{"total":147,"rows":[{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713,"area":null},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333,"area":null},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263,"area":null},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194,"area":null},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179,"area":null},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170,"area":null},{"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,"area":null},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153,"area":null},{"id":"2402.00789","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","created":"2024-02-01","cited_by_count":134,"area":"ssm"},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133,"area":null},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107,"area":null},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93,"area":null},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83,"area":null},{"id":"2210.02997","title":"Expander Graph Propagation","created":"2022-10-06","cited_by_count":75,"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":"2301.11956","title":"On the Connection Between MPNN and Graph Transformer","created":"2023-01-27","cited_by_count":61,"area":null},{"id":"2310.01668","title":"Locality-Aware Graph-Rewiring in GNNs","created":"2023-10-02","cited_by_count":56,"area":null},{"id":"2306.03589","title":"How does over-squashing affect the power of GNNs?","created":"2023-06-06","cited_by_count":53,"area":null},{"id":"2406.06470","title":"GKAN: Graph Kolmogorov-Arnold Networks","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2202.11097","title":"Message passing all the way up","created":"2022-02-22","cited_by_count":47,"area":null},{"id":"2303.04791","title":"Ewald-based Long-Range Message Passing for Molecular Graphs","created":"2023-03-08","cited_by_count":46,"area":null},{"id":"2306.06063","title":"Virtual Node Tuning for Few-shot Node Classification","created":"2023-06-09","cited_by_count":46,"area":null},{"id":"2302.00049","title":"Transformers Meet Directed Graphs","created":"2023-01-31","cited_by_count":40,"area":null},{"id":"2302.11329","title":"HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer","created":"2023-02-22","cited_by_count":35,"area":null},{"id":"2403.16030","title":"VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections","created":"2024-03-24","cited_by_count":34,"area":null},{"id":"2505.10960","title":"Relational Graph Transformer","created":"2025-05-16","cited_by_count":34,"area":null},{"id":"2307.07107","title":"Graph Positional and Structural Encoder","created":"2023-07-14","cited_by_count":33,"area":null},{"id":"2407.09777","title":"Graph Transformers: A Survey","created":"2024-07-13","cited_by_count":32,"area":null},{"id":"2205.15674","title":"Generalised Implicit Neural Representations","created":"2022-05-31","cited_by_count":31,"area":null},{"id":"2206.03364","title":"KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction","created":"2022-06-02","cited_by_count":31,"area":null},{"id":"2305.10329","title":"G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2502.01122","title":"Learning Efficient Positional Encodings with Graph Neural Networks","created":"2025-02-03","cited_by_count":24,"area":null},{"id":"2210.13148","title":"Transformers over Directed Acyclic Graphs","created":"2022-10-24","cited_by_count":23,"area":null},{"id":"2506.16654","title":"Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures","created":"2025-06-19","cited_by_count":23,"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":"2310.18716","title":"Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2203.10304","title":"PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs","created":"2022-03-19","cited_by_count":20,"area":null},{"id":"2402.14202","title":"Comparing Graph Transformers via Positional Encodings","created":"2024-02-22","cited_by_count":20,"area":null},{"id":"2110.14053","title":"NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks","created":"2021-10-26","cited_by_count":19,"area":null},{"id":"2401.03870","title":"Gramformer: Learning Crowd Counting via Graph-Modulated Transformer","created":"2024-01-08","cited_by_count":19,"area":null},{"id":"2410.13798","title":"Learning Graph Quantized Tokenizers","created":"2024-10-17","cited_by_count":19,"area":null},{"id":"2406.03386","title":"Learning Long Range Dependencies on Graphs via Random Walks","created":"2024-06-05","cited_by_count":18,"area":null},{"id":"2405.09285","title":"Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning","created":"2024-05-15","cited_by_count":17,"area":null},{"id":"2308.04808","title":"Joint-Relation Transformer for Multi-Person Motion Prediction","created":"2023-08-09","cited_by_count":16,"area":null},{"id":"2201.09332","title":"How Expressive are Transformers in Spectral Domain for Graphs?","created":"2022-01-23","cited_by_count":15,"area":null},{"id":"2303.00579","title":"Are More Layers Beneficial to Graph Transformers?","created":"2023-03-01","cited_by_count":15,"area":null},{"id":"2312.02339","title":"Expressive Sign Equivariant Networks for Spectral Geometric Learning","created":"2023-12-04","cited_by_count":15,"area":null},{"id":"2405.17311","title":"Probabilistic Graph Rewiring via Virtual Nodes","created":"2024-05-27","cited_by_count":15,"area":null},{"id":"2406.04336","title":"On the Expressive Power of Spectral Invariant Graph Neural Networks","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2306.03032","title":"Classification of Edge-dependent Labels of Nodes in Hypergraphs","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2310.19285","title":"Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes","created":"2023-10-30","cited_by_count":14,"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":"2303.10576","title":"An Efficient Subgraph GNN with Provable Substructure Counting Power","created":"2023-03-19","cited_by_count":13,"area":null},{"id":"2311.14864","title":"Effective Structural Encodings via Local Curvature Profiles","created":"2023-11-24","cited_by_count":13,"area":null},{"id":"2406.05815","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2411.12732","title":"Benchmarking