{"list":"other","total":65,"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":"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"2002.02126","title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","created":"2020-02-06","cited_by_count":1139},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"2002.09405","title":"Learning to Simulate Complex Physics with Graph Networks","created":"2020-02-21","cited_by_count":880},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"id":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"id":"1909.03211","title":"Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View","created":"2019-09-07","cited_by_count":545},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"2011.02260","title":"Graph Neural Networks in Recommender Systems: A Survey","created":"2020-11-04","cited_by_count":494},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"1905.00067","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","created":"2019-04-30","cited_by_count":443},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2101.00797","title":"Beyond Low-frequency Information in Graph Convolutional Networks","created":"2021-01-04","cited_by_count":362},{"id":"2302.11640","title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","created":"2023-02-22","cited_by_count":343},{"id":"2110.14446","title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","created":"2021-10-27","cited_by_count":311},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"2007.09296","title":"Towards Deeper Graph Neural Networks","created":"2020-07-18","cited_by_count":296},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2007.02901","title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks","created":"2020-07-06","cited_by_count":260},{"id":"2106.10934","title":"GRAND: Graph Neural Diffusion","created":"2021-06-21","cited_by_count":258},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"2202.04579","title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","created":"2022-02-09","cited_by_count":214},{"id":"2106.06134","title":"Is Homophily a Necessity for Graph Neural Networks?","created":"2021-06-11","cited_by_count":182},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"2205.11172","title":"How Powerful are Spectral Graph Neural Networks","created":"2022-05-23","cited_by_count":169},{"id":"2108.11482","title":"ETA Prediction with Graph Neural Networks in Google Maps","created":"2021-08-25","cited_by_count":130},{"id":"1807.05560","title":"DeepInf: Social Influence Prediction with Deep Learning","created":"2018-07-15","cited_by_count":128},{"id":"2006.06972","title":"Towards Deeper Graph Neural Networks with Differentiable Group Normalization","created":"2020-06-12","cited_by_count":114},{"id":"2204.04879","title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","created":"2022-04-11","cited_by_count":102},{"id":"2201.07858","title":"Decoupling the Depth and Scope of Graph Neural Networks","created":"2022-01-19","cited_by_count":94},{"id":"2104.01404","title":"New Benchmarks for Learning on Non-Homophilous Graphs","created":"2021-04-03","cited_by_count":81},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72},{"id":"2102.06966","title":"Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization","created":"2021-02-13","cited_by_count":70},{"id":"2210.09789","title":"Anti-Symmetric DGN: a stable architecture for Deep Graph Networks","created":"2022-10-18","cited_by_count":60},{"id":"2009.14332","title":"Multi-hop Attention Graph Neural Network","created":"2020-09-29","cited_by_count":53},{"id":"2010.12408","title":"On the Equivalence of Decoupled Graph Convolution Network and Label Propagation","created":"2020-10-23","cited_by_count":49},{"id":"2212.10701","title":"A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks","created":"2022-12-21","cited_by_count":49},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45},{"id":"2103.13355","title":"Bag of Tricks for Node Classification with Graph Neural Networks","created":"2021-03-24","cited_by_count":40},{"id":"2303.06562","title":"ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond","created":"2023-03-12","cited_by_count":39},{"id":"1910.11945","title":"Improving Graph Attention Networks with Large Margin-based Constraints","created":"2019-10-25","cited_by_count":34},{"id":"1810.10751","title":"Attack Graph Convolutional Networks by Adding Fake Nodes","created":"2018-10-25","cited_by_count":26},{"id":"2102.03147","title":"Learning Conjoint Attentions for Graph Neural Nets","created":"2021-02-05","cited_by_count":26},{"id":"2206.04361","title":"Model Degradation Hinders Deep Graph Neural Networks","created":"2022-06-09","cited_by_count":26},{"id":"2206.07743","title":"Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective","created":"2022-06-15","cited_by_count":19},{"id":"2207.11311","title":"Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective","created":"2022-07-22","cited_by_count":19},{"id":"2202.04139","title":"Simplified Graph Convolution with Heterophily","created":"2022-02-08","cited_by_count":17},{"id":"2303.00579","title":"Are More Layers Beneficial to Graph Transformers?","created":"2023-03-01","cited_by_count":15}],"next_cursor":null}