PolyGraph Discrepancy: a classifier-based metric for graph generation

• URL: http://arxiv.org/abs/2510.06122v1
• Date: Tue, 07 Oct 2025 17:02:44 GMT
• Title: PolyGraph Discrepancy: a classifier-based metric for graph generation
• Authors: Markus Krimmel, Philip Hartout, Karsten Borgwardt, Dexiong Chen,
• Abstract summary: PolyGraph Discrepancy (PGD) is a new framework for evaluating graph generative models.<n>It approximates the Jensen-Shannon distance of graph distributions by fitting binary classifiers to distinguish between real and generated graphs.<n>Resulting metrics are constrained to the unit interval [0,1] and are comparable across different graph descriptors.
• Score: 6.719930635944071
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing methods for evaluating graph generative models primarily rely on Maximum Mean Discrepancy (MMD) metrics based on graph descriptors. While these metrics can rank generative models, they do not provide an absolute measure of performance. Their values are also highly sensitive to extrinsic parameters, namely kernel and descriptor parametrization, making them incomparable across different graph descriptors. We introduce PolyGraph Discrepancy (PGD), a new evaluation framework that addresses these limitations. It approximates the Jensen-Shannon distance of graph distributions by fitting binary classifiers to distinguish between real and generated graphs, featurized by these descriptors. The data log-likelihood of these classifiers approximates a variational lower bound on the JS distance between the two distributions. Resulting metrics are constrained to the unit interval [0,1] and are comparable across different graph descriptors. We further derive a theoretically grounded summary metric that combines these individual metrics to provide a maximally tight lower bound on the distance for the given descriptors. Thorough experiments demonstrate that PGD provides a more robust and insightful evaluation compared to MMD metrics. The PolyGraph framework for benchmarking graph generative models is made publicly available at https://github.com/BorgwardtLab/polygraph-benchmark.

Related papers

• Beyond Message Passing: Neural Graph Pattern Machine [50.78679002846741]
  We introduce the Neural Graph Pattern Machine (GPM), a novel framework that bypasses message passing by learning directly from graph substructures.<n>GPM efficiently extracts, encodes, and prioritizes task-relevant graph patterns, offering greater expressivity and improved ability to capture long-range dependencies.
  arXiv  Detail & Related papers  (2025-01-30T20:37:47Z)
• Graph GOSPA metric: a metric to measure the discrepancy between graphs of different sizes [3.8823562292981393]
  This paper proposes a metric to measure the dissimilarity between graphs that may have a different number of nodes. The proposed graph GOSPA metric includes costs associated with node attribute errors for properly assigned nodes, missed and false nodes and edge mismatches between graphs.
  arXiv  Detail & Related papers  (2023-11-10T11:40:24Z)
• GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generators [0.6816499294108261]
  We study kernel-based metrics on distributions of graph invariants and manifold-based and kernel-based metrics in graph embedding space. We compare GraphRNN and GRAN, two well-known generative models for graphs, and unveil the influence of node orderings.
  arXiv  Detail & Related papers  (2023-07-13T12:07:39Z)
• Graph Fourier MMD for Signals on Graphs [67.68356461123219]
  We propose a novel distance between distributions and signals on graphs. GFMMD is defined via an optimal witness function that is both smooth on the graph and maximizes difference in expectation. We showcase it on graph benchmark datasets as well as on single cell RNA-sequencing data analysis.
  arXiv  Detail & Related papers  (2023-06-05T00:01:17Z)
• Collaborative likelihood-ratio estimation over graphs [55.98760097296213]
  Graph-based Relative Unconstrained Least-squares Importance Fitting (GRULSIF) We develop this idea in a concrete non-parametric method that we call Graph-based Relative Unconstrained Least-squares Importance Fitting (GRULSIF) We derive convergence rates for our collaborative approach that highlights the role played by variables such as the number of available observations per node, the size of the graph, and how accurately the graph structure encodes the similarity between tasks.
  arXiv  Detail & Related papers  (2022-05-28T15:37:03Z)
• GraphDCA -- a Framework for Node Distribution Comparison in Real and Synthetic Graphs [72.51835626235368]
  We argue that when comparing two graphs, the distribution of node structural features is more informative than global graph statistics. We present GraphDCA - a framework for evaluating similarity between graphs based on the alignment of their respective node representation sets.
  arXiv  Detail & Related papers  (2022-02-08T14:19:19Z)
• On Evaluation Metrics for Graph Generative Models [17.594098458581694]
  We study existing graph generative models (GGMs) and neural-network-based metrics for evaluating GGMs. Motivated by the power of certain Graph Neural Networks (GNNs) to extract meaningful graph representations without any training, we introduce several metrics based on the features extracted by an untrained random GNN.
  arXiv  Detail & Related papers  (2022-01-24T18:49:27Z)
• Prototypical Graph Contrastive Learning [141.30842113683775]
  We propose a Prototypical Graph Contrastive Learning (PGCL) approach to mitigate the critical sampling bias issue. Specifically, PGCL models the underlying semantic structure of the graph data via clustering semantically similar graphs into the same group, and simultaneously encourages the clustering consistency for different augmentations of the same graph. For a query, PGCL further reweights its negative samples based on the distance between their prototypes (cluster centroids) and the query prototype.
  arXiv  Detail & Related papers  (2021-06-17T16:45:31Z)
• Scalable Graph Neural Networks for Heterogeneous Graphs [12.44278942365518]
  Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities.
  arXiv  Detail & Related papers  (2020-11-19T06:03:35Z)
• Block-Approximated Exponential Random Graphs [77.4792558024487]
  An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs. We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions. Our methods are scalable to sparse graphs consisting of millions of nodes.
  arXiv  Detail & Related papers  (2020-02-14T11:42:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.