Positional Encodings for GNNs and Graph Transformers","created":"2024-11-19","cited_by_count":13,"area":null},{"id":"2411.16278","title":"Even Sparser Graph Transformers","created":"2024-11-25","cited_by_count":13,"area":null},{"id":"2502.02216","title":"Flatten Graphs as Sequences: Transformers are Scalable Graph Generators","created":"2025-02-04","cited_by_count":13,"area":null},{"id":"2212.08689","title":"TopoImb: Toward Topology-level Imbalance in Learning from Graphs","created":"2022-12-16","cited_by_count":12,"area":null},{"id":"2502.01681","title":"DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale","created":"2025-02-02","cited_by_count":12,"area":null},{"id":"2301.05104","title":"Learning Compiler Pass Orders using Coreset and Normalized Value Prediction","created":"2023-01-09","cited_by_count":11,"area":null},{"id":"2405.14094","title":"Attending to Topological Spaces: The Cellular Transformer","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2410.23686","title":"Towards Dynamic Message Passing on Graphs","created":"2024-10-31","cited_by_count":11,"area":null},{"id":"2310.13829","title":"Universal Representation of Permutation-Invariant Functions on Vectors and Tensors","created":"2023-10-20","cited_by_count":10,"area":null},{"id":"2311.02356","title":"MATA*: Combining Learnable Node Matching with A* Algorithm for Approximate Graph Edit Distance Computation","created":"2023-11-04","cited_by_count":10,"area":null},{"id":"2312.11109","title":"Graph Transformers for Large Graphs","created":"2023-12-18","cited_by_count":10,"area":null},{"id":"2402.02464","title":"A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer","created":"2024-02-04","cited_by_count":10,"area":null},{"id":"2403.12821","title":"FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer","created":"2024-03-19","cited_by_count":10,"area":null},{"id":"2407.14459","title":"PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer","created":"2024-07-19","cited_by_count":10,"area":null},{"id":"2412.16447","title":"A Generalizable Anomaly Detection Method in Dynamic Graphs","created":"2024-12-21","cited_by_count":10,"area":null},{"id":"2502.08958","title":"Biologically Plausible Brain Graph Transformer","created":"2025-02-13","cited_by_count":10,"area":null},{"id":"2302.10574","title":"MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysis","created":"2023-02-21","cited_by_count":9,"area":null},{"id":"2305.01666","title":"BrainNPT: Pre-training of Transformer networks for brain network classification","created":"2023-05-02","cited_by_count":9,"area":null},{"id":"2209.07869","title":"LogGD:Detecting Anomalies from System Logs by Graph Neural Networks","created":"2022-09-16","cited_by_count":8,"area":null},{"id":"2211.14425","title":"PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2310.08863","title":"In-Context Learning for Few-Shot Molecular Property Prediction","created":"2023-10-13","cited_by_count":8,"area":null},{"id":"2311.14333","title":"Cycle Invariant Positional Encoding for Graph Representation Learning","created":"2023-11-24","cited_by_count":8,"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":"2410.06746","title":"Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention","created":"2024-10-09","cited_by_count":8,"area":null},{"id":"2205.10852","title":"Relphormer: Relational Graph Transformer for Knowledge Graph Representations","created":"2022-05-22","cited_by_count":7,"area":null},{"id":"2206.14337","title":"Deformable Graph Transformer","created":"2022-06-29","cited_by_count":7,"area":null},{"id":"2304.10933","title":"Self-Attention in Colors: Another Take on Encoding Graph Structure in Transformers","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2401.16176","title":"A Survey on Structure-Preserving Graph Transformers","created":"2024-01-29","cited_by_count":7,"area":null},{"id":"2504.10917","title":"Towards A Universal Graph Structural Encoder","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2210.07715","title":"Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learning","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2305.15747","title":"Union Subgraph Neural Networks","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2409.17986","title":"Supra-Laplacian Encoding for Transformer on Dynamic Graphs","created":"2024-09-26","cited_by_count":6,"area":null},{"id":"2112.12482","title":"Self-Supervised Graph Representation Learning for Neuronal Morphologies","created":"2021-12-23","cited_by_count":5,"area":null},{"id":"2303.00613","title":"Diffusing Graph Attention","created":"2023-03-01","cited_by_count":5,"area":null},{"id":"2310.05296","title":"Tailoring Self-Attention for Graph via Rooted Subtrees","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2404.13604","title":"CKGConv: General Graph Convolution with Continuous Kernels","created":"2024-04-21","cited_by_count":5,"area":null},{"id":"2405.01663","title":"Oversmoothing Alleviation in Graph Neural Networks: A Survey and Unified View","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2405.02795","title":"Graph as Point Set","created":"2024-05-05","cited_by_count":4,"area":null},{"id":"2406.12059","title":"A Scalable and Effective Alternative to Graph Transformers","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2412.07407","title":"Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings","created":"2024-12-10","cited_by_count":4,"area":null},{"id":"2511.04557","title":"Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learning","created":"2025-11-06","cited_by_count":4,"area":null},{"id":"2402.07268","title":"Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer","created":"2024-02-11","cited_by_count":3,"area":null},{"id":"2405.21061","title":"Graph External Attention Enhanced Transformer","created":"2024-05-31","cited_by_count":3,"area":null},{"id":"2407.03125","title":"Foundations and Frontiers of Graph Learning Theory","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2506.05530","title":"Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum","created":"2025-06-05","cited_by_count":3,"area":null}],"next_cursor":"100"}