{"total":163,"rows":[{"id":"2302.11640","title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","created":"2023-02-22","cited_by_count":343,"area":null},{"id":"2305.10498","title":"Edge Directionality Improves Learning on Heterophilic Graphs","created":"2023-05-17","cited_by_count":90,"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":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83,"area":null},{"id":"2211.14208","title":"GREAD: Graph Neural Reaction-Diffusion Networks","created":"2022-11-25","cited_by_count":54,"area":null},{"id":"2405.16771","title":"ARC: A Generalist Graph Anomaly Detector with In-Context Learning","created":"2024-05-27","cited_by_count":48,"area":null},{"id":"2304.14621","title":"MUDiff: Unified Diffusion for Complete Molecule Generation","created":"2023-04-28","cited_by_count":42,"area":null},{"id":"2306.01323","title":"Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?","created":"2023-06-02","cited_by_count":41,"area":null},{"id":"2405.20445","title":"Fully-inductive Node Classification on Arbitrary Graphs","created":"2024-05-30","cited_by_count":39,"area":null},{"id":"2310.18884","title":"Simple and Asymmetric Graph Contrastive Learning without Augmentations","created":"2023-10-29","cited_by_count":38,"area":null},{"id":"2412.16441","title":"Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees","created":"2024-12-21","cited_by_count":32,"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":"2305.16780","title":"Graph Neural Convection-Diffusion with Heterophily","created":"2023-05-26","cited_by_count":26,"area":null},{"id":"2401.11750","title":"AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneity","created":"2024-01-22","cited_by_count":25,"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":"2310.02232","title":"HoloNets: Spectral Convolutions do extend to Directed Graphs","created":"2023-10-03","cited_by_count":20,"area":null},{"id":"2210.17224","title":"Improving Graph Neural Networks with Learnable Propagation Operators","created":"2022-10-31","cited_by_count":19,"area":null},{"id":"2212.10822","title":"Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Neural Networks","created":"2022-12-21","cited_by_count":19,"area":null},{"id":"2310.02861","title":"Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection","created":"2023-10-04","cited_by_count":19,"area":null},{"id":"2312.04111","title":"Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification","created":"2023-12-07","cited_by_count":19,"area":null},{"id":"2505.15547","title":"Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning","created":"2025-05-21","cited_by_count":19,"area":null},{"id":"2212.02483","title":"TIDE: Time Derivative Diffusion for Deep Learning on Graphs","created":"2022-12-05","cited_by_count":17,"area":null},{"id":"2404.17099","title":"Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2502.02379","title":"No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets","created":"2025-02-04","cited_by_count":16,"area":null},{"id":"2305.04225","title":"LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity","created":"2023-05-07","cited_by_count":15,"area":null},{"id":"2401.09125","title":"Understanding Heterophily for Graph Neural Networks","created":"2024-01-17","cited_by_count":15,"area":null},{"id":"2212.13069","title":"Homophily modulates double descent generalization in graph convolution networks","created":"2022-12-26","cited_by_count":13,"area":null},{"id":"2308.09198","title":"Half-Hop: A graph upsampling approach for slowing down message passing","created":"2023-08-17","cited_by_count":13,"area":null},{"id":"2408.13659","title":"ReactZyme: A Benchmark for Enzyme-Reaction Prediction","created":"2024-08-24","cited_by_count":13,"area":null},{"id":"2305.18965","title":"Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2409.00687","title":"When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning","created":"2024-09-01","cited_by_count":12,"area":null},{"id":"2507.00647","title":"Cooperative Sheaf Neural Networks","created":"2025-07-01","cited_by_count":12,"area":null},{"id":"2305.00139","title":"Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks","created":"2023-04-29","cited_by_count":11,"area":null},{"id":"2403.10543","title":"Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs","created":"2024-03-11","cited_by_count":10,"area":null},{"id":"2604.19028","title":"Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors","created":"2026-04-21","cited_by_count":10,"area":null},{"id":"2401.11074","title":"On The Temporal Domain of Differential Equation Inspired Graph Neural Networks","created":"2024-01-20","cited_by_count":9,"area":null},{"id":"2402.04621","title":"Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2406.18854","title":"What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networks","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2407.20597","title":"Joint Diffusion Processes as an Inductive Bias in Sheaf Neural Networks","created":"2024-07-30","cited_by_count":9,"area":null},{"id":"2505.20089","title":"Homophily Enhanced Graph Domain Adaptation","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2306.13532","title":"PathMLP: Smooth Path Towards High-order Homophily","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2405.20652","title":"Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs","created":"2024-05-31","cited_by_count":8,"area":null},{"id":"2410.09118","title":"FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Network","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2506.16110","title":"Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification","created":"2025-06-19","cited_by_count":8,"area":null},{"id":"2301.09851","title":"Neighborhood Homophily-based Graph Convolutional Network","created":"2023-01-24","cited_by_count":7,"area":null},{"id":"2302.03228","title":"Heterophily-Aware Graph Attention Network","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2302.13875","title":"Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts","created":"2023-02-27","cited_by_count":7,"area":null},{"id":"2304.14274","title":"When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability","created":"2023-04-25","cited_by_count":7,"area":null},{"id":"2304.14635","title":"Imbalanced Node Classification Beyond Homophilic Assumption","created":"2023-04-28","cited_by_count":7,"area":null},{"id":"2311.06554","title":"PGODE: Towards High-quality System Dynamics Modeling","created":"2023-11-11","cited_by_count":7,"area":null},{"id":"2411.05274","title":"Distributed-Order