REVIEW 5 cited by
Understanding Isomorphism Bias in Graph Data Sets
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
In recent years there has been a rapid increase in classification methods on graph structured data. Both in graph kernels and graph neural networks, one of the implicit assumptions of successful state-of-the-art models was that incorporating graph isomorphism features into the architecture leads to better empirical performance. However, as we discover in this work, commonly used data sets for graph classification have repeating instances which cause the problem of isomorphism bias, i.e. artificially increasing the accuracy of the models by memorizing target information from the training set. This prevents fair competition of the algorithms and raises a question of the validity of the obtained results. We analyze 54 data sets, previously extensively used for graph-related tasks, on the existence of isomorphism bias, give a set of recommendations to machine learning practitioners to properly set up their models, and open source new data sets for the future experiments.
Forward citations
Cited by 5 Pith papers
-
CryptGNN: Enabling Secure Inference for Graph Neural Networks
CryptGNN lets a client run a third-party GNN model on sensitive graph data using secret-shared computations across multiple cloud servers, keeping both data and model private.
-
Robust Graph Learning Against Adversarial Evasion Attacks via Prior-Free Diffusion-Based Structure Purification
DiffSP purifies attacked graphs by learning the clean graph distribution with a discrete diffusion model and reports consistent accuracy improvements over baselines on nine datasets and nine evasion attacks.
-
Predicting Steady-State Behavior in Complex Networks with Graph Neural Networks
A GCN/GAT framework predicts IPR values of the principal eigenvector and classifies networks into delocalized, weakly localized, and strongly localized states with roughly 95 percent accuracy on synthetic test networks.
-
KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks
Swapping attentive GNN score mappings for a single-layer Kolmogorov-Arnold Network improves benchmark performance and, on a specially constructed input matrix, provably achieves zero maximum ranking error.
-
Graph Counterfactual Explainable AI via Latent Space Traversal
Counterfactual graph explanations are generated by gradient descent in the latent space of a permutation-equivariant graph VAE, steering the graph's encoding to the opposite class.
Discussion (0). Continue with ORCID to comment.