Miles D. Cranmer, Rui Xu, Peter Battaglia, Shirley Ho
备注:
6 pages; references added + improvements to writing and clarity; accepted for an oral presentation at Machine Learning and the Physical Sciences Workshop @ NeurIPS 2019
We introduce an approach for imposing physically motivated inductive biases on graph networks to learn interpretable representations and improved zero-shot generalization. Our experiments show that our graph network models, which implement this inductive bias, can learn message representations equivalent to the true force vector when trained on n-body gravitational and spring-like simulations. We use symbolic regression to fit explicit algebraic equations to our trained model's message function and recover the symbolic form of Newton's law of gravitation without prior knowledge. We also show that our model generalizes better at inference time to systems with more bodies than had been experienced during training. Our approach is extensible, in principle, to any unknown interaction law learned by a graph network, and offers a valuable technique for interpreting and inferring explicit causal theories about the world from implicit knowledge captured by deep learning.
Multivariate de Bruijn Graphs: A Symbolic Graph Framework for Time Series Forecasting
Department of Computer Science, Indiana University Bloomington, IN, USA(印第安纳大学布卢明顿分校计算机科学系);College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar(哈马德·本·卡西姆大学科学与工程学院);Department of Computer Science, University of Illinois Springfield, IL, USA(伊利诺伊大学斯普林菲尔德分校计算机科学系)
A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs
University of Antwerp(安特卫普大学);Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);Elsevier(爱思唯尔);Universidad Católica de Chile(智利天主教大学);CENIA Chile(智利CENIA机构);Inst. for Math. and Comp. Eng.(数学与计算工程研究所);IMFD Chile(智利IMFD机构)
Neural-Symbolic Models for Logical Queries on Knowledge Graphs
Mila - Québec AI Institute(米拉-魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);McGill University(麦吉尔大学);HEC Montréal(蒙特利尔高等商学院);CIFAR AI Chair(加拿大高等研究院人工智能讲席)
Neuro-symbolic representation learning on biological knowledge graphs
King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);Hamad Bin Khalifa University(哈马德·本·哈利法大学);Osaka University(大阪大学);The Scripps Research Institute(斯克里普斯研究所)
Symbolic Graph Networks for Robust PDE Discovery from Noisy Sparse Data
School of Software Engineering, Chengdu University of Information Technology(成都信息科技学院软件工程学院);School of Statistics, Chengdu University of Information Technology(成都信息科技学院统计学院);College of Applied Mathematics, Chengdu University of Information Technology(成都信息科技学院应用数学学院);Key Laboratory of Mathematical Meteorology, Chengdu University of Information Technology(成都信息科技学院数学气象重点实验室)
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
ENSTA, Institut Polytechnique Paris(巴黎综合理工学院ENSTA);Inria(法国国家信息与自动化研究所);DaSCI Andalusian Institute in Data Science and Computational Intelligence, University of Granada(格拉纳达大学DaSCI安达卢西亚数据科学与计算智能研究所);University of Granada(格拉纳达大学);Free University of Bozen-Bolzano(波尔扎诺自由大学)
MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs
ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University, Linz, Austria(林茨ELLIS单元和LIT人工智能实验室,机器学习研究所,约翰·凯撒大学,林茨,奥地利);Clinical Research Institute Medical Artificial Intelligence, Johannes Kepler University, Linz, Austria(医学人工智能临床研究研究所,约翰·凯撒大学,林茨,奥地利)
Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition
Czech Technical University in Prague(布拉格捷克技术大学);Artificial Intelligence Center, Department of Computer Science, Faculty of Electrical Engineering(电气工程学院计算机科学系人工智能中心)
Enhancing Symbolic Regression and Universal Physics-Informed Neural Networks with Dimensional Analysis
Cheriton School of Computer Science(切尔顿计算机科学学院);Department of Electrical and Computer Engineering(电气与计算机工程系);University of Waterloo(滑铁卢大学);Electrical Engineering and Computer Science Department(电气工程与计算机科学系);Department of Applied Mathematics(应用数学系);University of Michigan(密歇根大学)
Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability
Laboratory of Applied Materials and Interfaces, Federal University of Rio Grande do Sul(南里奥格兰德联邦大学应用材料与界面实验室);Institute of Condensed Matter and Nanosciences, Université Catholique de Louvain(鲁汶天主教大学凝聚态与纳米科学研究所);Ruhr-Universität Bochum(波鸿鲁尔大学)
An energy-based model for neuro-symbolic reasoning on knowledge graphs
Siemens AG(西门子股份公司);European Space Agency(欧洲空间局);European Commission, Joint Research Centre (JRC)(欧盟委员会联合研究中心);Siemens AI Lab, Siemens AG Technology(西门子股份公司技术部人工智能实验室)
The Road to Learning Explainable Inverse Kinematic Models: Graph Neural Networks as Inductive Bias for Symbolic Regression
Faculty of Computer Science, Otto-von-Guericke-University Magdeburg(马格德堡奥托·冯·格里克大学计算机科学学院);Fraunhofer Institute for Transportation and Infrastructure Systems IVI(弗劳恩霍夫运输与基础设施系统研究所IVI)