Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
Datasets
State of the Art

Support

Contact
Pricing
Terms of Service
Privacy Policy
About

graph-classification

Isomorphism Testing

3260 papers • 126 benchmarks • 313 datasets

To test the power of graph representation learning methods based on Isomorphism Testing

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in graph-classification

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find graph-classification models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity

O-Joun Lee, Van Thuy Hoang•Thu Aug 17 2023

UGT reaches the expressive power of the third-order Weisfeiler-Lehman isomorphism test (3d-WL) in distinguishing non-isomorphic graph pairs and proposes a self-supervised learning task that effectively learns transition probability to fuse local and global structural features, which could be transferred to other downstream tasks.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Isomorphism Testing | State-of-the-Art

Paper Graph

Can graph neural networks count substructures?

Joan Bruna, Zhengdao Chen, Lei Chen, Soledad Villar•Sun Feb 09 2020

A local relational pooling approach with inspirations from Murphy et al. (2019) is proposed and demonstrated that it is not only effective for substructure counting but also able to achieve competitive performance on real-world tasks.

358 0

Paper Graph

On the equivalence between graph isomorphism testing and function approximation with GNNs

Joan Bruna, Zhengdao Chen, Lei Chen, Soledad Villar•Tue May 28 2019

It is proved that order-2 Graph G-invariant networks fail to distinguish non-isomorphic regular graphs with the same degree, and is extended to a new architecture, Ring-GNNs, which succeeds on distinguishing these graphs and provides improvements on real-world social network datasets.

305 0

Paper Graph

Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings

Chaim Baskin, A. Mendelson, Or Feldman, A. Boyarski, Shai Feldman, D. Kogan•Sun Jan 30 2022

This work shows that one can increase the expressive power of the Weisfeiler-Leman (WL) test ad infinitum, and proposes an efficient pre-coloring based on spectral features that provably increase the expressiveness of the vanilla WL test.

17 0

Paper Graph

On Graph Neural Networks versus Graph-Augmented MLPs

Zhengdao Chen, Lei Chen, Joan Bruna•Tue Oct 27 2020

This work compares multi-layer Graph Neural Networks with a simplified alternative that is called Graph-Augmented Multi-Layer Perceptrons (GA-MLPs), which first augments node features with certain multi-hop operators on the graph and then applies an MLP in a node-wise fashion.

48 0

Paper Graph

Gradual Weisfeiler-Leman: Slow and Steady Wins the Race

Nils M. Kriege, Franka Bause•Sun Sep 18 2022

This work generalizes the concept of color refinement and proposes a framework for gradual neighborhood refinement, which allows a slower convergence to the stable coloring and thus provides a more fine-grained refinement hierarchy and vertex similarity.

7 0

Paper Graph

A Practical, Progressively-Expressive GNN

L. Akoglu, Neil Shah, Lingxiao Zhao, Louis Härtel•Mon Oct 17 2022

This work proposes the (k, c)(<=)-SETWL hierarchy with greatly reduced complexity from k-WL, achieved by moving fromk-tuples of nodes to sets with<=k nodes defined over<=c connected components in the induced original graph, and shows favorable theoretical results for this model in relation to k- WL.

24 0

Paper Graph

PlanE: Representation Learning over Planar Graphs

Radoslav Dimitrov, Zeyang Zhao, Ralph Abboud, .Ismail .Ilkan Ceylan•Sun Jul 02 2023

Inspired by the classical planar graph isomorphism algorithm of Hopcroft and Tarjan, PlanE is proposed as a framework for planar representation learning, which includes architectures which can learn complete invariants over planar graphs while remaining practically scalable.

14 0

Paper Graph

Adding a benchmark result helps the community track progress.