paper-with-me

홈 › Papers

CoulGAT: An Experiment on Interpretability of Graph Attention Networks

2019-12-18 · Burc Gokden

We present an attention mechanism inspired from definition of screened Coulomb potential. This attention mechanism was used to interpret the Graph Attention (GAT) model layers and training dataset by using a flexible and scalable framework (CoulGAT) developed for this purpose. Using CoulGAT, a forest of plain and resnet models were trained and characterized using this attention mechanism against CHAMPS dataset. The learnable variables of the attention mechanism are used to extract node-node and node-feature interactions to define an empirical standard model for the graph structure and hidden layer. This representation of graph and hidden layers can be used as a tool to compare different models, optimize hidden layers and extract a compact definition of graph structure of the dataset.

📄 PDF Abstract BibTeX arXiv:1912.08409

Code (1)

burcgokden/CoulGAT-Graph-Attention-Interpretability 공식 구현

Tasks

Graph Attention

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs

2025-02-17 · Batu El, Deepro Choudhury, Pietro Liò, Chaitanya K. Joshi

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-attenti…

Node Classification

Graph Triple Attention Network: A Decoupled Perspective

2024-08-14 · Xiaotang Wang, Yun Zhu, Haizhou Shi, Yongchao Liu 외

Graph Transformers (GTs) have recently achieved significant success in the graph domain by effectively capturing both long-range dependencies and graph inductive biases. However, these methods face two primary challenges…

AttributeGraph ClassificationNode Classification

Optimization and Interpretability of Graph Attention Networks for Small Sparse Graph Structures in Automotive Applications

2023-05-25 · Marion Neumeier, Andreas Tollkühn, Sebastian Dorn, Michael Botsch 외

For automotive applications, the Graph Attention Network (GAT) is a prominently used architecture to include relational information of a traffic scenario during feature embedding. As shown in this work, however, one of t…

Graph Attention

Faithful Interpretation for Graph Neural Networks

2024-10-09 · Lijie Hu, Tianhao Huang, Lu Yu, WanYu Lin 외

Currently, attention mechanisms have garnered increasing attention in Graph Neural Networks (GNNs), such as Graph Attention Networks (GATs) and Graph Transformers (GTs). It is not only due to the commendable boost in per…

Graph Attention

DARTS-GT: Differentiable Architecture Search for Graph Transformers with Quantifiable Instance-Specific Interpretability Analysis

2025-10-16 · Shruti Sarika Chakraborty, Peter Minary arxiv

Graph Transformers (GTs) have emerged as powerful architectures for graph-structured data, yet remain constrained by rigid designs and lack quantifiable interpretability. Current state-of-the-art GTs commit to fixed GNN …