{"total":604,"rows":[{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167,"area":null},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835,"area":null},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713,"area":null},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478,"area":null},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473,"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":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268,"area":null},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263,"area":null},{"id":"2106.10934","title":"GRAND: Graph Neural Diffusion","created":"2021-06-21","cited_by_count":258,"area":null},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247,"area":null},{"id":"2106.12575","title":"Weisfeiler and Lehman Go Cellular: CW Networks","created":"2021-06-23","cited_by_count":218,"area":null},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210,"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":"2208.09481","title":"Graph neural networks for materials science and chemistry","created":"2022-08-05","cited_by_count":182,"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":"2302.11636","title":"Do We Really Need Complicated Model Architectures For Temporal Networks?","created":"2023-02-22","cited_by_count":143,"area":null},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137,"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":"2304.04779","title":"GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner","created":"2023-04-10","cited_by_count":132,"area":null},{"id":"2202.02296","title":"Graph-Coupled Oscillator Networks","created":"2022-02-04","cited_by_count":124,"area":null},{"id":"2112.09992","title":"Weisfeiler and Leman go Machine Learning: The Story so far","created":"2021-12-18","cited_by_count":122,"area":null},{"id":"2301.09505","title":"Rethinking the Expressive Power of GNNs via Graph Biconnectivity","created":"2023-01-23","cited_by_count":119,"area":null},{"id":"2107.01188","title":"Combinatorial Optimization with Physics-Inspired Graph Neural Networks","created":"2021-07-02","cited_by_count":108,"area":null},{"id":"2210.11790","title":"FoSR: First-order spectral rewiring for addressing oversquashing in GNNs","created":"2022-10-21","cited_by_count":105,"area":null},{"id":"2310.11829","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","created":"2023-10-18","cited_by_count":103,"area":null},{"id":"2211.15779","title":"Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature","created":"2022-11-28","cited_by_count":98,"area":null},{"id":"2107.02392","title":"Dirichlet Energy Constrained Learning for Deep Graph Neural Networks","created":"2021-07-06","cited_by_count":97,"area":null},{"id":"2302.06835","title":"Understanding Oversquashing in GNNs through the Lens of Effective Resistance","created":"2023-02-14","cited_by_count":97,"area":null},{"id":"2201.07858","title":"Decoupling the Depth and Scope of Graph Neural Networks","created":"2022-01-19","cited_by_count":94,"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":"2406.04267","title":"Transformers need glasses! Information over-squashing in language tasks","created":"2024-06-06","cited_by_count":91,"area":null},{"id":"2301.09308","title":"On the Expressive Power of Geometric Graph Neural Networks","created":"2023-01-23","cited_by_count":90,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2301.08210","title":"Everything is Connected: Graph Neural Networks","created":"2023-01-19","cited_by_count":85,"area":null},{"id":"2406.08993","title":"Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification","created":"2024-06-13","cited_by_count":85,"area":null},{"id":"2110.09443","title":"Beltrami Flow and Neural Diffusion on Graphs","created":"2021-10-18","cited_by_count":84,"area":null},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83,"area":null},{"id":"2305.08018","title":"DRew: Dynamically Rewired Message Passing with Delay","created":"2023-05-13","cited_by_count":82,"area":null},{"id":"2206.07369","title":"DiffWire: Inductive Graph Rewiring via the Lov\\'asz Bound","created":"2022-06-15","cited_by_count":79,"area":null},{"id":"2210.02997","title":"Expander Graph Propagation","created":"2022-10-06","cited_by_count":75,"area":null},{"id":"2302.01524","title":"Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing","created":"2023-02-03","cited_by_count":67,"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":"2204.01855","title":"A Survey on Graph Representation Learning Methods","created":"2022-04-04","cited_by_count":66,"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":"2212.02374","title":"On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks","created":"2022-12-05","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":"2204.02782","title":"GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets","created":"2022-04-06","cited_by_count":61,"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":"2210.09789","title":"Anti-Symmetric DGN: a stable architecture for Deep Graph Networks","created":"2022-10-18","cited_by_count":60,"area":null},{"id":"2206.10991","title":"Understanding convolution on graphs via energies","created":"2022-06-22","cited_by_count":59,"area":null},{"id":"2110.15174","title":"On Provable Benefits of