On statistical learning of graphs

• URL: http://arxiv.org/abs/2507.13054v1
• Date: Thu, 17 Jul 2025 12:26:25 GMT
• Title: On statistical learning of graphs
• Authors: Vittorio Cipriani, Valentino Delle Rose, Luca San Mauro, Giovanni Solda,
• Abstract summary: We study PAC and online learnability of hypothesis classes formed by copies of a countably infinite graph G.<n>Our main result shows that PAC learnability of all such finite-support copies implies online learnability of the full isomorphism type of G.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study PAC and online learnability of hypothesis classes formed by copies of a countably infinite graph G, where each copy is induced by permuting G's vertices. This corresponds to learning a graph's labeling, knowing its structure and label set. We consider classes where permutations move only finitely many vertices. Our main result shows that PAC learnability of all such finite-support copies implies online learnability of the full isomorphism type of G, and is equivalent to the condition of automorphic triviality. We also characterize graphs where copies induced by swapping two vertices are not learnable, using a relaxation of the extension property of the infinite random graph. Finally, we show that, for all G and k>2, learnability for k-vertex permutations is equivalent to that for 2-vertex permutations, yielding a four-class partition of infinite graphs, whose complexity we also determine using tools coming from both descriptive set theory and computability theory.

Related papers

• Improving Subgraph Matching by Combining Algorithms and Graph Neural Networks [23.01521187724899]
  Homomorphism is a key mapping technique between graphs that preserves their structure.<n>We propose HFrame, the first graph neural network-based framework for subgraph homomorphism.<n>HFrame is up to 101.91 times faster than exact matching algorithms and achieves an average accuracy of 0.962.
  arXiv  Detail & Related papers  (2025-07-27T11:10:15Z)
• Discrete Graph Auto-Encoder [52.50288418639075]
  We introduce a new framework named Discrete Graph Auto-Encoder (DGAE) We first use a permutation-equivariant auto-encoder to convert graphs into sets of discrete latent node representations. In the second step, we sort the sets of discrete latent representations and learn their distribution with a specifically designed auto-regressive model.
  arXiv  Detail & Related papers  (2023-06-13T12:40:39Z)
• Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs [48.79929516665371]
  Graphs with homophily-prone edges tend to connect nodes with the same class. Heterophily-prone edges tend to build relationships between nodes with different classes. Existing GNNs only take the original graph during training.
  arXiv  Detail & Related papers  (2023-06-13T08:06:10Z)
• Graph Contrastive Learning with Personalized Augmentation [17.714437631216516]
  Graph contrastive learning (GCL) has emerged as an effective tool for learning unsupervised representations of graphs. We propose a principled framework, termed as textitGraph contrastive learning with textitPersonalized textitAugmentation (GPA) GPA infers tailored augmentation strategies for each graph based on its topology and node attributes via a learnable augmentation selector.
  arXiv  Detail & Related papers  (2022-09-14T11:37:48Z)
• Quantum isomorphism of graphs from association schemes [0.0]
  We show that any two Hadamard graphs on the same number of vertices are quantum isomorphic. This follows from a more general recipe for showing quantum isomorphism of graphs arising from certain association schemes.
  arXiv  Detail & Related papers  (2022-09-10T03:22:28Z)
• Geometry Contrastive Learning on Heterogeneous Graphs [50.58523799455101]
  This paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL) GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines.
  arXiv  Detail & Related papers  (2022-06-25T03:54:53Z)
• A Topological characterisation of Weisfeiler-Leman equivalence classes [0.0]
  Graph Neural Networks (GNNs) are learning models aimed at processing graphs and signals on graphs. In this article, we rely on the theory of covering spaces to fully characterize the classes of graphs that GNNs cannot distinguish. We show that the number of indistinguishable graphs in our dataset grows super-exponentially with the number of nodes.
  arXiv  Detail & Related papers  (2022-06-23T17:28:55Z)
• AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution [79.44066256794187]
  We show how to convert a non-graph dataset into a graph by introducing the generative graph model, which is used to build graph convolution networks (GCNs) A bipartite graph constructed by anchors is updated dynamically to exploit the high-level information behind data. We theoretically prove that the simple update will lead to degeneration and a specific strategy is accordingly designed.
  arXiv  Detail & Related papers  (2021-11-12T07:08:13Z)
• Hamiltonian systems, Toda lattices, Solitons, Lax Pairs on weighted Z-graded graphs [62.997667081978825]
  We identify conditions which allow one to lift one dimensional solutions to solutions on graphs. We show that even for a simple example of a topologically interesting graph the corresponding non-trivial Lax pairs and associated unitary transformations do not lift to a Lax pair on the Z-graded graph.
  arXiv  Detail & Related papers  (2020-08-11T17:58:13Z)
• Unsupervised Graph Embedding via Adaptive Graph Learning [85.28555417981063]
  Graph autoencoders (GAEs) are powerful tools in representation learning for graph embedding. In this paper, two novel unsupervised graph embedding methods, unsupervised graph embedding via adaptive graph learning (BAGE) and unsupervised graph embedding via variational adaptive graph learning (VBAGE) are proposed. Experimental studies on several datasets validate our design and demonstrate that our methods outperform baselines by a wide margin in node clustering, node classification, and graph visualization tasks.
  arXiv  Detail & Related papers  (2020-03-10T02:33:14Z)

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.