paper-with-me

Papers

Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability

2023-04-14 · Indro Spinelli, Michele Guerra, Filippo Maria Bianchi, Simone Scardapane

Subgraph-enhanced graph neural networks (SGNN) can increase the expressive power of the standard message-passing framework. This model family represents each graph as a collection of subgraphs, generally extracted by random sampling or with hand-crafted heuristics. Our key observation is that by selecting "meaningful" subgraphs, besides improving the expressivity of a GNN, it is also possible to obtain interpretable results. For this purpose, we introduce a novel framework that jointly predicts the class of the graph and a set of explanatory sparse subgraphs, which can be analyzed to understand the decision process of the classifier. We compare the performance of our framework against standard subgraph extraction policies, like random node/edge deletion strategies. The subgraphs produced by our framework allow to achieve comparable performance in terms of accuracy, with the additional benefit of providing explanations.

📄 PDF Abstract BibTeX arXiv:2304.07152

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Graph Neural Network Causal Explanation via Neural Causal Models

2024-07-12 · Arman Behnam, Binghui Wang

Graph neural network (GNN) explainers identify the important subgraph that ensures the prediction for a given graph. Until now, almost all GNN explainers are based on association, which is prone to spurious correlations.…

Causal InferenceGraph Neural Network

EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time

2024-05-02 · Shengyao Lu, Bang Liu, Keith G. Mills, Jiao He 외

Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining attention for their intuitive appeal. Howev…

Self-supervised Subgraph Neural Network With Deep Reinforcement Walk Exploration

2025-02-03 · Jianming Huang, Hiroyuki Kasai

Graph data, with its structurally variable nature, represents complex real-world phenomena like chemical compounds, protein structures, and social networks. Traditional Graph Neural Networks (GNNs) primarily utilize the …

Improving Expressivity of Graph Neural Networks using Localization

2023-05-31 · Anant Kumar, Shrutimoy Das, Shubhajit Roy, Binita Maity 외

In this paper, we propose localized versions of Weisfeiler-Leman (WL) algorithms in an effort to both increase the expressivity, as well as decrease the computational overhead. We focus on the specific problem of subgrap…

Subgraph CountingSubgraph Counting - 2 starSubgraph Counting - 3 StarSubgraph Counting - C4+3

Ordered Subgraph Aggregation Networks

2022-06-22 · Chendi Qian, Gaurav Rattan, Floris Geerts, Christopher Morris 외

Numerous subgraph-enhanced graph neural networks (GNNs) have emerged recently, provably boosting the expressive power of standard (message-passing) GNNs. However, there is a limited understanding of how these approaches …