{"list":"other","total":63,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"2007.06823","title":"Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users","created":"2020-07-14","cited_by_count":338},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"2104.09459","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","created":"2021-04-19","cited_by_count":187},{"id":"2305.03053","title":"ZipIt! Merging Models from Different Tasks without Training","created":"2023-05-04","cited_by_count":179},{"id":"1901.09342","title":"On the Universality of Invariant Networks","created":"2019-01-27","cited_by_count":152},{"id":"2010.04495","title":"Linear Mode Connectivity in Multitask and Continual Learning","created":"2020-10-09","cited_by_count":145},{"id":"1506.02617","title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","created":"2015-06-08","cited_by_count":120},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120},{"id":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107},{"id":"2009.02439","title":"Optimizing Mode Connectivity via Neuron Alignment","created":"2020-09-05","cited_by_count":86},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70},{"id":"2002.05688","title":"Classifying the classifier: dissecting the weight space of neural networks","created":"2020-02-13","cited_by_count":65},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64},{"id":"2212.12042","title":"Re-basin via implicit Sinkhorn differentiation","created":"2022-12-22","cited_by_count":62},{"id":"2403.12143","title":"Graph Neural Networks for Learning Equivariant Representations of Neural Networks","created":"2024-03-18","cited_by_count":59},{"id":"2312.04501","title":"Graph Metanetworks for Processing Diverse Neural Architectures","created":"2023-12-07","cited_by_count":57},{"id":"2305.13546","title":"Neural Functional Transformers","created":"2023-05-22","cited_by_count":52},{"id":"2306.12517","title":"FFCV: Accelerating Training by Removing Data Bottlenecks","created":"2023-06-21","cited_by_count":49},{"id":"1910.06539","title":"Challenges in Markov chain Monte Carlo for Bayesian neural networks","created":"2019-10-15","cited_by_count":44},{"id":"2310.05719","title":"Transformer Fusion with Optimal Transport","created":"2023-10-09","cited_by_count":36},{"id":"2210.17216","title":"Symmetries, flat minima, and the conserved quantities of gradient flow","created":"2022-10-31","cited_by_count":35},{"id":"2310.13397","title":"Equivariant Deep Weight Space Alignment","created":"2023-10-20","cited_by_count":35},{"id":"2010.01590","title":"Deep kernel processes","created":"2020-10-04","cited_by_count":34},{"id":"2104.11044","title":"Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes","created":"2021-04-22","cited_by_count":28},{"id":"2106.16004","title":"What can linear interpolation of neural network loss landscapes tell us?","created":"2021-06-30","cited_by_count":28},{"id":"2202.03038","title":"Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry","created":"2022-02-07","cited_by_count":28},{"id":"2402.05232","title":"Universal Neural Functionals","created":"2024-02-07","cited_by_count":26},{"id":"2310.19103","title":"Proving Linear Mode Connectivity of Neural Networks via Optimal Transport","created":"2023-10-29","cited_by_count":25},{"id":"2012.06898","title":"Revisiting \"Qualitatively Characterizing Neural Network Optimization Problems\"","created":"2020-12-12","cited_by_count":24},{"id":"2402.04081","title":"Improved Generalization of Weight Space Networks via Augmentations","created":"2024-02-06","cited_by_count":24},{"id":"2305.13404","title":"Improving Convergence and Generalization Using Parameter Symmetries","created":"2023-05-22","cited_by_count":23},{"id":"2304.02902","title":"Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry","created":"2023-04-06","cited_by_count":21},{"id":"1511.01029","title":"Understanding symmetries in deep networks","created":"2015-11-03","cited_by_count":17},{"id":"2403.00986","title":"Merging Text Transformer Models from Different Initializations","created":"2024-03-01","cited_by_count":16},{"id":"2108.13097","title":"A theory of representation learning gives a deep generalisation of kernel methods","created":"2021-08-30","cited_by_count":15},{"id":"2310.08287","title":"A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors","created":"2023-10-12","cited_by_count":12},{"id":"2210.01019","title":"Plateau in Monotonic Linear Interpolation -- A \"Biased\" View of Loss Landscape for Deep Networks","created":"2022-10-03","cited_by_count":10},{"id":"2209.07157","title":"On the detrimental effect of invariances in the likelihood for variational inference","created":"2022-09-15","cited_by_count":8},{"id":"2305.17017","title":"Investigating how ReLU-networks encode symmetries","created":"2023-05-26","cited_by_count":8},{"id":"2312.09832","title":"Disentangling Linear Mode-Connectivity","created":"2023-12-15","cited_by_count":8},{"id":"2401.00611","title":"A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry","created":"2023-12-31","cited_by_count":7},{"id":"2309.09814","title":"Convolutional Deep Kernel Machines","created":"2023-09-18","cited_by_count":3}],"next_cursor":null}