{"total":152,"rows":[{"id":"2106.08903","title":"GemNet: Universal Directional Graph Neural Networks for Molecules","created":"2021-06-02","cited_by_count":343,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2104.09459","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","created":"2021-04-19","cited_by_count":187,"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":"2205.11172","title":"How Powerful are Spectral Graph Neural Networks","created":"2022-05-23","cited_by_count":169,"area":null},{"id":"2110.13197","title":"Nested Graph Neural Networks","created":"2021-10-25","cited_by_count":137,"area":null},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133,"area":null},{"id":"2106.06610","title":"Scalars are universal: Equivariant machine learning, structured like classical physics","created":"2021-06-11","cited_by_count":127,"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":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112,"area":null},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107,"area":null},{"id":"2106.04319","title":"Breaking the Limits of Message Passing Graph Neural Networks","created":"2021-06-08","cited_by_count":101,"area":null},{"id":"2102.10333","title":"Provably Strict Generalisation Benefit for Equivariant Models","created":"2021-02-20","cited_by_count":91,"area":null},{"id":"2402.00326","title":"PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks","created":"2024-02-01","cited_by_count":72,"area":null},{"id":"2110.05292","title":"Understanding Pooling in Graph Neural Networks","created":"2021-10-11","cited_by_count":69,"area":null},{"id":"2110.00577","title":"Reconstruction for Powerful Graph Representations","created":"2021-10-01","cited_by_count":65,"area":null},{"id":"2210.08566","title":"Theory for Equivariant Quantum Neural Networks","created":"2022-10-16","cited_by_count":62,"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":"2210.13978","title":"Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs","created":"2022-10-22","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":"2106.06707","title":"Graph Neural Networks with Local Graph Parameters","created":"2021-06-12","cited_by_count":52,"area":null},{"id":"2210.09974","title":"Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks","created":"2022-10-18","cited_by_count":52,"area":null},{"id":"2206.01003","title":"Shortest Path Networks for Graph Property Prediction","created":"2022-06-02","cited_by_count":46,"area":null},{"id":"2101.08543","title":"Boost then Convolve: Gradient Boosting Meets Graph Neural Networks","created":"2021-01-21","cited_by_count":44,"area":null},{"id":"2103.01710","title":"Autobahn: Automorphism-based Graph Neural Nets","created":"2021-03-02","cited_by_count":39,"area":null},{"id":"2209.12288","title":"On Representing Linear Programs by Graph Neural Networks","created":"2022-09-25","cited_by_count":39,"area":null},{"id":"2205.02956","title":"Low Dimensional Invariant Embeddings for Universal Geometric Learning","created":"2022-05-05","cited_by_count":38,"area":null},{"id":"2203.13913","title":"SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks","created":"2022-03-25","cited_by_count":37,"area":null},{"id":"2106.02346","title":"Provably Strict Generalisation Benefit for Invariance in Kernel Methods","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2106.00694","title":"Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators","created":"2021-06-01","cited_by_count":29,"area":null},{"id":"2303.14269","title":"The Exact Sample Complexity Gain from Invariances for Kernel Regression","created":"2023-03-24","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":"2405.18378","title":"A Canonicalization Perspective on Invariant and Equivariant Learning","created":"2024-05-28","cited_by_count":27,"area":null},{"id":"2105.13099","title":"On the Universality of Graph Neural Networks on Large Random Graphs","created":"2021-05-27","cited_by_count":26,"area":null},{"id":"2306.02866","title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","created":"2023-06-05","cited_by_count":26,"area":null},{"id":"2307.16506","title":"Explainable Equivariant Neural Networks for Particle Physics: PELICAN","created":"2023-07-31","cited_by_count":24,"area":null},{"id":"2404.01039","title":"A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide","created":"2024-04-01","cited_by_count":23,"area":null},{"id":"2410.04207","title":"Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models","created":"2024-10-05","cited_by_count":22,"area":null},{"id":"2205.07362","title":"What is an equivariant neural network?","created":"2022-05-15","cited_by_count":21,"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":"2405.20231","title":"The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof","created":"2024-05-30","cited_by_count":21,"area":null},{"id":"2106.00967","title":"Multiresolution Equivariant Graph Variational Autoencoder","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2203.07546","title":"Permutation Invariant Representations with Applications to Graph Deep Learning","created":"2022-03-14","cited_by_count":20,"area":null},{"id":"2210.09521","title":"A Practical, Progressively-Expressive GNN","created":"2022-10-18","cited_by_count":20,"area":null},{"id":"2303.04745","title":"A General Theory of Correct, Incorrect, and Extrinsic Equivariance","created":"2023-03-08","cited_by_count":19,"area":null},{"id":"2303.13458","title":"Optimization Dynamics of Equivariant and Augmented Neural Networks","created":"2023-03-23","cited_by_count":18,"area":null},{"id":"2506.14291","title":"Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models","created":"2025-06-17","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":"2402.08595","title":"Homomorphism Counts for Graph Neural Networks: All About That Basis","created":"2024-02-13","cited_by_count":16,"area":null},{"id":"2103.09360","title":"Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers","created":"2021-03-16","cited_by_count":15,"area":null},{"id":"2104.06703","title":"Deep Permutation Equivariant Structure from Motion","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2111.15341","title":"ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds","created":"2021-11-30","cited_by_count":15,"area":null},{"id":"2205.14368","title":"Going Deeper into Permutation-Sensitive Graph Neural