{"total":177,"rows":[{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320,"area":null},{"id":"2103.00111","title":"Graph Self-Supervised Learning: A Survey","created":"2021-02-27","cited_by_count":289,"area":null},{"id":"2201.08821","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","created":"2022-01-21","cited_by_count":195,"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":"2310.04560","title":"Talk like a Graph: Encoding Graphs for Large Language Models","created":"2023-10-06","cited_by_count":176,"area":null},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170,"area":null},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147,"area":null},{"id":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138,"area":null},{"id":"2105.07342","title":"Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive","created":"2021-05-16","cited_by_count":136,"area":null},{"id":"2202.08235","title":"Data Augmentation for Deep Graph Learning: A Survey","created":"2022-02-16","cited_by_count":133,"area":null},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133,"area":null},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114,"area":null},{"id":"2102.05034","title":"SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks","created":"2021-02-09","cited_by_count":110,"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":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2310.11829","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","created":"2023-10-18","cited_by_count":103,"area":null},{"id":"2301.09474","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","created":"2023-01-23","cited_by_count":87,"area":null},{"id":"2304.11116","title":"Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT","created":"2023-04-10","cited_by_count":80,"area":"lr"},{"id":"2306.11025","title":"Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting","created":"2023-06-19","cited_by_count":77,"area":"lr"},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72,"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":"2204.07697","title":"Theory of Graph Neural Networks: Representation and Learning","created":"2022-04-16","cited_by_count":61,"area":null},{"id":"2311.16534","title":"Graph Prompt Learning: A Comprehensive Survey and Beyond","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2106.09876","title":"Anomaly Detection in Dynamic Graphs via Transformer","created":"2021-06-18","cited_by_count":59,"area":null},{"id":"2304.04193","title":"Extractive Summarization via ChatGPT for Faithful Summary Generation","created":"2023-04-09","cited_by_count":59,"area":null},{"id":"2102.10739","title":"Dissecting the Diffusion Process in Linear Graph Convolutional Networks","created":"2021-02-22","cited_by_count":58,"area":null},{"id":"2201.03662","title":"Learning Fair Node Representations with Graph Counterfactual Fairness","created":"2022-01-10","cited_by_count":58,"area":null},{"id":"2305.14835","title":"SummIt: Iterative Text Summarization via ChatGPT","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"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":"2105.00522","title":"Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer","created":"2021-05-02","cited_by_count":45,"area":null},{"id":"2105.04528","title":"Accelerating Large Scale Real-Time GNN Inference using Channel Pruning","created":"2021-05-10","cited_by_count":41,"area":null},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41,"area":null},{"id":"2103.05872","title":"Sampling methods for efficient training of graph convolutional networks: A survey","created":"2021-03-10","cited_by_count":40,"area":null},{"id":"2110.14363","title":"VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization","created":"2021-10-27","cited_by_count":39,"area":null},{"id":"2201.12674","title":"Rewiring with Positional Encodings for Graph Neural Networks","created":"2022-01-29","cited_by_count":36,"area":null},{"id":"2310.18152","title":"Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs","created":"2023-10-27","cited_by_count":36,"area":null},{"id":"2307.07107","title":"Graph Positional and Structural Encoder","created":"2023-07-14","cited_by_count":33,"area":null},{"id":"2402.02130","title":"GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning","created":"2024-02-03","cited_by_count":33,"area":"lr"},{"id":"2402.19302","title":"DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly","created":"2024-02-29","cited_by_count":33,"area":"diffusion"},{"id":"2404.14928","title":"Graph Machine Learning in the Era of Large Language Models (LLMs)","created":"2024-04-23","cited_by_count":33,"area":null},{"id":"2304.10668","title":"Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs","created":"2023-04-20","cited_by_count":29,"area":null},{"id":"2210.04126","title":"HEGEL: Hypergraph Transformer for Long Document Summarization","created":"2022-10-09","cited_by_count":28,"area":null},{"id":"2305.06424","title":"Bot or Human? Detecting ChatGPT Imposters with A Single Question","created":"2023-05-10","cited_by_count":26,"area":null},{"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,"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":"2202.07893","title":"A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications","created":"2022-02-16","cited_by_count":23,"area":null},{"id":"2301.12458","title":"SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking","created":"2023-01-29","cited_by_count":23,"area":null},{"id":"2210.13014","title":"Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks","created":"2022-10-24","cited_by_count":22,"area":"distill"},{"id":"2202.02989","title":"Graph Self-supervised Learning with