FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks
Yale University（耶鲁大学）；Brown University（布朗大学）；New York University（纽约大学）；MIT（麻省理工学院）；ETH Zurich（苏黎世联邦理工学院）；Idaho State University（爱达荷州立大学）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）；Baylor College of Medicine（贝勒医学院）；EPFL（洛桑联邦理工学院）；University of Southern California（南加州大学）
Syed Asad Rizvi, Nazreen Pallikkavaliyaveetil, David Zhang, Zhuoyang Lyu, Nhi Nguyen, Haoran Lyu, Benjamin Christensen, Josue Ortega Caro, Antonio H. O. Fonseca… 展开作者
Syed Asad Rizvi, Nazreen Pallikkavaliyaveetil, David Zhang, Zhuoyang Lyu, Nhi Nguyen, Haoran Lyu, Benjamin Christensen, Josue Ortega Caro, Antonio H. O. Fonseca, Emanuele Zappala, Maryam Bagherian, Christopher Averill, Chadi G. Abdallah, Amin Karbasi, Rex Ying, Maria Brbic, Rahul Madhav Dhodapkar, David van Dijk
Foundation models have achieved remarkable success across many domains, relying on pretraining over vast amounts of data. Graph-structured data often lacks the same scale as unstructured data, making the development of graph foundation models challenging. In this work, we propose Foundation-Informed Message Passing (FIMP), a Graph Neural Network (GNN) message-passing framework that leverages pretrained non-textual foundation models in graph-based tasks. We show that the self-attention layers of foundation models can effectively be repurposed on graphs to perform cross-node attention-based message-passing. Our model is evaluated on a real-world image network dataset and two biological applications (single-cell RNA sequencing data and fMRI brain activity recordings) in both finetuned and zero-shot settings. FIMP outperforms strong baselines, demonstrating that it can effectively leverage state-of-the-art foundation models in graph tasks.
HypNO: A Graph-Based Neural Operator with Physics-Informed Message Passing for Hyperbolic Conservation Laws
Laboratory of Computer Science (LIX), École Polytechnique（计算机科学实验室（LIX），巴黎综合理工学院）；Department of Electrical Engineering and Computer Sciences, University of California, Berkeley（电气工程与计算机科学系，加利福尼亚大学伯克利分校）
Symmetry-Informed Graph Neural Networks for Carbon Dioxide Isotherm and Adsorption Prediction in Aluminum-Substituted Zeolites
Eindhoven University of Technology（埃因霍温理工大学）；Eindhoven Artificial Intelligence Systems Institute（埃因霍温人工智能系统研究所）；Data and AI, Department of Mathematics and Computer Science, Eindhoven University of Technology（埃因霍温理工大学数学与计算机科学系数据与人工智能部）；Materials Simulation and Modelling（材料模拟与建模中心）
Physics-Informed Graph Neural Networks to Reconstruct Local Fields Considering Finite Strain Hyperelasticity
Univ. Bordeaux, CNRS, Bordeaux INP, I2M, UMR 5295（波尔多大学、国家科学研究中心、波尔多INP、I2M、UMR 5295）；Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800（波尔多大学、国家科学研究中心、波尔多INP、LaBRI、UMR 5800）；Arts et Metiers Institute of Technology, CNRS, Bordeaux INP, I2M, UMR 5295（艺术与技术学院技术学院、国家科学研究中心、波尔多INP、I2M、UMR 5295）
DUALFloodGNN: Physics-informed Graph Neural Network for Operational Flood Modeling
Department of Computer Science, School of Computing, National University of Singapore（新加坡国立大学计算机科学系）；School of Civil Engineering, Faculty of Engineering, The University of Sydney（悉尼大学土木工程学院）；Delft Institute of Applied Mathematics, Delft University of Technology（代尔夫特理工大学应用数学研究所）
Inference of Sequential Patterns for Neural Message Passing in Temporal Graphs
University of Zurich（苏黎世大学）；Julius-Maximilians-Universität Würzburg（维尔茨堡大学）；Center for Artificial Intelligence and Data Science (CAIDAS)（人工智能与数据科学中心）；Chair of Machine Learning for Complex Networks（复杂网络机器学习主席席位）
Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks
Univ. Bordeaux, CNRS, Bordeaux INP, I2M, UMR 5295（波尔多大学、国家科学研究中心、波尔多工业学院、I2M、UMR 5295）；Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800（波尔多大学、国家科学研究中心、波尔多工业学院、LaBRI、UMR 5800）；Institute of Mechanics and Fluid Dynamics, TU Bergakademie Freiberg（力学与流体动力学研究所、弗赖堡技术大学）；Univ. Grenoble Alpes, CNRS, UMR 5525（格勒诺布尔阿尔卑斯大学、国家科学研究中心、UMR 5525）；Arts et Metiers Institute of Technology, CNRS, Bordeaux INP, I2M, UMR 5295（艺术与工艺技术学院、国家科学研究中心、波尔多工业学院、I2M、UMR 5295）
Graph Neural ODE Digital Twins for Control-Oriented Reactor Thermal-Hydraulic Forecasting Under Partial Observability
Department of Nuclear Engineering, Texas A&M University, College Station, TX 77843, USA（德克萨斯A&M大学核工程系，学院站，TX 77843，美国）；Argonne National Laboratory, Nuclear Science and Engineering Division, USA（阿贡国家实验室，核科学与工程部，美国）
Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
Operations Research, Université de Montréal（运营研究，蒙特利尔大学）；Mila – Quebec AI Institute（魁北克人工智能研究所）；Valence Labs（Valence实验室）；Dept. of Mathematics, Boise State University（数学系，博伊州立大学）
Symmetry-Reduced Physics-Informed Learning of Tensegrity Dynamics
Department of Mathematics, University of Kentucky（数学系，肯塔基大学）；Department of Mechanical and Aerospace Engineering, University of Houston（机械与航空航天工程系，休斯顿大学）
Wireless Power Control Based on Large Language Models
School of Information Science and Engineering, Southeast University（东南大学信息科学与工程学院）；Department of Electrical and Computer Engineering, University of California, Santa Cruz（加州大学圣克鲁兹分校电气与计算机工程系）
Learning, Solving and Optimizing PDEs with TensorGalerkin: an efficient high-performance Galerkin assembly algorithm
ETH Zurich, Switzerland（苏黎世联邦理工学院，瑞士）；Imperial College London, UK（伦敦帝国学院，英国）；Northeastern University, USA（东北大学，美国）；Renmin University of China, China（中国人民大学，中国）
