{"list":"other","total":95,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2102.09844","title":"E(n) Equivariant Graph Neural Networks","created":"2021-02-19","cited_by_count":965},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"1905.11136","title":"Provably Powerful Graph Networks","created":"2019-05-27","cited_by_count":389},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"1612.08498","title":"Steerable CNNs","created":"2016-12-27","cited_by_count":305},{"id":"2104.12229","title":"Vector Neurons: A General Framework for SO(3)-Equivariant Networks","created":"2021-04-25","cited_by_count":305},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"1905.09550","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","created":"2019-05-23","cited_by_count":261},{"id":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"id":"2010.01179","title":"The Surprising Power of Graph Neural Networks with Random Node Initialization","created":"2020-10-02","cited_by_count":198},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","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":"1506.04579","title":"ParseNet: Looking Wider to See Better","created":"2015-06-15","cited_by_count":177},{"id":"1802.08665","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","created":"2018-02-23","cited_by_count":175},{"id":"1905.12560","title":"On the equivalence between graph isomorphism testing and function approximation with GNNs","created":"2019-05-29","cited_by_count":172},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"2110.03336","title":"Frame Averaging for Invariant and Equivariant Network Design","created":"2021-10-07","cited_by_count":168},{"id":"2110.02910","title":"Equivariant Subgraph Aggregation Networks","created":"2021-10-06","cited_by_count":154},{"id":"1901.09342","title":"On the Universality of Invariant Networks","created":"2019-01-27","cited_by_count":152},{"id":"1903.02541","title":"Relational Pooling for Graph Representations","created":"2019-03-06","cited_by_count":150},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2006.16908","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","created":"2020-06-30","cited_by_count":142},{"id":"1702.08389","title":"Equivariance Through Parameter-Sharing","created":"2017-02-27","cited_by_count":141},{"id":"1804.10306","title":"Universal approximations of invariant maps by neural networks","created":"2018-04-26","cited_by_count":127},{"id":"2106.13264","title":"You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks","created":"2021-06-24","cited_by_count":127},{"id":"2301.09505","title":"Rethinking the Expressive Power of GNNs via Graph Biconnectivity","created":"2023-01-23","cited_by_count":119},{"id":"2007.08426","title":"Investigating Pretrained Language Models for Graph-to-Text Generation","created":"2020-07-16","cited_by_count":117},{"id":"1903.08850","title":"Stochastic Optimization of Sorting Networks via Continuous Relaxations","created":"2019-03-21","cited_by_count":111},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107},{"id":"2106.04319","title":"Breaking the Limits of Message Passing Graph Neural Networks","created":"2021-06-08","cited_by_count":101},{"id":"1811.01900","title":"Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs","created":"2018-11-05","cited_by_count":98},{"id":"2002.08599","title":"On Learning Sets of Symmetric Elements","created":"2020-02-20","cited_by_count":98},{"id":"2301.09308","title":"On the Expressive Power of Geometric Graph Neural Networks","created":"2023-01-23","cited_by_count":90},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83},{"id":"2210.01765","title":"One Transformer Can Understand Both 2D & 3D Molecular Data","created":"2022-10-04","cited_by_count":77},{"id":"2006.16038","title":"SoftSort: A Continuous Relaxation for the argsort Operator","created":"2020-06-29","cited_by_count":66},{"id":"1910.00753","title":"Equivariant Flows: sampling configurations for multi-body systems with symmetric energies","created":"2019-10-02","cited_by_count":57},{"id":"1912.06058","title":"Coloring graph neural networks for node disambiguation","created":"2019-12-12","cited_by_count":52},{"id":"1808.05563","title":"Learning Invariances using the Marginal Likelihood","created":"2018-08-16","cited_by_count":51},{"id":"2110.10211","title":"Learning Partial Equivariances from Data","created":"2021-10-19","cited_by_count":45},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42},{"id":"2103.01710","title":"Autobahn: Automorphism-based Graph Neural Nets","created":"2021-03-02","cited_by_count":39},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39},{"id":"2110.14416","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","created":"2021-10-27","cited_by_count":35},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34},{"id":"2208.07220","title":"PatchDropout: Economizing Vision Transformers Using Patch Dropout","created":"2022-08-10","cited_by_count":28},{"id":"2104.09856","title":"Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning","created":"2021-04-20","cited_by_count":23},{"id":"2203.06153","title":"Symmetry Group Equivariant Architectures for Physics","created":"2022-03-11","cited_by_count":23},{"id":"2210.06475","title":"Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models","created":"2022-10-13","cited_by_count":22},{"id":"2202.12439","title":"Learning Invariant Weights in Neural Networks","created":"2022-02-25","cited_by_count":16},{"id":"2208.10428","title":"Equivariant Hypergraph Neural Networks","created":"2022-08-22","cited_by_count":14},{"id":"2006.16867","title":"Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey","created":"2020-06-30","cited_by_count":12},{"id":"2104.10105","title":"Neural Networks for Learning Counterfactual G-Invariances from Single Environments","created":"2021-04-20","cited_by_count":8},{"id":"2107.12460","title":"Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers","created":"2021-07-26","cited_by_count":6},{"id":"2202.02142","title":"Deep invariant networks with differentiable augmentation layers","created":"2022-02-04","cited_by_count":6},{"id":"2002.07528","title":"A Computationally Efficient Neural Network Invariant to the Action of Symmetry Subgroups","created":"2020-02-18","cited_by_count":4},{"id":"2110.08092","title":"Equivariant and Invariant Reynolds Networks","created":"2021-10-15","cited_by_count":4}],"next_cursor":null}