Estimating Subgraph Importance with Structural Prior Domain Knowledge

• URL: http://arxiv.org/abs/2605.12009v1
• Date: Tue, 12 May 2026 12:00:16 GMT
• Title: Estimating Subgraph Importance with Structural Prior Domain Knowledge
• Abstract summary: We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space.<n>Our method effectively leverages prior domain knowledge of graph substructures, while remaining independent of the specific form of the output layer or readout function used in the GNN architecture.<n> Experiments on real-world graph datasets demonstrate that our method consistently outperforms existing baselines in subgraph importance estimation.
• Score: 9.121437356699355
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space. Our method effectively leverages prior domain knowledge of graph substructures, while remaining independent of the specific form of the output layer or readout function used in the GNN architecture, and it does not require access to ground-truth target labels. Experiments on real-world graph datasets demonstrate that our method consistently outperforms existing baselines in subgraph importance estimation. Furthermore, we extend our method to identify important nodes within the graph.

Related papers

• Topology-Aware Active Learning on Graphs [3.649864838876551]
  We propose a graph-topological approach to active learning that targets the core challenge of exploration versus exploitation under scarce label budgets.<n>To guide exploration, we introduce a coreset construction based on Balanced Forman Curvature (BFC), which selects representative initial labels.<n>We also use BFC to dynamically trigger the shift from exploration to exploitation within active learning routines, replacing hand-tuned algorithms.
  arXiv  Detail & Related papers  (2025-10-29T18:49:24Z)
• Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints [7.605749412696919]
  Graph Neural Networks (GNNs) excel in handling graph-structured data but often underperform in link prediction tasks.<n>We present a novel method to enhance the expressivity of GNNs by embedding induced subgraphs into the graph Laplacian matrix's eigenbasis.<n>We demonstrate the ability to distinguish graphs that are indistinguishable by 2-WL, while maintaining efficient time complexity.
  arXiv  Detail & Related papers  (2024-08-22T12:22:00Z)
• Improving the interpretability of GNN predictions through conformal-based graph sparsification [9.550589670316523]
  Graph Neural Networks (GNNs) have achieved state-of-the-art performance in solving graph classification tasks. We propose a GNN emphtraining approach that finds the most predictive subgraph by removing edges and/or nodes. We rely on reinforcement learning to solve the resulting bi-level optimization with a reward function based on conformal predictions.
  arXiv  Detail & Related papers  (2024-04-18T17:34:47Z)
• Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding [51.75091298017941]
  This paper proposes a novel Deep Manifold (Variational) Graph Auto-Encoder (DMVGAE/DMGAE) for attributed graph data. The proposed method surpasses state-of-the-art baseline algorithms by a significant margin on different downstream tasks across popular datasets.
  arXiv  Detail & Related papers  (2024-01-12T17:57:07Z)
• Self-supervised Learning and Graph Classification under Heterophily [4.358149865548289]
  We propose a novel self-supervised strategy for Pre-training Graph neural networks (GNNs) based on the Metric (PGM) Our strategy achieves state-of-the-art performance for molecular property prediction and protein function prediction.
  arXiv  Detail & Related papers  (2023-06-14T12:32:38Z)
• Bures-Wasserstein Means of Graphs [60.42414991820453]
  We propose a novel framework for defining a graph mean via embeddings in the space of smooth graph signal distributions. By finding a mean in this embedding space, we can recover a mean graph that preserves structural information. We establish the existence and uniqueness of the novel graph mean, and provide an iterative algorithm for computing it.
  arXiv  Detail & Related papers  (2023-05-31T11:04:53Z)
• EGRC-Net: Embedding-induced Graph Refinement Clustering Network [66.44293190793294]
  We propose a novel graph clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net) EGRC-Net effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance. Our proposed methods consistently outperform several state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-19T09:08:43Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• 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)
• Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks [14.924672048447338]
  Graph convolutional networks (GCNs) aim at extending deep learning to arbitrary irregular domains, such as graphs. We introduce a novel method that learns the topology of input graphs as a part of GCN design. Experiments conducted on the challenging task of skeleton-based hand-gesture recognition show the high effectiveness of the learned GCNs.
  arXiv  Detail & Related papers  (2021-04-09T09:06:53Z)
• Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
  We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
  arXiv  Detail & Related papers  (2020-10-19T21:51:47Z)

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.