No article text was recorded for this version.
subgraph-based expressivity
Version 1 of 160 papers72 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Theoretical Comparison of Graph Neural Network Extensions
- Blog: Boosting Graph Structure Learning with Dummy Nodes
- Blog: Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
- Blog: KerGNNs: Interpretable Graph Neural Networks with Graph Kernels
- Blog: Collaboration-Aware Graph Convolutional Network for Recommender Systems
- Blog: Weisfeiler–Leman at the margin
- Blog: A Theoretical Comparison of Graph Neural Network Extensions
- Blog: $\mathcal{O}$-GNN: incorporating ring priors into molecular modeling
- Blog: Graph Filtration Kernels
- Blog: Substructure Aware Graph Neural Networks
- Blog: GLASS: GNN with Labeling Tricks for Subgraph Representation Learning
- Blog: Graph Neural Networks with Local Graph Parameters
- Blog: Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability
- Blog: Person Re-Identification Using Local Relation-Aware Graph Convolutional Network
- Blog: Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
- Blog: Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power
- Blog: 𝒪-GNN: incorporating ring priors into molecular modeling
- Blog: KerGNNs: Interpretable Graph Neural Networks with Graph Kernels
- Blog: Shortest Path Networks for Graph Property Prediction
- Blog: Graph Pooling Provably Improves Expressivity
- Blog: Learning Scalable Structural Representations for Link Prediction with Bloom Signatures
- Blog: Galois Theory Challenges Weisfeiler Leman: Invariant Features for Symmetric Matrices and Point Clouds
- Blog: Reconstruction for Powerful Graph Representations
- Blog: Decoupling the Depth and Scope of Graph Neural Networks
- Blog: Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
- Blog: Equivariant Polynomials for Graph Neural Networks
- Blog: Two-Level Graph Neural Network
- Blog: Harnessing Collective Structure Knowledge in Data Augmentation for Graph Neural Networks
- Blog: Counting Graph Substructures with Graph Neural Networks
- Blog: Learning Conjoint Attentions for Graph Neural Nets
- Blog: Affinity-Aware Graph Networks
- Blog: MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy
- Blog: Edge Rewiring Goes Neural: Boosting Network Resilience via Policy Gradient
- Blog: Deep Homomorphism Networks
- Blog: Recurrent Temporal Revision Graph Networks
- Blog: Data Augmentation for Deep Graph Learning: A Survey
- Blog: Improving the Expressiveness of K-hop Message-Passing GNNs by Injecting Contextualized Substructure Information
- Blog: AnchorGT: Efficient and Flexible Attention Architecture for Scalable Graph Transformers
- Blog: Probabilistic Graph Rewiring via Virtual Nodes
- Blog: Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs
- Blog: Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization
- Blog: Diffusion Probabilistic Models for Structured Node Classification
- Blog: Local Vertex Colouring Graph Neural Networks
- Blog: Boosting Graph Structure Learning with Dummy Nodes
- Blog: MuseGNN: Interpretable and Convergent Graph Neural Network Layers at Scale
- Blog: An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
- Blog: Nested Graph Neural Networks
- Blog: Wasserstein Graph Distance Based on L1-Approximated Tree Edit Distance between Weisfeiler-Lehman Subtrees
- Blog: Subgraph Permutation Equivariant Networks
- Blog: From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
- Blog: 𝒩-WL: A New Hierarchy of Expressivity for Graph Neural Networks
- Blog: Learning Long Range Dependencies on Graphs via Random Walks
- Blog: Discrete Graph Auto-Encoder
- Blog: Expressive Graph Informer Networks
- Blog: On The Expressive Power of GNN Derivatives
- Blog: Full-Spectrum Graph Neural Networks: Expressive and Scalable
- Blog: Weisfeiler-Leman at the margin: When more expressivity matters
- Blog: Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization
- Blog: Homomorphism Counts for Graph Neural Networks: All About That Basis
- Blog: Weisfeiler-Leman at the margin: When more expressivity matters
History & citation
Current · Permanent link
- This direction split from 1-WL expressivity limit (80% overlap)
- This direction split from Higher Order Topological Deep Learning (95% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_subgraph_based_expressivity_3fe7c302,
title = {subgraph-based expressivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/subgraph-based-expressivity/rdr_3fe7c302819640c1acadb5cec6612164},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_subgraph_based_expressivity_3fe7c302_v1,
title = {subgraph-based expressivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/subgraph-based-expressivity/rdr_3fe7c302819640c1acadb5cec6612164/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}