wasserstein Learning for Graph Matching and Node Embedding","created":"2019-01-17","cited_by_count":126},{"id":"2103.03606","title":"Unbalanced minibatch Optimal Transport; applications to Domain Adaptation","created":"2021-03-05","cited_by_count":125},{"id":"1908.06315","title":"Implicit Deep Learning","created":"2019-08-17","cited_by_count":124},{"id":"1905.07645","title":"Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching","created":"2019-05-18","cited_by_count":103},{"id":"1811.02834","title":"Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties","created":"2018-11-07","cited_by_count":93},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"1710.06276","title":"Smooth and Sparse Optimal Transport","created":"2017-10-17","cited_by_count":83},{"id":"1909.04866","title":"Deep Declarative Networks: A New Hope","created":"2019-09-11","cited_by_count":78},{"id":"1610.06519","title":"Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems","created":"2016-10-20","cited_by_count":73},{"id":"2002.03293","title":"On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm","created":"2020-02-09","cited_by_count":61},{"id":"1711.05376","title":"Sliced Wasserstein Distance for Learning Gaussian Mixture Models","created":"2017-11-15","cited_by_count":59},{"id":"2006.09430","title":"Wasserstein Embedding for Graph Learning","created":"2020-06-16","cited_by_count":56},{"id":"2009.04266","title":"The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation","created":"2020-09-09","cited_by_count":56},{"id":"1807.09915","title":"Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition","created":"2018-07-26","cited_by_count":47},{"id":"1509.08985","title":"Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree","created":"2015-09-30","cited_by_count":36},{"id":"2007.10467","title":"Second-Order Pooling for Graph Neural Networks","created":"2020-07-20","cited_by_count":33},{"id":"1311.1780","title":"Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks","created":"2013-11-07","cited_by_count":32},{"id":"1510.00012","title":"Fast Discrete Distribution Clustering Using Wasserstein Barycenter with Sparse Support","created":"2015-09-30","cited_by_count":30},{"id":"1911.08530","title":"Gromov-Wasserstein Factorization Models for Graph Clustering","created":"2019-11-19","cited_by_count":25},{"id":"2002.02913","title":"Learning Autoencoders with Relational Regularization","created":"2020-02-07","cited_by_count":20},{"id":"1306.3203","title":"Bregman Alternating Direction Method of Multipliers","created":"2013-06-13","cited_by_count":19},{"id":"2110.09140","title":"Learning Prototype-oriented Set Representations for Meta-Learning","created":"2021-10-18","cited_by_count":19},{"id":"1806.10175","title":"Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling","created":"2018-06-26","cited_by_count":16},{"id":"2012.00123","title":"A Hypergradient Approach to Robust Regression without Correspondence","created":"2020-11-30","cited_by_count":7},{"id":"2010.07078","title":"Differentiable Implicit Layers","created":"2020-10-14","cited_by_count":6},{"id":"2202.12404","title":"Exploiting Problem Structure in Deep Declarative Networks: Two Case Studies","created":"2022-02-24","cited_by_count":6},{"id":"2106.06210","title":"Learning to Pool in Graph Neural Networks for Extrapolation","created":"2021-06-11","cited_by_count":4},{"id":"1510.00921","title":"Cross-convolutional-layer Pooling for Image Recognition","created":"2015-10-04","cited_by_count":2}],"next_cursor":null}