Flow-Attentional Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks (GNNs) have become essential for learning from graph-structured data. However, existing GNNs do not consider the conservation law inherent in graphs associated with a flow of physical resources, such as electrical current in power grids or traffic in transportation networks, which can lead to reduced model performance. To address this, we propose flow attention, which adapts existing graph attention mechanisms to satisfy Kirchhoff's first law. Furthermore, we discuss how this modification influences the expressivity and identify sets of non-isomorphic graphs that can be discriminated by flow attention but not by standard attention. Through extensive experiments on two flow graph datasets (electronic circuits and power grids) we demonstrate that flow attention enhances the performance of attention-based GNNs on both graph-level classification and regression tasks.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 6 Jun 2025.
Builds on
35 of 53 references.
References · 35
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
- 2021How Attentive are Graph Attention Networks?cited by 835
23 more
- 2018Link Prediction Based on Graph Neural Networkscited by 832
- 2019Graph Neural Networks for Social Recommendationcited by 714
- 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
- 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
- 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
- 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
- 2019What graph neural networks cannot learn: depth vs widthcited by 201
- 2022Structure-Aware Transformer for Graph Representation Learningcited by 194
- 2020Random Features Strengthen Graph Neural Networkscited by 186
- 2022Graph neural networks for materials science and chemistrycited by 182
- 2023Exphormer: Sparse Transformers for Graphscited by 170
- 2019D-VAE: A Variational Autoencoder for Directed Acyclic Graphscited by 98
- 2024Graph Mamba: Towards Learning on Graphs with State Space Modelscited by 86
- 2021Directed Acyclic Graph Neural Networkscited by 70
- 2021A Review of Graph Neural Networks and Their Applications in Power Systemscited by 63
- 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 58
- 2024Graph Transformers: A Surveycited by 32
- 2024A Review of Graph Neural Networks in Epidemic Modelingcited by 31
- 2022Transformers over Directed Acyclic Graphscited by 23
- 2022Graph Neural Networks Designed for Different Graph Types: A Surveycited by 21
- 2022PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphscited by 20
- 2021Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Gridscited by 18
- 2022Minimal Width for Universal Property of Deep RNNcited by 12
Built on by
Citing papers per year: 2026: 1.
1 paper.