{"total":37,"rows":[{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713,"area":null},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83,"area":null},{"id":"2306.13089","title":"GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning","created":"2023-05-28","cited_by_count":70,"area":null},{"id":"2403.01232","title":"Polynormer: Polynomial-Expressive Graph Transformer in Linear Time","created":"2024-03-02","cited_by_count":65,"area":null},{"id":"2407.09777","title":"Graph Transformers: A Survey","created":"2024-07-13","cited_by_count":32,"area":null},{"id":"2405.01009","title":"On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2402.14202","title":"Comparing Graph Transformers via Positional Encodings","created":"2024-02-22","cited_by_count":20,"area":null},{"id":"2502.02562","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","created":"2025-02-04","cited_by_count":19,"area":null},{"id":"2305.00156","title":"Taming graph kernels with random features","created":"2023-04-29","cited_by_count":17,"area":null},{"id":"2303.00579","title":"Are More Layers Beneficial to Graph Transformers?","created":"2023-03-01","cited_by_count":15,"area":null},{"id":"2502.16533","title":"A Survey of Graph Transformers: Architectures, Theories and Applications","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2401.12007","title":"Tensor-view Topological Graph Neural Network","created":"2024-01-22","cited_by_count":12,"area":null},{"id":"2404.15729","title":"Gradformer: Graph Transformer with Exponential Decay","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2302.01925","title":"Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers","created":"2023-02-03","cited_by_count":10,"area":null},{"id":"2302.01128","title":"Mnemosyne: Learning to Train Transformers with Transformers","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2402.08450","title":"Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2302.00942","title":"Efficient Graph Field Integrators Meet Point Clouds","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2410.03462","title":"Linear Transformer Topological Masking with Graph Random Features","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2509.03691","title":"Graph Random Features for Scalable Gaussian Processes","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2406.15881","title":"Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2406.16450","title":"Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2410.16699","title":"Graph Transformers Dream of Electric Flow","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2509.22259","title":"Rotary Position Encodings for Graphs","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2405.11622","title":"Continuous Predictive Modeling of Clinical Notes and ICD Codes in Patient Health Records","created":"2024-05-19","cited_by_count":1,"area":null},{"id":"2411.17296","title":"GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2508.05070","title":"TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2601.04159","title":"ToTMNet: FFT-Accelerated Toeplitz Temporal Mixing Network for Lightweight Remote Photoplethysmography","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2602.15239","title":"Size-Transferability of Graph Transformers with Convolutional Positional Encodings","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2605.10706","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2609.36062","title":"SMat-Attention: Structured Long-Context Sequence Modeling","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2211.14312","title":"Karyotype AI for Precision Oncology","created":"2022-11-20","cited_by_count":0,"area":null},{"id":"2403.11100","title":"Graph Expansion in Pruned Recurrent Neural Network Layers Preserve Performance","created":"2024-03-17","cited_by_count":0,"area":null},{"id":"2403.16130","title":"AKBR: Learning Adaptive Kernel-based Representations for Graph Classification","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2502.15331","title":"Lightweight yet Efficient: An External Attentive Graph Convolutional Network with Positional Prompts for Sequential Recommendation","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2504.19740","title":"Graph Fourier Transformer with Structure-Frequency Information","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2508.11092","title":"Predictive Multimodal Modeling of Diagnoses and Treatments in EHR","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2607.26369","title":"ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}