Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
HERE Technologies(HERE科技公司);Indian Institute of Technology Hyderabad(印度理工学院海得拉巴分校);RWTH Aachen(亚琛工业大学);Cerence Gmbh(Cerence有限公司);The University of Tokyo(东京大学)
We present the Evolving Graph Fourier Transform (EFT), the first invertible spectral transform that captures evolving representations on temporal graphs. We motivate our work by the inadequacy of existing methods for capturing the evolving graph spectra, which are also computationally expensive due to the temporal aspect along with the graph vertex domain. We view the problem as an optimization over the Laplacian of the continuous time dynamic graph. Additionally, we propose pseudo-spectrum relaxations that decompose the transformation process, making it highly computationally efficient. The EFT method adeptly captures the evolving graph's structural and positional properties, making it effective for downstream tasks on evolving graphs. Hence, as a reference implementation, we develop a simple neural model induced with EFT for capturing evolving graph spectra. We empirically validate our theoretical findings on a number of large-scale and standard temporal graph benchmarks and demonstrate that our model achieves state-of-the-art performance.
Clustering Time-Evolving Networks Using the Spatio-Temporal Graph Laplacian
Maxwell Institute for Mathematical Sciences(麦克斯韦数学研究所);University of Edinburgh(爱丁堡大学);Heriot–Watt University(赫瑞瓦特大学);Zuse Institute Berlin(柏林祖斯研究所);School of Mathematical & Computer Sciences(数学与计算机科学学院)
StFT: Spatio-temporal Fourier Transformer for Long-term Dynamics Prediction
School of Computing University of Utah(计算学院犹他大学);AMCR Division Lawrence Berkeley National Laboratory(伯克利国家实验室AMCR部门);Applied Mathematics and Computational Research Division Lawrence Berkeley National Laboratory(伯克利国家实验室应用数学与计算研究部门)
Diagnostic Spatio-temporal Transformer with Faithful Encoding
Ikerlan Technology Research Centre(伊克兰技术研究中心);Basque Research and Technology Alliance (BRTA)(巴斯克研究与技术联盟(BRTA));Mondragon University(蒙德拉贡大学);IBM Research(IBM研究院)
Evolutionary Echo State Network: evolving reservoirs in the Fourier space
Faculty of Electrical Engineering and Computer Science(电气工程与计算机科学学院);VŠB-Technical University of Ostrava(俄斯特拉发技术大学);INRIA Rennes – Bretagne Atlantique(法国国家信息与自动化研究所雷恩-布列塔尼大西洋中心)
DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting
Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai(能源化学过程智能制造关键实验室,教育部,东华大学,上海);Faculty of Informatics, Università della Svizzera italiana(瑞士意大利大学信息学院);Department of Electronics, Information and Bioengineering, Politecnico di Milano(米兰理工学院电子、信息与生物工程系)
Institute of Information Science, Beijing Jiaotong University(信息科学学院,北京交通大学);Visual Intelligence + X International Joint Laboratory of the Ministry of Education(教育部视觉智能+X国际联合实验室);Medical Big Data Research Center, Chinese PLA General Hospital Beijing, China(中国人民解放军总医院医学大数据研究中心)
DeStripe: A Self2Self Spatio-Spectral Graph Neural Network with Unfolded Hessian for Stripe Artifact Removal in Light-sheet Microscopy
Technical University of Munich(慕尼黑工业大学);Georg-August-University Goettingen(哥廷根大学);Johns Hopkins University(约翰斯·霍普金斯大学);Institute of AI for Health, Helmholtz Munich - German Research Center for Environmental Health(亥姆霍兹慕尼黑中心-德国环境健康研究中心健康人工智能研究所);Helmholtz AI, Helmholtz Munich - German Research Center for Environmental Health(亥姆霍兹慕尼黑中心-德国环境健康研究中心亥姆霍兹人工智能)
FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
Beijing Institute of Technology(北京理工大学);Tongji University(同济大学);University of Oxford(牛津大学);University of Macau(澳门大学);HeFei University of Technology(合肥工业大学);Macquarie University(麦考瑞大学)
A Multidimensional Graph Fourier Transformation Neural Network for Vehicle Trajectory Prediction
CARISSMA Institute of Automated Driving, Technische Hochschule Ingolstadt(英戈尔施塔特应用技术大学CARISSMA自动驾驶研究所);Technical University of Munich(慕尼黑工业大学);AUDI AG(奥迪股份公司)
Effects of boundary conditions in fully convolutional networks for learning spatio-temporal dynamics
University of Sherbrooke(舍布鲁克大学);ISAE-Supaero(法国高等航空航天学院);Université de Lyon(里昂大学);École Centrale de Lyon(里昂中央理工学院);INSA Lyon(里昂国立应用科学学院);Université Claude Bernard Lyon 1(里昂第一大学);CNRS(法国国家科学研究中心)
Evolving Space-Time Neural Architectures for Videos
Google Brain(谷歌大脑)
我们提出了一种新的方法来寻找视频CNN架构,捕捉丰富的时空信息的视频。以前的工作,利用3D卷积,通过手动设计视频CNN架构,获得了有希望的结果。在这里,我们开发了一种新的进化搜索算法,自动探索模型与不同类型和组合的层,共同学习视频表示的空间和时间方面之间的相互作用。我们证明了该算法的通用性,将其应用到两个元架构,获得新的架构优于手动设计的架构。此外,我们提出了一个新的组件,iTGM层,它更有效地利用其参数,允许学习的空间-时间的相互作用在更长的时间范围。iTGM层通常是进化算法的首选,并允许构建具有成本效益的网络。所提出的方法发现了以前未知的新的和不同的视频架构。更重要的是,它们比以前的模型更准确、更快,并且在我们测试的多个数据集上的表现优于最先进的结果,包括HMDB、Kinetics和Moments in Time。我们将开源代码和模型,以鼓励未来的模型开发。