Networks","created":"2022-05-28","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":"2208.10428","title":"Equivariant Hypergraph Neural Networks","created":"2022-08-22","cited_by_count":14,"area":null},{"id":"2105.07264","title":"Neural Trees for Learning on Graphs","created":"2021-05-15","cited_by_count":13,"area":null},{"id":"2206.08561","title":"Boosting Graph Structure Learning with Dummy Nodes","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2209.14991","title":"Machine learning and invariant theory","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2110.06390","title":"Learning ground states of quantum Hamiltonians with graph networks","created":"2021-10-12","cited_by_count":12,"area":null},{"id":"2211.16494","title":"On the Ability of Graph Neural Networks to Model Interactions Between Vertices","created":"2022-11-29","cited_by_count":12,"area":null},{"id":"2305.14814","title":"What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2309.04941","title":"Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power","created":"2023-09-10","cited_by_count":12,"area":null},{"id":"2402.07099","title":"Rethinking the Capacity of Graph Neural Networks for Branching Strategy","created":"2024-02-11","cited_by_count":12,"area":null},{"id":"2202.02164","title":"Group invariant machine learning by fundamental domain projections","created":"2022-02-04","cited_by_count":11,"area":null},{"id":"2203.01216","title":"A Simple and Universal Rotation Equivariant Point-cloud Network","created":"2022-03-02","cited_by_count":11,"area":null},{"id":"2205.14819","title":"Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups","created":"2022-05-30","cited_by_count":11,"area":null},{"id":"2307.01180","title":"PlanE: Representation Learning over Planar Graphs","created":"2023-07-03","cited_by_count":11,"area":null},{"id":"2401.10119","title":"Towards Principled Graph Transformers","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2103.07016","title":"On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions","created":"2021-03-12","cited_by_count":10,"area":null},{"id":"2201.10129","title":"Convergence of Invariant Graph Networks","created":"2022-01-25","cited_by_count":9,"area":null},{"id":"2208.08707","title":"Deep Neural Network Approximation of Invariant Functions through Dynamical Systems","created":"2022-08-18","cited_by_count":9,"area":null},{"id":"2304.11140","title":"Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs","created":"2023-04-21","cited_by_count":9,"area":null},{"id":"2401.09235","title":"A Characterization Theorem for Equivariant Networks with Point-wise Activations","created":"2024-01-17","cited_by_count":9,"area":null},{"id":"2406.19244","title":"Improving the Expressiveness of $K$-hop Message-Passing GNNs by Injecting Contextualized Substructure Information","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2307.04661","title":"On the power of graph neural networks and the role of the activation function","created":"2023-07-10","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":"2201.04672","title":"How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation","created":"2022-01-12","cited_by_count":7,"area":null},{"id":"2301.13060","title":"Zero-One Laws of Graph Neural Networks","created":"2023-01-30","cited_by_count":7,"area":null},{"id":"2309.02898","title":"A Unified Framework for Discovering Discrete Symmetries","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2410.18676","title":"Homomorphism Counts as Structural Encodings for Graph Learning","created":"2024-10-24","cited_by_count":7,"area":null},{"id":"2507.01649","title":"GradMetaNet: An Equivariant Architecture for Learning on Gradients","created":"2025-07-02","cited_by_count":7,"area":null},{"id":"2601.21645","title":"Identifiable Equivariant Networks are Layerwise Equivariant","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2211.15724","title":"Malign Overfitting: Interpolation Can Provably Preclude Invariance","created":"2022-11-28","cited_by_count":6,"area":null},{"id":"2307.04001","title":"Polynomial Width is Sufficient for Set Representation with High-dimensional Features","created":"2023-07-08","cited_by_count":6,"area":null},{"id":"2411.04219","title":"Equivariant Graph Network Approximations of High-Degree Polynomials for Force Field Prediction","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2109.11330","title":"Quantum algorithms for group convolution, cross-correlation, and equivariant transformations","created":"2021-09-23","cited_by_count":5,"area":null},{"id":"2202.08833","title":"What Functions Can Graph Neural Networks Generate?","created":"2022-02-17","cited_by_count":5,"area":null},{"id":"2205.09219","title":"A Classification of $G$-invariant Shallow Neural Networks","created":"2022-05-18","cited_by_count":5,"area":null},{"id":"2301.10152","title":"How Jellyfish Characterise Alternating Group Equivariant Neural Networks","created":"2023-01-24","cited_by_count":5,"area":null},{"id":"2410.04692","title":"A Clifford Algebraic Approach to E(n)-Equivariant High-order Graph Neural Networks","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2505.11298","title":"Graph Representational Learning: When Does More Expressivity Hurt Generalization?","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2110.08092","title":"Equivariant and Invariant Reynolds Networks","created":"2021-10-15","cited_by_count":4,"area":null},{"id":"2303.13750","title":"LON-GNN: Spectral GNNs with Learnable Orthonormal Basis","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2308.00273","title":"Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions","created":"2023-08-01","cited_by_count":4,"area":null},{"id":"2406.12841","title":"Demystifying Higher-Order Graph Neural Networks","created":"2024-06-18","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":"2501.07773","title":"Symmetry-Aware Generative Modeling through Learned Canonicalization","created":"2025-01-14","cited_by_count":4,"area":null},{"id":"2506.02293","title":"On Universality Classes of Equivariant Networks","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2510.22984","title":"Equivariant Neural Networks for General Linear Symmetries on Lie Algebras","created":"2025-10-27","cited_by_count":4,"area":null},{"id":"2205.09801","title":"Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis","created":"2022-05-19","cited_by_count":3,"area":null}],"next_cursor":"100"}