{"total":320,"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":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"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":"2110.03753","title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","created":"2021-10-07","cited_by_count":155,"area":null},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136,"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":"2206.00133","title":"Pre-training via Denoising for Molecular Property Prediction","created":"2022-05-31","cited_by_count":124,"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":"2311.07361","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","created":"2023-11-13","cited_by_count":112,"area":null},{"id":"2310.01089","title":"GraphText: Graph Reasoning in Text Space","created":"2023-10-02","cited_by_count":111,"area":"lr"},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107,"area":null},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102,"area":null},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"area":null},{"id":"2206.08917","title":"The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts","created":"2022-06-17","cited_by_count":95,"area":null},{"id":"2203.00199","title":"Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks","created":"2022-03-01","cited_by_count":94,"area":null},{"id":"2203.00274","title":"TableFormer: Robust Transformer Modeling for Table-Text Encoding","created":"2022-03-01","cited_by_count":91,"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":"2210.01765","title":"One Transformer Can Understand Both 2D & 3D Molecular Data","created":"2022-10-04","cited_by_count":77,"area":null},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72,"area":null},{"id":"2302.07253","title":"Energy Transformer","created":"2023-02-14","cited_by_count":71,"area":null},{"id":"2201.12787","title":"GRPE: Relative Positional Encoding for Graph Transformer","created":"2022-01-30","cited_by_count":70,"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":"2110.09681","title":"Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction","created":"2021-10-19","cited_by_count":68,"area":null},{"id":"2112.15009","title":"Knowledge Matters: Radiology Report Generation with General and Specific Knowledge","created":"2021-12-30","cited_by_count":68,"area":null},{"id":"2203.14500","title":"MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design","created":"2022-03-28","cited_by_count":66,"area":null},{"id":"2203.04810","title":"Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets","created":"2022-03-09","cited_by_count":64,"area":null},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63,"area":null},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"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":"2207.06010","title":"Does GNN Pretraining Help Molecular Representation?","created":"2022-07-13","cited_by_count":60,"area":null},{"id":"2308.16406","title":"CktGNN: Circuit Graph Neural Network for Electronic Design Automation","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2201.09637","title":"DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations","created":"2022-01-24","cited_by_count":54,"area":null},{"id":"2209.03299","title":"Multimodal learning with graphs","created":"2022-09-07","cited_by_count":54,"area":null},{"id":"2211.13878","title":"Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism","created":"2022-11-25","cited_by_count":53,"area":null},{"id":"2305.19987","title":"InGram: Inductive Knowledge Graph Embedding via Relation Graphs","created":"2023-05-31","cited_by_count":52,"area":null},{"id":"2202.11097","title":"Message passing all the way up","created":"2022-02-22","cited_by_count":47,"area":null},{"id":"2206.14331","title":"Spherical Channels for Modeling Atomic Interactions","created":"2022-06-29","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":"2106.07971","title":"Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond","created":"2021-06-15","cited_by_count":44,"area":null},{"id":"2110.01191","title":"Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs","created":"2021-10-04","cited_by_count":44,"area":null},{"id":"2302.13406","title":"GNNDelete: A General Strategy for Unlearning in Graph Neural Networks","created":"2023-02-26","cited_by_count":43,"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":"2302.00049","title":"Transformers Meet Directed Graphs","created":"2023-01-31","cited_by_count":40,"area":null},{"id":"2107.07999","title":"From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers","created":"2021-07-16","cited_by_count":38,"area":null},{"id":"2202.09346","title":"Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast","created":"2022-02-18","cited_by_count":37,"area":null},{"id":"2207.08824","title":"Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs","created":"2022-07-18","cited_by_count":37,"area":null},{"id":"2306.10045","title":"Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction","created":"2023-06-12","cited_by_count":37,"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":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"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":"2306.05955","title":"Path Neural Networks: Expressive and Accurate Graph Neural Networks","created":"2023-06-09","cited_by_count":32,"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":"2112.14397","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","created":"2021-12-29","cited_by_count":30,"area":"moe"},{"id":"2305.08740","title":"Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction","created":"2023-05-09","cited_by_count":30,"area":null},{"id":"2306.10280","title":"OpenGSL: