No article text was recorded for this version.
expressivity-generalization tradeoff
Version 1 of 137 papers54 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Rademacher Meets Colors: More Expressivity, but at What Cost?
- Blog: Weisfeiler–Leman at the margin
- Blog: WL meet VC
- Blog: Will More Expressive Graph Neural Networks Do Better on Generative Tasks?
- Blog: How Powerful are Graph Neural Networks?
- Blog: Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
- Blog: Position: Future Directions in the Theory of Graph Machine Learning
- Blog: The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs
- Blog: Graph Representational Learning: When Does More Expressivity Hurt Generalization?
- Blog: Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
- Blog: Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks
- Blog: Towards a Theory of Machine Learning on Graphs and its Applications in Combinatorial Optimization
- Blog: Sign Rank Limitations for Inner Product Graph Decoders
- Blog: Expressive Power of Invariant and Equivariant Graph Neural Networks
- Blog: Towards Better Evaluation of GNN Expressiveness with BREC Dataset
- Blog: Graph CNN for Moving Object Detection in Complex Environments from Unseen Videos
- Blog: On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encoding
- Blog: Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
- Blog: SpeqNets: Sparsity-aware permutation-equivariant graph networks
- Blog: ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
- Blog: Provably Powerful Graph Networks
- Blog: Graph Positional Encoding via Random Feature Propagation
- Blog: A Theoretical Comparison of Graph Neural Network Extensions
- Blog: On dimensionality of feature vectors in MPNNs
- Blog: Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs
- Blog: Size-Invariant Graph Representations for Graph Classification Extrapolations
- Blog: A survey on graph kernels
- Blog: 𝒩-WL: A New Hierarchy of Expressivity for Graph Neural Networks
- Blog: Coloring Graph Neural Networks for Node Disambiguation
- Blog: A Systematic Approach to Universal Random Features in Graph Neural Networks
- Blog: Neural Trees for Learning on Graphs
- Blog: PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
- Blog: EdgeNets: Edge Varying Graph Neural Networks
- Blog: On Graph Neural Networks versus Graph-Augmented MLPs
- Blog: Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization
- Blog: Covered Forest: Fine-grained generalization analysis of graph neural networks
- Blog: Expressive Pooling for Graph Neural Networks
History & citation
Current · Permanent link
- This direction split from Expressivity and Generalization in Graph Neural Networks (54% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_expressivity_generalization_tradeoff_345d78e3,
title = {expressivity-generalization tradeoff},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/expressivity-generalization-tradeoff/rdr_345d78e3bac44125b59c166be62363d8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_expressivity_generalization_tradeoff_345d78e3_v1,
title = {expressivity-generalization tradeoff},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/expressivity-generalization-tradeoff/rdr_345d78e3bac44125b59c166be62363d8/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}