paper-with-me

홈 › Papers

Dirac--Bianconi Graph Neural Networks -- Enabling Non-Diffusive Long-Range Graph Predictions

2024-07-17 · Christian Nauck, Rohan Gorantla, Michael Lindner, Konstantin Schürholt, Antonia S. J. S. Mey, Frank Hellmann

The geometry of a graph is encoded in dynamical processes on the graph. Many graph neural network (GNN) architectures are inspired by such dynamical systems, typically based on the graph Laplacian. Here, we introduce Dirac--Bianconi GNNs (DBGNNs), which are based on the topological Dirac equation recently proposed by Bianconi. Based on the graph Laplacian, we demonstrate that DBGNNs explore the geometry of the graph in a fundamentally different way than conventional message passing neural networks (MPNNs). While regular MPNNs propagate features diffusively, analogous to the heat equation, DBGNNs allow for coherent long-range propagation. Experimental results showcase the superior performance of DBGNNs over existing conventional MPNNs for long-range predictions of power grid stability and peptide properties. This study highlights the effectiveness of DBGNNs in capturing intricate graph dynamics, providing notable advancements in GNN architectures.

📄 PDF Abstract BibTeX arXiv:2407.12419

Code (1)

PIK-ICoNe/DBGNN_paper-companion 공식 구현 pytorch

Tasks

Graph Neural Network

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Symmetry-Constrained Multi-Scale Physics-Informed Neural Networks for Graphene Electronic Band Structure Prediction

2025-08-14 · Wei Shan Lee, I Hang Kwok, Kam Ian Leong, Chi Kiu Althina Chau 외 arxiv

Accurate prediction of electronic band structures in two-dimensional materials remains a fundamental challenge, with existing methods struggling to balance computational efficiency and physical accuracy. We present the S…

Computational Efficiency

Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification

2020-01-22 · Jiawei Zhang

Existing graph neural networks may suffer from the "suspended animation problem" when the model architecture goes deep. Meanwhile, for some graph learning scenarios, e.g., nodes with text/image attributes or graphs with …

General ClassificationGraph LearningGraph Neural NetworkGraph Representation Learning+2

Beyond holography: the entropic quantum gravity foundations of image processing

2025-03-18 · Ginestra Bianconi

Recently, thanks to the development of artificial intelligence (AI) there is increasing scientific attention to establishing the connections between theoretical physics and AI. Traditionally, these connections have been …

Identification of diffusively coupled linear networks through structured polynomial models

2021-06-03 · E. M. M., Kivits, Paul M. J. Van den Hof

Physical dynamic networks most commonly consist of interconnections of physical components that can be described by diffusive couplings. These diffusive couplings imply that the cause-effect relationships in the intercon…

Dirac Processes and Default Risk

2015-04-17

We introduce Dirac processes, using Dirac delta functions, for short-rate-type pricing of financial derivatives. Dirac processes add spikes to the existing building blocks of diffusions and jumps. Dirac processes are Gen…