{"list":"other","total":65,"rows":[{"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"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":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"1905.00067","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","created":"2019-04-30","cited_by_count":443},{"id":"1409.5185","title":"Deeply-Supervised Nets","created":"2014-09-18","cited_by_count":367},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"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":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"1704.02901","title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","created":"2017-04-10","cited_by_count":310},{"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":"2106.10934","title":"GRAND: Graph Neural Diffusion","created":"2021-06-21","cited_by_count":258},{"id":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"2006.13009","title":"Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings","created":"2020-06-21","cited_by_count":214},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"1911.07532","title":"Graph Neural Ordinary Differential Equations","created":"2019-11-18","cited_by_count":154},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"id":"1902.09689","title":"AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks","created":"2019-02-26","cited_by_count":112},{"id":"2309.00367","title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","created":"2023-09-01","cited_by_count":85},{"id":"2406.08993","title":"Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification","created":"2024-06-13","cited_by_count":85},{"id":"2305.08018","title":"DRew: Dynamically Rewired Message Passing with Delay","created":"2023-05-13","cited_by_count":82},{"id":"2004.12814","title":"Why should we add early exits to neural networks?","created":"2020-04-27","cited_by_count":70},{"id":"2403.01232","title":"Polynormer: Polynomial-Expressive Graph Transformer in Linear Time","created":"2024-03-02","cited_by_count":65},{"id":"2301.11956","title":"On the Connection Between MPNN and Graph Transformer","created":"2023-01-27","cited_by_count":61},{"id":"2210.09789","title":"Anti-Symmetric DGN: a stable architecture for Deep Graph Networks","created":"2022-10-18","cited_by_count":60},{"id":"1706.00885","title":"IDK Cascades: Fast Deep Learning by Learning not to Overthink","created":"2017-06-03","cited_by_count":48},{"id":"2206.01003","title":"Shortest Path Networks for Graph Property Prediction","created":"2022-06-02","cited_by_count":46},{"id":"2502.10818","title":"On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning","created":"2025-02-15","cited_by_count":43},{"id":"2310.01267","title":"Cooperative Graph Neural Networks","created":"2023-10-02","cited_by_count":36},{"id":"2406.02997","title":"Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs","created":"2024-06-05","cited_by_count":34},{"id":"2002.10306","title":"Adaptive Propagation Graph Convolutional Network","created":"2020-02-24","cited_by_count":31},{"id":"2206.05437","title":"ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks","created":"2022-06-11","cited_by_count":31},{"id":"2405.01009","title":"On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems","created":"2024-05-02","cited_by_count":28},{"id":"2502.09263","title":"Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence","created":"2025-02-13","cited_by_count":26},{"id":"2312.16560","title":"Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching","created":"2023-12-27","cited_by_count":24},{"id":"2310.00697","title":"Learning How to Propagate Messages in Graph Neural Networks","created":"2023-10-01","cited_by_count":23},{"id":"2505.15547","title":"Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning","created":"2025-05-21","cited_by_count":19},{"id":"2405.17163","title":"Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks","created":"2024-05-27","cited_by_count":16},{"id":"1606.04429","title":"Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation","created":"2016-06-14","cited_by_count":15},{"id":"1706.02480","title":"Forward Thinking: Building and Training Neural Networks One Layer at a Time","created":"2017-06-08","cited_by_count":15},{"id":"2305.10544","title":"Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks","created":"2023-05-17","cited_by_count":7}],"next_cursor":null}