{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"1905.05178","title":"Graph U-Nets","created":"2019-05-11","cited_by_count":492},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"id":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"id":"1802.03480","title":"GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders","created":"2018-02-09","cited_by_count":383},{"id":"1706.00292","title":"Learning Generative Models with Sinkhorn Divergences","created":"2017-06-01","cited_by_count":314},{"id":"1511.06391","title":"Order Matters: Sequence to sequence for sets","created":"2015-11-19","cited_by_count":237},{"id":"2202.03104","title":"SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation","created":"2022-02-07","cited_by_count":171},{"id":"1711.08267","title":"GraphGAN: Graph Representation Learning with Generative Adversarial Nets","created":"2017-11-22","cited_by_count":121},{"id":"1905.13177","title":"Graph Normalizing Flows","created":"2019-05-30","cited_by_count":104},{"id":"1904.00597","title":"Learning Combinatorial Embedding Networks for Deep Graph Matching","created":"2019-04-01","cited_by_count":99},{"id":"1904.11088","title":"D-VAE: A Variational Autoencoder for Directed Acyclic Graphs","created":"2019-04-24","cited_by_count":98},{"id":"1906.01210","title":"Attributed Graph Clustering via Adaptive Graph Convolution","created":"2019-06-04","cited_by_count":96},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"1808.05689","title":"SimGNN: A Neural Network Approach to Fast Graph Similarity Computation","created":"2018-08-16","cited_by_count":90},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83},{"id":"2203.06714","title":"A Survey on Deep Graph Generation: Methods and Applications","created":"2022-03-13","cited_by_count":69},{"id":"2203.10202","title":"Relationformer: A Unified Framework for Image-to-Graph Generation","created":"2022-03-19","cited_by_count":67},{"id":"2201.00785","title":"Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning","created":"2022-01-03","cited_by_count":46},{"id":"2007.04395","title":"Multilevel Graph Matching Networks for Deep Graph Similarity Learning","created":"2020-07-08","cited_by_count":29},{"id":"2205.06688","title":"A Unified Framework for Implicit Sinkhorn Differentiation","created":"2022-05-13","cited_by_count":28},{"id":"2305.13768","title":"One-step differentiation of iterative algorithms","created":"2023-05-23","cited_by_count":28},{"id":"1608.08063","title":"Wasserstein Discriminant Analysis","created":"2016-08-29","cited_by_count":25},{"id":"2011.15039","title":"Combinatorial Learning of Graph Edit Distance via Dynamic Embedding","created":"2020-11-30","cited_by_count":25},{"id":"2104.09856","title":"Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning","created":"2021-04-20","cited_by_count":23},{"id":"2309.15123","title":"Uncovering Neural Scaling Laws in Molecular Representation Learning","created":"2023-09-15","cited_by_count":23},{"id":"2202.03813","title":"Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters","created":"2022-02-08","cited_by_count":22},{"id":"2203.00854","title":"FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours","created":"2022-03-02","cited_by_count":14},{"id":"2402.10793","title":"An end-to-end attention-based approach for learning on graphs","created":"2024-02-16","cited_by_count":11},{"id":"2409.17687","title":"Graph Edit Distance with General Costs Using Neural Set Divergence","created":"2024-09-26","cited_by_count":11},{"id":"1805.11028","title":"Autoencoding any Data through Kernel Autoencoders","created":"2018-05-28","cited_by_count":10},{"id":"2304.01507","title":"RARE: Robust Masked Graph Autoencoder","created":"2023-04-04","cited_by_count":10},{"id":"2012.11898","title":"Graph Autoencoders with Deconvolutional Networks","created":"2020-12-22","cited_by_count":9},{"id":"2402.12269","title":"Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss","created":"2024-02-19","cited_by_count":7},{"id":"2410.18858","title":"Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens","created":"2024-10-24","cited_by_count":3},{"id":"2411.11682","title":"Learning Differentiable Surrogate Losses for Structured Prediction","created":"2024-11-18","cited_by_count":1}],"next_cursor":null}