Accurate Discrepancy Learning","created":"2022-02-07","cited_by_count":21,"area":null},{"id":"2207.02263","title":"Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control","created":"2022-07-05","cited_by_count":21,"area":null},{"id":"2207.09179","title":"SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization","created":"2022-07-19","cited_by_count":19,"area":null},{"id":"2401.00529","title":"GraphGPT: Generative Pre-trained Graph Eulerian Transformer","created":"2023-12-31","cited_by_count":17,"area":null},{"id":"2108.10733","title":"Graph Neural Networks: Methods, Applications, and Opportunities","created":"2021-08-24","cited_by_count":16,"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":"2207.10860","title":"Transformer with Implicit Edges for Particle-based Physics Simulation","created":"2022-07-22","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":"2304.05729","title":"Dynamic Graph Representation Learning with Neural Networks: A Survey","created":"2023-04-12","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":"2406.01977","title":"What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding","created":"2024-06-04","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":"2201.13311","title":"Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer","created":"2022-01-25","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":"2511.05592","title":"GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning","created":"2025-11-05","cited_by_count":13,"area":null},{"id":"2206.05658","title":"Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization","created":"2022-06-12","cited_by_count":12,"area":null},{"id":"2501.01124","title":"Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning","created":"2025-01-02","cited_by_count":12,"area":null},{"id":"2502.18771","title":"Exploring Graph Learning Tasks with Pure LLMs: A Comprehensive Benchmark and Investigation","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2503.00912","title":"HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning","created":"2025-03-02","cited_by_count":12,"area":"lr"},{"id":"2306.15154","title":"Contrastive Meta-Learning for Few-shot Node Classification","created":"2023-06-27","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":"2412.15589","title":"Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck","created":"2024-12-20","cited_by_count":11,"area":null},{"id":"2503.01805","title":"Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers","created":"2025-03-03","cited_by_count":11,"area":null},{"id":"2109.00269","title":"Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs","created":"2021-09-01","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":"2207.10603","title":"Unsupervised pre-training of graph transformers on patient population graphs","created":"2022-07-21","cited_by_count":9,"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":"2305.11424","title":"Graph Propagation Transformer for Graph Representation Learning","created":"2023-05-19","cited_by_count":9,"area":null},{"id":"2308.10737","title":"UGSL: A Unified Framework for Benchmarking Graph Structure Learning","created":"2023-08-21","cited_by_count":9,"area":null},{"id":"2403.16137","title":"A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective","created":"2024-03-24","cited_by_count":9,"area":null},{"id":"2105.14357","title":"Constructing Flow Graphs from Procedural Cybersecurity Texts","created":"2021-05-29","cited_by_count":8,"area":null},{"id":"2205.00731","title":"Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning","created":"2022-05-02","cited_by_count":8,"area":"lr"},{"id":"2206.14337","title":"Deformable Graph Transformer","created":"2022-06-29","cited_by_count":7,"area":null},{"id":"2503.09363","title":"Towards Graph Foundation Models: A Transferability Perspective","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2212.09724","title":"A Retrieve-and-Read Framework for Knowledge Graph Link Prediction","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2412.11983","title":"Leveraging Large Language Models for Effective Label-free Node Classification in Text-Attributed Graphs","created":"2024-12-16","cited_by_count":6,"area":null},{"id":"2111.10447","title":"DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability","created":"2021-11-19","cited_by_count":5,"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":"2310.05296","title":"Tailoring Self-Attention for Graph via Rooted Subtrees","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2401.15203","title":"FedGT: Federated Node Classification with Scalable Graph Transformer","created":"2024-01-26","cited_by_count":5,"area":null},{"id":"2405.17535","title":"Calibrated Dataset Condensation for Faster Hyperparameter Search","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2407.14106","title":"TorchGT: A Holistic System for Large-scale Graph Transformer Training","created":"2024-07-19","cited_by_count":5,"area":null},{"id":"2602.04768","title":"Billion-Scale Graph Foundation Models","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2106.04993","title":"Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2309.03219","title":"Companion Animal Disease Diagnostics based on Literal-aware Medical Knowledge Graph Representation Learning","created":"2023-08-31","cited_by_count":4,"area":null},{"id":"2403.09721","title":"A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction","created":"2024-03-12","cited_by_count":4,"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":"2405.19779","title":"Automatic Graph Topology-Aware Transformer","created":"2024-05-30","cited_by_count":4,"area":null}],"next_cursor":"100"}