Efficient Higher-order Subgraph Attribution via Message Passing

• URL: http://arxiv.org/abs/2605.22385v1
• Date: Thu, 21 May 2026 12:16:19 GMT
• Title: Efficient Higher-order Subgraph Attribution via Message Passing
• Abstract summary: Higher-order interpretation schemes, such as GNN-LRP, emerged as powerful tools for unraveling how different features interact.<n>We propose novel algorithms that enable to attribute subgraphs with GNN-LRP in linear-time.
• Score: 23.932427893302826
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explaining graph neural networks (GNNs) has become more and more important recently. Higher-order interpretation schemes, such as GNN-LRP (layer-wise relevance propagation for GNN), emerged as powerful tools for unraveling how different features interact thereby contributing to explaining GNNs. GNN-LRP gives a relevance attribution of walks between nodes at each layer, and the subgraph attribution is expressed as a sum over exponentially many such walks. In this work, we demonstrate that such exponential complexity can be avoided. In particular, we propose novel algorithms that enable to attribute subgraphs with GNN-LRP in linear-time (w.r.t. the network depth). Our algorithms are derived via message passing techniques that make use of the distributive property, thereby directly computing quantities for higher-order explanations. We further adapt our efficient algorithms to compute a generalization of subgraph attributions that also takes into account the neighboring graph features. Experimental results show the significant acceleration of the proposed algorithms and demonstrate the high usefulness and scalability of our novel generalized subgraph attribution method.

Related papers

• Relevant Walk Search for Explaining Graph Neural Networks [23.612178520096162]
  Graph Networks (GNNs) have become important machine learning tools for machine learning analysis.<n> Layer-wise relevance propagation for GNNs (GNN-LRP) evaluates the relevance of emphwalks to reveal important information flows in the network.<n>We propose em-time algorithms for finding top-time$K$ relevant walks, which drastically reduces the applicability of GNN-LRP to large-scale problems.
  arXiv  Detail & Related papers  (2026-05-22T14:21:37Z)
• Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations [0.0]
  We formulate an XAI-based model improvement approach for Graph Neural Networks (GNNs) for node classification, called Explanation Enhanced Graph Learning (EEGL) The goal is to improve predictive performance of GNN using explanations. EEGL is an iterative self-improving algorithm, which starts with a learned "vanilla" GNN, and repeatedly uses frequent subgraph mining to find relevant patterns in explanation subgraphs.
  arXiv  Detail & Related papers  (2024-03-12T17:41:27Z)
• MAG-GNN: Reinforcement Learning Boosted Graph Neural Network [68.60884768323739]
  A particular line of work proposed subgraph GNNs that use subgraph information to improve GNNs' expressivity and achieved great success. Such effectivity sacrifices the efficiency of GNNs by enumerating all possible subgraphs. We propose Magnetic Graph Neural Network (MAG-GNN), a reinforcement learning (RL) boosted GNN, to solve the problem.
  arXiv  Detail & Related papers  (2023-10-29T20:32:21Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module [65.81781176362848]
  Graph Neural Networks (GNNs) can learn from graph-structured data through neighborhood information aggregation. As the number of layers increases, node representations become indistinguishable, which is known as over-smoothing. We propose a textbfPosterior-Sampling-based, Node-distinguish Residual module (PSNR).
  arXiv  Detail & Related papers  (2023-05-09T12:03:42Z)
• Relation Embedding based Graph Neural Networks for Handling Heterogeneous Graph [58.99478502486377]
  We propose a simple yet efficient framework to make the homogeneous GNNs have adequate ability to handle heterogeneous graphs. Specifically, we propose Relation Embedding based Graph Neural Networks (RE-GNNs), which employ only one parameter per relation to embed the importance of edge type relations and self-loop connections.
  arXiv  Detail & Related papers  (2022-09-23T05:24:18Z)
• Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis [124.97061497512804]
  We show that standard Graph Neural Networks (GNNs) produce more discriminative representations than the Weisfeiler-Lehman (WL) algorithm. We also show that simple convolutional architectures with white inputs, produce equivariant features that count the closed paths in the graph.
  arXiv  Detail & Related papers  (2022-05-19T18:40:25Z)
• Two-level Graph Neural Network [15.014364222532347]
  We propose a novel GNN framework, referred to as the Two-level GNN (TL-GNN) This merges subgraph-level information with node-level information. Experiments show that TL-GNN outperforms existing GNNs and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-01-03T02:15:20Z)
• Learning Graph Neural Networks with Approximate Gradient Descent [24.49427608361397]
  Two types of graph neural networks (GNNs) are investigated, depending on whether labels are attached to nodes or graphs. A comprehensive framework for designing and analyzing convergence of GNN training algorithms is developed. The proposed algorithm guarantees a linear convergence rate to the underlying true parameters of GNNs.
  arXiv  Detail & Related papers  (2020-12-07T02:54:48Z)
• Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results [58.277290855841976]
  We study tradeoffs of computational cost and expressive power of Graph Neural Networks (GNNs) We show that a new model can count subgraphs of size $k$, and thereby overcomes a known limitation of low-order GNNs. In several cases, the proposed algorithm can greatly reduce computational complexity compared to the existing higher-order $k$-GNNs.
  arXiv  Detail & Related papers  (2020-12-06T03:42:54Z)
• Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification [70.50751397870972]
  FastGAT is a method to make attention based GNNs lightweight by using spectral sparsification to generate an optimal pruning of the input graph. We experimentally evaluate FastGAT on several large real world graph datasets for node classification tasks.
  arXiv  Detail & Related papers  (2020-06-15T22:07:54Z)
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks [3.1510406584101776]
  Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. In this paper, we show that GNNs can in fact be naturally explained using higher-order expansions. We extract practically relevant insights on sentiment analysis of text data, structure-property relationships in quantum chemistry, and image classification.
  arXiv  Detail & Related papers  (2020-06-05T17:59:14Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

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.