A Comprehensive Benchmark for Graph Structure Learning","created":"2023-06-17","cited_by_count":30,"area":null},{"id":"2303.04143","title":"Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2403.00485","title":"A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications","created":"2024-03-01","cited_by_count":28,"area":null},{"id":"2110.00973","title":"Graph Pointer Neural Networks","created":"2021-10-03","cited_by_count":27,"area":null},{"id":"2305.12347","title":"Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation","created":"2023-05-21","cited_by_count":27,"area":"diffusion"},{"id":"2306.02866","title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","created":"2023-06-05","cited_by_count":26,"area":null},{"id":"2306.05445","title":"Towards Predicting Equilibrium Distributions for Molecular Systems with Deep Learning","created":"2023-06-08","cited_by_count":26,"area":null},{"id":"2202.01336","title":"Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation","created":"2022-02-02","cited_by_count":25,"area":null},{"id":"2402.02518","title":"Unifying Generation and Prediction on Graphs with Latent Graph Diffusion","created":"2024-02-04","cited_by_count":25,"area":"diffusion"},{"id":"2112.07160","title":"A New Perspective on the Effects of Spectrum in Graph Neural Networks","created":"2021-12-14","cited_by_count":24,"area":null},{"id":"2306.07812","title":"Automated 3D Pre-Training for Molecular Property Prediction","created":"2023-06-13","cited_by_count":24,"area":null},{"id":"2402.09617","title":"LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations","created":"2024-02-14","cited_by_count":24,"area":null},{"id":"2303.16982","title":"Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+","created":"2023-03-16","cited_by_count":22,"area":null},{"id":"2209.05582","title":"Graph Neural Networks for Molecules","created":"2022-09-12","cited_by_count":21,"area":null},{"id":"2202.09891","title":"Equivariant Graph Attention Networks for Molecular Property Prediction","created":"2022-02-20","cited_by_count":20,"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":"2404.14986","title":"$\\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning","created":"2024-04-23","cited_by_count":20,"area":null},{"id":"2406.01317","title":"The Interpretable and Effective Graph Neural Additive Networks","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2305.13987","title":"On Structural Expressive Power of Graph Transformers","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2406.00134","title":"Anomaly Detection in Dynamic Graphs: A Comprehensive Survey","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2205.11678","title":"Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation","created":"2022-05-24","cited_by_count":18,"area":"distill"},{"id":"2206.11941","title":"Affinity-Aware Graph Networks","created":"2022-06-23","cited_by_count":17,"area":null},{"id":"2207.05064","title":"Adaptive Graph Spatial-Temporal Transformer Network for Traffic Flow Forecasting","created":"2022-07-09","cited_by_count":17,"area":null},{"id":"2305.02866","title":"Hierarchical Transformer for Scalable Graph Learning","created":"2023-05-04","cited_by_count":17,"area":null},{"id":"2409.13194","title":"ChemDFM-X: Towards Large Multimodal Model for Chemistry","created":"2024-09-20","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":"2309.04082","title":"Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning","created":"2023-09-08","cited_by_count":15,"area":null},{"id":"2310.04610","title":"DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies","created":"2023-10-06","cited_by_count":15,"area":null},{"id":"2203.10280","title":"Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily","created":"2022-03-19","cited_by_count":14,"area":null},{"id":"2211.15335","title":"You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets","created":"2022-11-28","cited_by_count":14,"area":null},{"id":"2307.02031","title":"Improving Automatic Parallel Training via Balanced Memory Workload Optimization","created":"2023-07-05","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":"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":"2211.16684","title":"Capturing long-range interaction with reciprocal space neural network","created":"2022-11-30","cited_by_count":13,"area":null},{"id":"2402.02005","title":"Topology-Informed Graph Transformer","created":"2024-02-03","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":"2502.12979","title":"Electron flow matching for generative reaction mechanism prediction obeying conservation laws","created":"2025-02-18","cited_by_count":13,"area":"diffusion"},{"id":"2203.04695","title":"Structured Multi-task Learning for Molecular Property Prediction","created":"2022-02-22","cited_by_count":12,"area":null},{"id":"2402.04538","title":"Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers","created":"2024-02-07","cited_by_count":12,"area":null},{"id":"2506.07624","title":"Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks","created":"2025-06-09","cited_by_count":12,"area":null},{"id":"2112.03159","title":"UniLog: Deploy One Model and Specialize it for All Log Analysis Tasks","created":"2021-12-06","cited_by_count":11,"area":null},{"id":"2208.07012","title":"MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution","created":"2022-08-15","cited_by_count":11,"area":null}],"next_cursor":"100"}