Drop the mask! GAMM-A Taxonomy for Graph Attributes Missing Mechanisms

• URL: http://arxiv.org/abs/2602.08407v1
• Date: Mon, 09 Feb 2026 09:12:01 GMT
• Title: Drop the mask! GAMM-A Taxonomy for Graph Attributes Missing Mechanisms
• Authors: Richard Serrano, Baptiste Jeudy, Charlotte Laclau, Christine Largeron,
• Abstract summary: GAMM (Graph Attributes Missing Mechanisms) is a framework that links missingness probability to both node attributes and the underlying graph structure.<n>We empirically demonstrate that state-of-the-art imputation methods, while effective on traditional masks, significantly struggle when confronted with more realistic graph-aware missingness scenarios.
• Score: 2.1806414691083904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Exploring missing data in attributed graphs introduces unique challenges beyond those found in tabular datasets. In this work, we extend the taxonomy for missing data mechanisms to attributed graphs by proposing GAMM (Graph Attributes Missing Mechanisms), a framework that systematically links missingness probability to both node attributes and the underlying graph structure. Our taxonomy enriches the conventional definitions of masking mechanisms by introducing graph-specific dependencies. We empirically demonstrate that state-of-the-art imputation methods, while effective on traditional masks, significantly struggle when confronted with these more realistic graph-aware missingness scenarios.

Related papers

• Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification [81.06278257153835]
  We propose a graph rewiring method that balances structural bottleneck reduction and graph property preservation.<n>Our method generates graphs with enhanced connectivity while maintaining sparsity and largely preserving the original graph spectrum.
  arXiv  Detail & Related papers  (2025-06-19T08:01:00Z)
• 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 Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models [8.098074314691125]
  We show that graph attention mechanisms can enhance classification performance when structure noise exceeds feature noise.<n>We propose a novel multi-layer Graph Attention Network (GAT) architecture that significantly outperforms single-layer GATs in achieving emphperfect node classification.
  arXiv  Detail & Related papers  (2024-12-20T02:22:38Z)
• Hi-GMAE: Hierarchical Graph Masked Autoencoders [90.30572554544385]
  Hierarchical Graph Masked AutoEncoders (Hi-GMAE) Hi-GMAE is a novel multi-scale GMAE framework designed to handle the hierarchical structures within graphs. Our experiments on 15 graph datasets consistently demonstrate that Hi-GMAE outperforms 17 state-of-the-art self-supervised competitors.
  arXiv  Detail & Related papers  (2024-05-17T09:08:37Z)
• Graph Neural Networks with a Distribution of Parametrized Graphs [27.40566674759208]
  We introduce latent variables to parameterize and generate multiple graphs. We obtain the maximum likelihood estimate of the network parameters in an Expectation-Maximization framework.
  arXiv  Detail & Related papers  (2023-10-25T06:38:24Z)
• Multi-Layer Attention-Based Explainability via Transformers for Tabular Data [11.866061471514582]
  We propose a graph-oriented attention-based explainability method for tabular data. We take into account the attention matrices of all heads and layers as a whole. To assess the quality of multi-layer attention-based explanations, we compare them with popular attention-, gradient-, and perturbation-based explanability methods.
  arXiv  Detail & Related papers  (2023-02-28T03:28:18Z)
• GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
  We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
  arXiv  Detail & Related papers  (2022-12-01T11:49:07Z)
• Graph Pooling with Maximum-Weight $k$-Independent Sets [12.251091325930837]
  We introduce a graph coarsening mechanism based on the graph-theoretic concept of maximum-weight $k$-independent sets. We prove theoretical guarantees for distortion bounds on path lengths, as well as the ability to preserve key topological properties in the coarsened graphs.
  arXiv  Detail & Related papers  (2022-08-06T14:12:47Z)
• GraphMI: Extracting Private Graph Data from Graph Neural Networks [59.05178231559796]
  We present textbfGraph textbfModel textbfInversion attack (GraphMI), which aims to extract private graph data of the training graph by inverting GNN. Specifically, we propose a projected gradient module to tackle the discreteness of graph edges while preserving the sparsity and smoothness of graph features. We design a graph auto-encoder module to efficiently exploit graph topology, node attributes, and target model parameters for edge inference.
  arXiv  Detail & Related papers  (2021-06-05T07:07:52Z)
• 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)
• Homology-Preserving Multi-Scale Graph Skeletonization Using Mapper on Graphs [5.86893539706548]
  We propose to apply the mapper construction -- a popular tool in topological data analysis -- to graph visualization. We develop a variation of the mapper construction targeting weighted, undirected graphs, called mog, which generates homology-preserving skeletons of graphs. We provide a software tool that enables interactive explorations of such skeletons and demonstrate the effectiveness of our method for synthetic and real-world data.
  arXiv  Detail & Related papers  (2018-04-03T19:18:36Z)

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.