{"list":"other","total":83,"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"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":"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":"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":"1911.05485","title":"Diffusion Improves Graph Learning","created":"2019-10-28","cited_by_count":414},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"1910.12933","title":"Hyperbolic Graph Convolutional Neural Networks","created":"2019-10-28","cited_by_count":402},{"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":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"1511.06464","title":"Unitary Evolution Recurrent Neural Networks","created":"2015-11-20","cited_by_count":294},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"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":"2202.04579","title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","created":"2022-02-09","cited_by_count":214},{"id":"2302.02941","title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","created":"2023-02-06","cited_by_count":166},{"id":"2402.00789","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","created":"2024-02-01","cited_by_count":134},{"id":"1711.04735","title":"Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice","created":"2017-11-13","cited_by_count":132},{"id":"2202.02296","title":"Graph-Coupled Oscillator Networks","created":"2022-02-04","cited_by_count":124},{"id":"2108.01938","title":"PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations","created":"2021-08-04","cited_by_count":106},{"id":"2210.11790","title":"FoSR: First-order spectral rewiring for addressing oversquashing in GNNs","created":"2022-10-21","cited_by_count":105},{"id":"2003.01219","title":"Exactly Computing the Local Lipschitz Constant of ReLU Networks","created":"2020-03-02","cited_by_count":102},{"id":"2302.06835","title":"Understanding Oversquashing in GNNs through the Lens of Effective Resistance","created":"2023-02-14","cited_by_count":97},{"id":"2406.04267","title":"Transformers need glasses! Information over-squashing in language tasks","created":"2024-06-06","cited_by_count":91},{"id":"2301.09474","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","created":"2023-01-23","cited_by_count":87},{"id":"2110.09443","title":"Beltrami Flow and Neural Diffusion on Graphs","created":"2021-10-18","cited_by_count":84},{"id":"2010.00951","title":"Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies","created":"2020-10-02","cited_by_count":82},{"id":"2305.08018","title":"DRew: Dynamically Rewired Message Passing with Delay","created":"2023-05-13","cited_by_count":82},{"id":"2006.07220","title":"On Second Order Behaviour in Augmented Neural ODEs","created":"2020-06-12","cited_by_count":68},{"id":"2212.02374","title":"On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks","created":"2022-12-05","cited_by_count":64},{"id":"2210.09789","title":"Anti-Symmetric DGN: a stable architecture for Deep Graph Networks","created":"2022-10-18","cited_by_count":60},{"id":"1902.08129","title":"A Mean Field Theory of Batch Normalization","created":"2019-02-21","cited_by_count":58},{"id":"2102.10739","title":"Dissecting the Diffusion Process in Linear Graph Convolutional Networks","created":"2021-02-22","cited_by_count":58},{"id":"2310.01668","title":"Locality-Aware Graph-Rewiring in GNNs","created":"2023-10-02","cited_by_count":56},{"id":"2210.00513","title":"Gradient Gating for Deep Multi-Rate Learning on Graphs","created":"2022-10-02","cited_by_count":49},{"id":"2305.16102","title":"Demystifying Oversmoothing in Attention-Based Graph Neural Networks","created":"2023-05-25","cited_by_count":49},{"id":"2305.13084","title":"A Fractional Graph Laplacian Approach to Oversmoothing","created":"2023-05-22","cited_by_count":45},{"id":"1602.06662","title":"Recurrent Orthogonal Networks and Long-Memory Tasks","created":"2016-02-22","cited_by_count":38},{"id":"2006.02427","title":"Lyapunov spectra of chaotic recurrent neural networks","created":"2020-06-03","cited_by_count":37},{"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":"2202.10720","title":"EIGNN: Efficient Infinite-Depth Graph Neural Networks","created":"2022-02-22","cited_by_count":32},{"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":"2406.02740","title":"Long Range Propagation on Continuous-Time Dynamic Graphs","created":"2024-06-04","cited_by_count":28},{"id":"2305.19535","title":"Low-rank extended Kalman filtering for online learning of neural networks from streaming data","created":"2023-05-31","cited_by_count":23},{"id":"2311.07073","title":"Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges","created":"2023-11-13","cited_by_count":22},{"id":"2405.05646","title":"Outlier-robust Kalman Filtering through Generalised Bayes","created":"2024-05-09","cited_by_count":21},{"id":"2307.06104","title":"Deep learning for dynamic graphs: models and benchmarks","created":"2023-07-12","cited_by_count":19},{"id":"2308.16800","title":"Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks","created":"2023-08-31","cited_by_count":18},{"id":"2309.04810","title":"Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization","created":"2023-09-09","cited_by_count":18},{"id":"2405.19121","title":"Spatio-Spectral Graph Neural Networks","created":"2024-05-29","cited_by_count":17},{"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":"2405.20799","title":"Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching","created":"2024-05-31","cited_by_count":16},{"id":"2312.01538","title":"Recurrent Distance Filtering for Graph Representation Learning","created":"2023-12-03","cited_by_count":11},{"id":"2404.19508","title":"Temporal Graph ODEs for Irregularly-Sampled Time Series","created":"2024-04-30","cited_by_count":11},{"id":"2303.11754","title":"Projections of Model Spaces for Latent Graph Inference","created":"2023-03-21","cited_by_count":9},{"id":"2310.02012","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","created":"2023-10-03","cited_by_count":8},{"id":"2408.16115","title":"Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations","created":"2024-08-28","cited_by_count":8},{"id":"2410.05499","title":"Unitary convolutions for learning on graphs and groups","created":"2024-10-07","cited_by_count":8},{"id":"2406.02269","title":"Graph Neural Networks Do Not Always Oversmooth","created":"2024-06-04","cited_by_count":7},{"id":"2402.03495","title":"Partially Stochastic Infinitely Deep Bayesian Neural Networks","created":"2024-02-05","cited_by_count":6},{"id":"2403.10288","title":"Rough Transformers for Continuous and Efficient Time-Series Modelling","created":"2024-03-15","cited_by_count":6},{"id":"2502.01556","title":"A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks","created":"2025-02-03","cited_by_count":5}],"next_cursor":null}