Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences

• URL: http://arxiv.org/abs/2603.20025v1
• Date: Fri, 20 Mar 2026 15:12:42 GMT
• Title: Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences
• Abstract summary: We study adversarial learning when the target distribution factorizes according to a known Bayesian network.<n>We prove a new infimal subadditivity principle showing that, under suitable conditions, a global variational discrepancy is controlled by an average of family-level discrepancies aligned with the graph.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study adversarial learning when the target distribution factorizes according to a known Bayesian network. For interpolative divergences, including $(f,Γ)$-divergences, we prove a new infimal subadditivity principle showing that, under suitable conditions, a global variational discrepancy is controlled by an average of family-level discrepancies aligned with the graph. In an additive regime, this surrogate is exact. This provides a variational justification for replacing a graph-agnostic GAN with a monolithic discriminator by a graph-informed GAN with localized family-level discriminators. The result does not require the optimizer itself to factorize according to the graph. We also obtain parallel results for integral probability metrics and proximal optimal transport divergences, identify natural discriminator classes for which the theory applies, and present experiments showing improved stability and structural recovery relative to graph-agnostic baselines.

Related papers

• Directed Graph Topology Inference via Graph Filter Identification [54.541275287889164]
  We address the problem of inferring a directed network from nodal measurements generated by a graph convolutional filter.<n>A joint graph filter and topology identification algorithm is also proposed, which alternates between the aforementioned steps to offer improved sample complexity.
  arXiv  Detail & Related papers  (2026-06-25T18:25:57Z)
• Global Convergence of Gradient Descent for Score Matching in Gaussian Mixtures via Reverse Fisher Divergence [67.12978375116599]
  We study an alternative objective: the reverse Fisher divergence, where the expectation is taken with respect to the student distribution.<n>We prove global convergence guarantees under a $widetilde(1)$-separation assumption on the target means.<n>Our rely on a new Lyapunov-based analysis of the gradient descent dynamics, showing that the reverse Fisher divergence has a much more favorable optimization landscape than the forward Fisher divergence.
  arXiv  Detail & Related papers  (2026-06-18T07:34:33Z)
• A Theory of Random Graph Shift in Truncated-Spectrum vRKHS [26.195791008324495]
  This paper develops a theory of graph classification under domain shift through a random-graph generative lens.<n>We consider intra-class graphs sharing the same random graph model (RGM) and the domain shift induced by changes in RGM components.
  arXiv  Detail & Related papers  (2026-02-27T10:19:57Z)
• Moment Matters: Mean and Variance Causal Graph Discovery from Heteroscedastic Observational Data [2.436681150766912]
  Heteroscedasticity -- where the variance of a variable changes with other variables -- is pervasive in real data.<n>Standard causal discovery does not reveal which causes act on the mean versus the variance, as it returns a single moment-agnostic graph.<n>We propose a Bayesian, moment-driven causal discovery framework that infers separate textitmean and textit variance causal graphs from observational heteroscedastic data.
  arXiv  Detail & Related papers  (2026-02-27T02:13:03Z)
• Representation Geometry as a Diagnostic for Out-of-Distribution Robustness [0.5978543974412219]
  We propose a geometry-based diagnostic framework that constructs class-conditional mutual k-nearest-neighbor graphs from in-distribution embeddings.<n>We find that lower spectral complexity and higher mean curvature consistently predict stronger out-of-distribution (OOD) accuracy across checkpoints.<n>Our results demonstrate that representation geometry enables interpretable, label-free diagnosis and supports reliable unsupervised checkpoint selection.
  arXiv  Detail & Related papers  (2026-02-03T19:13:36Z)
• Consistent DAG selection for Bayesian causal discovery under general error distributions [9.971549076128268]
  We consider the problem of learning the underlying causal structure among a set of variables.<n>The associated errors are independent and allowed to be non-Gaussian.<n>A Bayesian hierarchical model is proposed to identify the true data-generating directed acyclic graph (DAG) structure.
  arXiv  Detail & Related papers  (2025-08-01T18:03:28Z)
• A Unified Invariant Learning Framework for Graph Classification [25.35939628738617]
  Invariant learning aims to recognize stable features in graph data for classification.<n>We introduce the Unified Invariant Learning framework for graph classification.<n>We present both theoretical and empirical evidence to confirm our method's ability to recognize superior stable features.
  arXiv  Detail & Related papers  (2025-01-22T02:45:21Z)
• Identifiable Latent Neural Causal Models [82.14087963690561]
  Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
  arXiv  Detail & Related papers  (2024-03-23T04:13:55Z)
• Learning Graphical Factor Models with Riemannian Optimization [70.13748170371889]
  This paper proposes a flexible algorithmic framework for graph learning under low-rank structural constraints. The problem is expressed as penalized maximum likelihood estimation of an elliptical distribution. We leverage geometries of positive definite matrices and positive semi-definite matrices of fixed rank that are well suited to elliptical models.
  arXiv  Detail & Related papers  (2022-10-21T13:19:45Z)
• Invariance Principle Meets Out-of-Distribution Generalization on Graphs [66.04137805277632]
  Complex nature of graphs thwarts the adoption of the invariance principle for OOD generalization. domain or environment partitions, which are often required by OOD methods, can be expensive to obtain for graphs. We propose a novel framework to explicitly model this process using a contrastive strategy.
  arXiv  Detail & Related papers  (2022-02-11T04:38:39Z)
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs [51.33152272781324]
  Graph Neural Networks (GNNs) are proposed without considering the distribution shifts between training and testing graphs. In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation. We propose a general causal representation framework, called StableGNN, to eliminate the impact of spurious correlations.
  arXiv  Detail & Related papers  (2021-11-20T18:57:18Z)

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.