English
Related papers

Related papers: MEGAN: Multi-Explanation Graph Attention Network

200 papers

Graph Neural Networks (GNNs) achieve state-of-the-art performance in various graph-related tasks. However, the black-box nature often limits their interpretability and trustworthiness. Numerous explainability methods have been proposed to…

Machine Learning · Computer Science 2023-11-13 Jialin Chen , Kenza Amara , Junchi Yu , Rex Ying

Graph neural networks have demonstrated state-of-the-art performance on knowledge graph tasks such as link prediction. However, interpreting GNN predictions remains a challenging open problem. While many GNN explainability methods have been…

Machine Learning · Computer Science 2025-06-17 Ryoji Kubo , Djellel Difallah

The apparent ``black box'' nature of neural networks is a barrier to adoption in applications where explainability is essential. This paper presents TAME (Trainable Attention Mechanism for Explanations), a method for generating explanation…

Computer Vision and Pattern Recognition · Computer Science 2025-01-30 Mariano Ntrougkas , Nikolaos Gkalelis , Vasileios Mezaris

Interpretable graph neural networks (XGNNs ) are widely adopted in various scientific applications involving graph-structured data. Existing XGNNs predominantly adopt the attention-based mechanism to learn edge or node importance for…

Machine Learning · Computer Science 2024-06-13 Yongqiang Chen , Yatao Bian , Bo Han , James Cheng

Despite the Graph Neural Networks' (GNNs) proficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations disjointed from…

Machine Learning · Computer Science 2024-07-26 Zhenhua Huang , Kunhao Li , Shaojie Wang , Zhaohong Jia , Wentao Zhu , Sharad Mehrotra

Recently, significant attention has been given to the idea of viewing relational databases as heterogeneous graphs, enabling the application of graph neural network (GNN) technology for predictive tasks. However, existing GNN methods…

Machine Learning · Computer Science 2025-02-26 Francesco Ferrini , Antonio Longa , Andrea Passerini , Manfred Jaeger

This paper presents Gem, a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal…

Machine Learning · Computer Science 2021-06-08 Wanyu Lin , Hao Lan , Baochun Li

This paper presents a contextualized graph attention network that combines edge features and multiple sub-graphs for improving relation extraction. A novel method is proposed to use multiple sub-graphs to learn rich node representations in…

Computation and Language · Computer Science 2020-04-23 Angrosh Mandya , Danushka Bollegala , Frans Coenen

Detecting unusual patterns in graph data is a crucial task in data mining. However, existing methods face challenges in consistently achieving satisfactory performance and often lack interpretability, which hinders our understanding of…

Machine Learning · Computer Science 2024-06-28 Yifei Yang , Peng Wang , Xiaofan He , Dongmian Zou

Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous graph neural networks (GNN) require a large…

Machine Learning · Computer Science 2020-09-04 Yanqiao Zhu , Yichen Xu , Feng Yu , Shu Wu , Liang Wang

Graph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linkage patterns across graphs in various applications. As…

Machine Learning · Computer Science 2021-01-01 Donghan Yu , Ruohong Zhang , Zhengbao Jiang , Yuexin Wu , Yiming Yang

Graph Neural Networks (GNNs) have achieved remarkable performance in a wide range of graph-related learning tasks. However, explaining their predictions remains a challenging problem, especially due to the mismatch between the graphs used…

Machine Learning · Computer Science 2025-08-05 Zhuomin Chen , Jingchao Ni , Hojat Allah Salehi , Xu Zheng , Dongsheng Luo

We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction tasks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations for a…

Quantitative Methods · Quantitative Biology 2020-11-11 Danilo Numeroso , Davide Bacciu

Graph Neural Networks (GNNs) are a popular class of machine learning models. Inspired by the learning to explain (L2X) paradigm, we propose L2XGNN, a framework for explainable GNNs which provides faithful explanations by design. L2XGNN…

Machine Learning · Computer Science 2024-06-17 Giuseppe Serra , Mathias Niepert

We introduce Attention Graphs, a new tool for mechanistic interpretability of Graph Neural Networks (GNNs) and Graph Transformers based on the mathematical equivalence between message passing in GNNs and the self-attention mechanism in…

Machine Learning · Computer Science 2025-02-26 Batu El , Deepro Choudhury , Pietro Liò , Chaitanya K. Joshi

We propose a novel technique to enhance Knowledge Graph Reasoning by combining Graph Convolution Neural Network (GCN) with the Attention Mechanism. This approach utilizes the Attention Mechanism to examine the relationships between entities…

Information Retrieval · Computer Science 2025-03-24 Meera Gupta , Ravi Khanna , Divya Choudhary , Nandini Rao

Recently popularized graph neural networks achieve the state-of-the-art accuracy on a number of standard benchmark datasets for graph-based semi-supervised learning, improving significantly over existing approaches. These architectures…

Machine Learning · Statistics 2018-03-13 Kiran K. Thekumparampil , Chong Wang , Sewoong Oh , Li-Jia Li

Generating realistic graph-structured data is challenging due to discrete structures, variable sizes, and class-specific connectivity patterns that resist conventional generative modelling. While recent graph generation methods employ…

Machine Learning · Computer Science 2026-02-02 Seyedeh Ava Razi Razavi , James Sargant , Sheridan Houghten , Renata Dividino

Graph Neural Networks (GNNs) are effective for node classification in graph-structured data, but they lack explainability, especially at the global level. Current research mainly utilizes subgraphs of the input as local explanations or…

Artificial Intelligence · Computer Science 2024-05-22 Dominik Köhler , Stefan Heindorf

Meta-path-based heterogeneous graph neural networks aggregate over meta-path-induced views, and their semantic-level attention over meta-path channels is widely used as a narrative for ``which semantics matter.'' We study this assumption…

Machine Learning · Computer Science 2026-02-10 Maiqi Jiang , Noman Ali , Yiran Ding , Yanfu Zhang