Depth in Training Graph Convolutional Networks","created":"2021-10-28","cited_by_count":58,"area":null},{"id":"2111.04840","title":"Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods","created":"2021-11-08","cited_by_count":58,"area":null},{"id":"2206.11168","title":"Ordered Subgraph Aggregation Networks","created":"2022-06-22","cited_by_count":57,"area":null},{"id":"2310.01668","title":"Locality-Aware Graph-Rewiring in GNNs","created":"2023-10-02","cited_by_count":56,"area":null},{"id":"2208.03471","title":"Oversquashing in GNNs through the lens of information contraction and graph expansion","created":"2022-08-06","cited_by_count":53,"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":"2210.00513","title":"Gradient Gating for Deep Multi-Rate Learning on Graphs","created":"2022-10-02","cited_by_count":49,"area":null},{"id":"2202.11097","title":"Message passing all the way up","created":"2022-02-22","cited_by_count":47,"area":null},{"id":"2206.01003","title":"Shortest Path Networks for Graph Property Prediction","created":"2022-06-02","cited_by_count":46,"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":"2502.10818","title":"On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning","created":"2025-02-15","cited_by_count":43,"area":null},{"id":"2309.09384","title":"Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature","created":"2023-09-17","cited_by_count":41,"area":null},{"id":"2103.04886","title":"Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks","created":"2021-03-08","cited_by_count":39,"area":null},{"id":"2210.05801","title":"Linkless Link Prediction via Relational Distillation","created":"2022-10-11","cited_by_count":39,"area":null},{"id":"2108.10521","title":"Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study","created":"2021-08-24","cited_by_count":36,"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":"2310.01267","title":"Cooperative Graph Neural Networks","created":"2023-10-02","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":"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":"2408.06316","title":"Body Transformer: Leveraging Robot Embodiment for Policy Learning","created":"2024-08-12","cited_by_count":32,"area":null},{"id":"2206.05437","title":"ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks","created":"2022-06-11","cited_by_count":31,"area":null},{"id":"2208.08302","title":"Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing","created":"2022-08-17","cited_by_count":31,"area":null},{"id":"2211.04952","title":"Graph Neural Networks with Adaptive Readouts","created":"2022-11-09","cited_by_count":29,"area":null},{"id":"2202.13538","title":"Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning","created":"2022-02-28","cited_by_count":28,"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":"2406.02740","title":"Long Range Propagation on Continuous-Time Dynamic Graphs","created":"2024-06-04","cited_by_count":28,"area":null},{"id":"2308.08235","title":"The Expressive Power of Graph Neural Networks: A Survey","created":"2023-08-16","cited_by_count":27,"area":null},{"id":"2309.04332","title":"Graph Neural Networks Use Graphs When They Shouldn't","created":"2023-09-08","cited_by_count":26,"area":null},{"id":"2310.02156","title":"Probabilistically Rewired Message-Passing Neural Networks","created":"2023-10-03","cited_by_count":26,"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":"2407.11095","title":"DeepGate3: Towards Scalable Circuit Representation Learning","created":"2024-07-15","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":"2111.04718","title":"Directional Message Passing on Molecular Graphs via Synthetic Coordinates","created":"2021-11-08","cited_by_count":24,"area":null},{"id":"2306.02376","title":"Towards Deep Attention in Graph Neural Networks: Problems and Remedies","created":"2023-06-04","cited_by_count":24,"area":null},{"id":"2312.16560","title":"Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching","created":"2023-12-27","cited_by_count":24,"area":null},{"id":"2404.04612","title":"Spectral Graph Pruning Against Over-Squashing and Over-Smoothing","created":"2024-04-06","cited_by_count":24,"area":null},{"id":"2405.12474","title":"How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing","created":"2024-05-21","cited_by_count":24,"area":null},{"id":"2205.11578","title":"BolT: Fused Window Transformers for fMRI Time Series Analysis","created":"2022-05-23","cited_by_count":23,"area":null},{"id":"2209.08264","title":"Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach","created":"2022-09-17","cited_by_count":23,"area":null},{"id":"2210.13148","title":"Transformers over Directed Acyclic Graphs","created":"2022-10-24","cited_by_count":23,"area":null},{"id":"2211.16199","title":"Latent Graph Inference using Product Manifolds","created":"2022-11-26","cited_by_count":23,"area":null},{"id":"2308.15568","title":"Over-Squashing in Graph Neural Networks: A Comprehensive survey","created":"2023-08-29","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":"2410.03424","title":"Cayley Graph Propagation","created":"2024-10-04","cited_by_count":21,"area":null},{"id":"2506.16640","title":"Long-Context Generalization with Sparse Attention","created":"2025-06-19","cited_by_count":21,"area":null}],"next_cursor":"100"}