B-cos GNNs: Faithful Explanations through Dynamic Linearity

• URL: http://arxiv.org/abs/2605.19778v2
• Date: Wed, 27 May 2026 07:50:54 GMT
• Title: B-cos GNNs: Faithful Explanations through Dynamic Linearity
• Abstract summary: B-cos GNNs are an inherently explainable class of graph neural networks.<n>They decompose predictions into per-node, per-feature contributions via a single input-dependent linear map.
• Score: 1.2234742322758418
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We introduce B-cos GNNs, an inherently explainable class of graph neural networks whose predictions decompose exactly into per-node, per-feature contributions via a single input-dependent linear map. B-cos GNNs use linear (sum-based) aggregation and replace non-linear message and update functions with B-cos transforms. This induces meaningful, task-specific weight-input alignment that is directly accessible through the model's dynamic linearity. Instance-level explanations follow from a single forward and backward pass, requiring no auxiliary explainer, modified learning objective, or perturbation procedure. Instantiated as a GIN, our approach trades small losses in predictive accuracy for state-of-the-art explainability across diverse synthetic and real-world benchmarks, producing explanations orders of magnitude faster than post-hoc baselines.

Related papers

• GNNAnatomy: Rethinking Model-Level Explanations for Graph Neural Networks [20.05098366613674]
  Graph Neural Networks (GNNs) achieve outstanding performance across graph-based tasks but remain difficult to interpret.<n>This paper introduces GNNAnatomy, a distillation-based method designed to generate explanations while avoiding pitfalls.<n>To account for structural diversity within a class, GNNAnatomy generates explanations at the required granularity through an interface that supports human-AI teaming.
  arXiv  Detail & Related papers  (2024-06-06T23:09:54Z)
• Neural Tangent Kernels Motivate Graph Neural Networks with Cross-Covariance Graphs [94.44374472696272]
  We investigate NTKs and alignment in the context of graph neural networks (GNNs) Our results establish the theoretical guarantees on the optimality of the alignment for a two-layer GNN. These guarantees are characterized by the graph shift operator being a function of the cross-covariance between the input and the output data.
  arXiv  Detail & Related papers  (2023-10-16T19:54:21Z)
• How Graph Neural Networks Learn: Lessons from Training Dynamics [80.41778059014393]
  We study the training dynamics in function space of graph neural networks (GNNs) We find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function. This finding offers new interpretable insights into when and why the learned GNN functions generalize.
  arXiv  Detail & Related papers  (2023-10-08T10:19:56Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• Discovering Invariant Rationales for Graph Neural Networks [104.61908788639052]
  Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features. We propose a new strategy of discovering invariant rationale (DIR) to construct intrinsically interpretable GNNs.
  arXiv  Detail & Related papers  (2022-01-30T16:43:40Z)
• A Meta-Learning Approach for Training Explainable Graph Neural Networks [10.11960004698409]
  We propose a meta-learning framework for improving the level of explainability of a GNN directly at training time. Our framework jointly trains a model to solve the original task, e.g., node classification, and to provide easily processable outputs for downstream algorithms. Our model-agnostic approach can improve the explanations produced for different GNN architectures and use any instance-based explainer to drive this process.
  arXiv  Detail & Related papers  (2021-09-20T11:09:10Z)
• Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks [6.004582130591279]
  We find that the previous explanation generation approaches that maximize the mutual information between the label distribution produced by the GNN model and the explanation to be restrictive. Specifically, existing approaches do not enforce explanations to be predictive, sparse, or robust to input perturbations. We propose a novel approach Zorro based on the principles from rate-distortion theory that uses a simple procedure to optimize for fidelity.
  arXiv  Detail & Related papers  (2021-05-18T15:53:09Z)
• Parameterized Explainer for Graph Neural Network [49.79917262156429]
  We propose PGExplainer, a parameterized explainer for Graph Neural Networks (GNNs) Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification.
  arXiv  Detail & Related papers  (2020-11-09T17:15:03Z)
• Data-Driven Learning of Geometric Scattering Networks [74.3283600072357]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2020-10-06T01:20:27Z)
• Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretability [28.90948136731314]
  We propose neural generators of sparse local linear models (NGSLLs) NGSLLs generate sparse linear weights for each sample using deep neural networks (DNNs) We demonstrate the effectiveness of the NGSLL quantitatively and qualitatively by evaluating prediction performance and visualizing generated weights on image and text classification tasks.
  arXiv  Detail & Related papers  (2020-03-13T18:49:36Z)

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.