No article text was recorded for this version.
1-WL expressivity limit
Version 2 of 21,002 papers1,486 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks
- Blog: A Topological characterisation of Weisfeiler-Leman equivalence classes
- Blog: Incompleteness of graph convolutional neural networks for points clouds in three dimensions
- Blog: Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
- Blog: Generalization limits of Graph Neural Networks in identity effects learning
- Blog: Topological Blind Spots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
- Blog: Can graph neural networks count substructures?
- Blog: Can Graph Neural Networks Count Substructures?
- Blog: How Powerful are Graph Neural Networks?
- Blog: A Theoretical Comparison of Graph Neural Network Extensions
- Blog: A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
- Blog: How Powerful are K-hop Message Passing Graph Neural Networks
- Blog: The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs
- Blog: Homomorphism Expressivity of Spectral Invariant Graph Neural Networks
- Blog: Examining graph neural networks for crystal structures: Limitations and opportunities for capturing periodicity
- Blog: Generalization and Representational Limits of Graph Neural Networks
- Blog: Cycle to Clique (Cy2C) Graph Neural Network: A Sight to See beyond Neighborhood Aggregation
- Blog: On the Expressive Power of GNNs for Boolean Satisfiability
- Blog: A Theoretical Comparison of Graph Neural Network Extensions
- Blog: Symmetries and Expressive Requirements for Learning General Policies
- Blog: What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much?
- Blog: Going beyond persistent homology using persistent homology
- Blog: Galois Theory Challenges Weisfeiler Leman: Invariant Features for Symmetric Matrices and Point Clouds
- Blog: Analyzing GFlowNets: Stability, Expressiveness, and Assessment
- Blog: Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
- Blog: On the Expressive Power of Spectral Invariant Graph Neural Networks
- Blog: Learning Domain-Independent Heuristics for Grounded and Lifted Planning
- Blog: Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
- Blog: Graph Embeddings: Theory meets Practice (Dagstuhl Seminar 22132)
- Blog: Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?
- Blog: A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
- Blog: A Survey on The Expressive Power of Graph Neural Networks
- Blog: Symmetries and Expressive Requirements for Learning General Policies
- Blog: Weisfeiler and Lehman Go Measurement Modeling: Probing the Validity of the WL Test
- Blog: Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
- Blog: Expressiveness and Approximation Properties of Graph Neural Networks
- Blog: Generalization and Representational Limits of Graph Neural Networks
- Blog: The expressive power of kth-order invariant graph networks
- Blog: Expressive Higher-Order Link Prediction through Hypergraph Symmetry Breaking
- Blog: Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
- Blog: How Powerful are Graph Neural Networks?
- Blog: On Representing Mixed-Integer Linear Programs by Graph Neural Networks
- Blog: Graph Homomorphism Convolution
- Blog: Weisfeiler and Leman Return with Graph Transformations
- Blog: Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
- Blog: Expressive Higher-Order Link Prediction through Hypergraph Symmetry Breaking
- Blog: Towards a Theory of Machine Learning on Graphs and its Applications in Combinatorial Optimization
- Blog: Graph Laplacians, Riemannian Manifolds and their Machine-Learning
- Blog: Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges
- Blog: word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data
- Blog: Graph-level Neural Networks: Current Progress and Future Directions
- Blog: Barriers for the performance of graph neural networks (GNN) in discrete random structures. A comment on~\cite{schuetz2022combinatorial}, \cite{angelini2023modern}, \cite{schuetz2023reply}
- Blog: The Power of Graph Convolutional Networks to Distinguish Random Graph Models: Short Version
- Blog: Rethinking the Capacity of Graph Neural Networks for Branching Strategy
- Blog: Foundations and Frontiers of Graph Learning Theory
- Blog: On the Expressive Power of Spectral Invariant Graph Neural Networks
- Blog: On Representing Convex Quadratically Constrained Quadratic Programs via Graph Neural Networks
- Blog: A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
- Blog: MANTRA: The Manifold Triangulations Assemblage
- Blog: edGNN: a Simple and Powerful GNN for Directed Labeled Graphs
Showing 60 of 1,002 papers.
History & citation
Current · Permanent link
- Higher Order Topological Deep Learning merged into this direction (62% overlap)
- Localized Higher Order Graph Neural Networks merged into this direction (62% overlap)
- Characterizing the Functional Power of Graph Neural Networks merged into this direction (85% overlap)
- Expressivity and Simplification of Spectral Graph Neural Networks merged into this direction (50% overlap)
- Local Automorphism Equivariance for Graph Neural Networks merged into this direction (67% overlap)
- Enhancing Graph Expressivity with Spectral Signatures merged into this direction (79% overlap)
- Communication Capacity and Information Bottlenecks in Graph Neural Networks merged into this direction (75% overlap)
- The Expressive Power of Graph Neural Networks merged into this direction (57% overlap)
- Injective Aggregation for Expressive Graph Neural Networks merged into this direction (50% overlap)
- Graph Isomorphism and the Universality of Graph Neural Networks merged into this direction (50% overlap)
- The Computation Tree Perspective of Graph Neural Networks merged into this direction (69% overlap)
- A Unified Hierarchy for Graph Neural Network Expressivity merged into this direction (68% overlap)
- Random Walk Structural Encodings for Graph Expressivity merged into this direction (71% overlap)
- topological expressivity split from this direction (76% overlap)
- subgraph-based expressivity split from this direction (80% overlap)
- stochastic symmetry breaking (structural symmetry breaking) split from this direction (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_1_wl_expressivity_limit_376ff515,
title = {1-WL expressivity limit},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/1-wl-expressivity-limit/rdr_376ff5150bfc448795c9906d14dd33f1},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_1_wl_expressivity_limit_376ff515_v2,
title = {1-WL expressivity limit},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/1-wl-expressivity-limit/rdr_376ff5150bfc448795c9906d14dd33f1/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}