Fractional Graph Operating Network","created":"2024-11-08","cited_by_count":7,"area":null},{"id":"2507.02409","title":"S2FGL: Spatial Spectral Federated Graph Learning","created":"2025-07-03","cited_by_count":7,"area":null},{"id":"2403.01475","title":"Representation Learning on Heterophilic Graph with Directional Neighborhood Attention","created":"2024-03-03","cited_by_count":6,"area":null},{"id":"2407.10916","title":"When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2408.09490","title":"Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts","created":"2024-08-18","cited_by_count":6,"area":null},{"id":"2409.11504","title":"Preventing Representational Rank Collapse in MPNNs by Splitting the Computational Graph","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2410.02622","title":"Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms","created":"2024-10-03","cited_by_count":6,"area":null},{"id":"2412.16435","title":"THeGCN: Temporal Heterophilic Graph Convolutional Network","created":"2024-12-21","cited_by_count":6,"area":null},{"id":"2505.02573","title":"Rethinking Federated Graph Learning: A Data Condensation Perspective","created":"2025-05-05","cited_by_count":6,"area":null},{"id":"2512.21106","title":"Semantic Refinement with LLMs for Graph Representations","created":"2025-12-24","cited_by_count":6,"area":null},{"id":"2210.16508","title":"Clenshaw Graph Neural Networks","created":"2022-10-29","cited_by_count":5,"area":null},{"id":"2306.02285","title":"Clarify Confused Nodes via Separated Learning","created":"2023-06-04","cited_by_count":5,"area":null},{"id":"2308.09570","title":"Investigating the Interplay between Features and Structures in Graph Learning","created":"2023-08-18","cited_by_count":5,"area":null},{"id":"2310.04171","title":"Dynamic Relation-Attentive Graph Neural Networks for Fraud Detection","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2310.11025","title":"SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2402.03675","title":"Effective Protein-Protein Interaction Exploration with PPIretrieval","created":"2024-02-06","cited_by_count":5,"area":null},{"id":"2404.14886","title":"GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2405.17768","title":"Revisiting the Message Passing in Heterophilous Graph Neural Networks","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2406.13125","title":"A Unified Framework for Combinatorial Optimization Based on Graph Neural Networks","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2410.00327","title":"EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamics","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2502.08101","title":"Rethinking Tokenized Graph Transformers for Node Classification","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2211.11761","title":"From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm","created":"2022-11-21","cited_by_count":4,"area":null},{"id":"2306.16976","title":"Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2402.07999","title":"NetInfoF Framework: Measuring and Exploiting Network Usable Information","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2404.03139","title":"Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2409.05755","title":"Revealing the Pitfalls and Re-Evaluating the Advancement of Heterophilic Graph Learning","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2412.09663","title":"Revisiting Graph Homophily Measures","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2306.14340","title":"GPatcher: A Simple and Adaptive MLP Model for Alleviating Graph Heterophily","created":"2023-06-25","cited_by_count":3,"area":null},{"id":"2310.05105","title":"How Graph Neural Networks Learn: Lessons from Training Dynamics","created":"2023-10-08","cited_by_count":3,"area":null},{"id":"2401.15584","title":"DGNN: Decoupled Graph Neural Networks with Structural Consistency between Attribute and Graph Embedding Representations","created":"2024-01-28","cited_by_count":3,"area":null},{"id":"2409.09888","title":"Flexible Diffusion Scopes with Parameterized Laplacian for Heterophilic Graph Learning","created":"2024-09-15","cited_by_count":3,"area":null},{"id":"2412.07188","title":"Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective","created":"2024-12-10","cited_by_count":3,"area":null},{"id":"2510.10864","title":"HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2306.08274","title":"A Simple and Scalable Graph Neural Network for Large Directed Graphs","created":"2023-06-14","cited_by_count":2,"area":null},{"id":"2403.20221","title":"Graph Neural Aggregation-diffusion with Metastability","created":"2024-03-29","cited_by_count":2,"area":null},{"id":"2405.19919","title":"Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2407.18480","title":"Scalable Graph Compressed Convolutions","created":"2024-07-26","cited_by_count":2,"area":null},{"id":"2412.04064","title":"Graph Neural Networks Need Cluster-Normalize-Activate Modules","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2412.08310","title":"Edge-Splitting MLP: Node Classification on Homophilic and Heterophilic Graphs without Message Passing","created":"2024-12-11","cited_by_count":2,"area":null},{"id":"2412.09805","title":"Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness-Generalization Perspective","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2502.11394","title":"A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2505.19762","title":"Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2505.22152","title":"Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2603.00143","title":"GrapHist: Graph Self-Supervised Learning for Histopathology","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2210.16979","title":"When Do We Need Graph Neural Networks for Node Classification?","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2305.18385","title":"Self-attention Dual Embedding for Graphs with Heterophily","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2306.12640","title":"On Addressing the Limitations of Graph Neural Networks","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2310.05250","title":"Simple GNNs with Low Rank Non-parametric Aggregators","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2310.16401","title":"Graph Neural Networks with a Distribution of Parametrized Graphs","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2401.09754","title":"Towards Robust Graph Structural Learning Beyond Homophily via Preserving Neighbor Similarity","created":"2024-01-18","cited_by_count":1,"area":null}],"next_cursor":"100"}