{"total":59,"rows":[{"id":"2504.02732","title":"Why do LLMs attend to the first token?","created":"2025-04-03","cited_by_count":127,"area":null},{"id":"2305.13084","title":"A Fractional Graph Laplacian Approach to Oversmoothing","created":"2023-05-22","cited_by_count":45,"area":null},{"id":"2310.10121","title":"From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyond","created":"2023-10-16","cited_by_count":26,"area":null},{"id":"2311.07073","title":"Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges","created":"2023-11-13","cited_by_count":22,"area":null},{"id":"2401.04301","title":"Setting the Record Straight on Transformer Oversmoothing","created":"2024-01-09","cited_by_count":21,"area":null},{"id":"2410.03424","title":"Cayley Graph Propagation","created":"2024-10-04","cited_by_count":21,"area":null},{"id":"2503.09008","title":"Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement","created":"2025-03-12","cited_by_count":20,"area":null},{"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,"area":null},{"id":"2404.17099","title":"Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2307.16092","title":"Feature Transportation Improves Graph Neural Networks","created":"2023-07-29","cited_by_count":15,"area":null},{"id":"2405.13526","title":"Understanding Virtual Nodes: Oversquashing and Node Heterogeneity","created":"2024-05-22","cited_by_count":14,"area":null},{"id":"2405.15540","title":"Bundle Neural Networks for message diffusion on graphs","created":"2024-05-24","cited_by_count":14,"area":null},{"id":"2402.06275","title":"Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics","created":"2024-02-09","cited_by_count":11,"area":null},{"id":"2506.16656","title":"Mesh-Informed Neural Operator : A Transformer Generative Approach","created":"2025-06-20","cited_by_count":11,"area":null},{"id":"2409.17475","title":"On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2401.11074","title":"On The Temporal Domain of Differential Equation Inspired Graph Neural Networks","created":"2024-01-20","cited_by_count":9,"area":null},{"id":"2309.17417","title":"Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2405.18877","title":"Continuous Product Graph Neural Networks","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2310.06417","title":"Supercharging Graph Transformers with Advective Diffusion","created":"2023-10-10","cited_by_count":7,"area":"diffusion"},{"id":"2309.13599","title":"From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited","created":"2023-09-24","cited_by_count":6,"area":null},{"id":"2401.14580","title":"Design Your Own Universe: A Physics-Informed Agnostic Method for Enhancing Graph Neural Networks","created":"2024-01-26","cited_by_count":6,"area":null},{"id":"2409.11504","title":"Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2502.04591","title":"Are We Measuring Oversmoothing in Graph Neural Networks Correctly?","created":"2025-02-07","cited_by_count":6,"area":null},{"id":"2506.15507","title":"Over-squashing in Spatiotemporal Graph Neural Networks","created":"2025-06-18","cited_by_count":6,"area":null},{"id":"2502.06751","title":"What makes a good feedforward computational graph?","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2404.03139","title":"Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2407.11876","title":"Simplifying the Theory on Over-Smoothing","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2408.16698","title":"SympGNNs: Symplectic Graph Neural Networks for identifiying high-dimensional Hamiltonian systems and node classification","created":"2024-08-29","cited_by_count":4,"area":null},{"id":"2411.00835","title":"Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2407.04516","title":"G-Adaptivity: optimised graph-based mesh relocation for finite element methods","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2410.05593","title":"When Graph Neural Networks Meet Dynamic Mode Decomposition","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2410.14109","title":"Improving Graph Neural Networks by Learning Continuous Edge Directions","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2506.20324","title":"Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2307.06631","title":"Frameless Graph Knowledge Distillation","created":"2023-07-13","cited_by_count":2,"area":"distill"},{"id":"2308.03306","title":"Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2310.12457","title":"MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy","created":"2023-10-19","cited_by_count":2,"area":null},{"id":"2407.12419","title":"Dirac--Bianconi Graph Neural Networks -- Enabling Non-Diffusive Long-Range Graph Predictions","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2501.19089","title":"Resolving Oversmoothing with Opinion Dissensus","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2602.15634","title":"Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors","created":"2026-02-17","cited_by_count":2,"area":null},{"id":"2311.06942","title":"Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach","created":"2023-11-12","cited_by_count":1,"area":null},{"id":"2402.14802","title":"Link Prediction with Physics-Inspired Graph Neural Networks","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2403.04763","title":"BloomGML: Graph Machine Learning through the Lens of Bilevel Optimization","created":"2024-03-07","cited_by_count":1,"area":null},{"id":"2411.14158","title":"Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2502.06595","title":"Surrogate models for diffusion on graphs via sparse polynomials","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2508.00037","title":"Predicting Large-scale Urban Network Dynamics with Energy-informed Graph Neural Diffusion","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2508.12787","title":"Wavy Transformer","created":"2025-08-18","cited_by_count":1,"area":null},{"id":"2608.02558","title":"Benchmarking Sheaf Neural Networks for Inductive Tasks","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2312.10279","title":"A charge-preserving method for solving graph neural diffusion networks","created":"2023-12-16","cited_by_count":0,"area":null},{"id":"2407.14387","title":"GLAudio Listens to the Sound of the Graph","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2412.08419","title":"Energy Guided smoothness to improve Robustness in Graph Classification","created":"2024-12-11","cited_by_count":0,"area":null},{"id":"2503.14048","title":"Beyond holography: the entropic quantum gravity foundations of image processing","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2506.11869","title":"How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2508.12993","title":"Predicting the Performance of Graph Convolutional Networks with Spectral Properties of the Graph Laplacian","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2508.17126","title":"Token Homogenization under Positional Bias","created":"2025-08-23","cited_by_count":0,"area":null},{"id":"2509.02015","title":"Second-Order Tensorial Partial Differential Equations on Graphs","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2509.18893","title":"Exploring Heterophily in Graph-level Tasks","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2511.19984","title":"Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2607.21885","title":"Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2610.19324","title":"Why don't Graph Transformers attend to the same token?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}