Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning
Not on the map. Why?
Abstract (arXiv)
Dynamic graphs exhibit complex temporal dynamics due to the interplay between evolving node features and changing network structures. Recently, Graph Neural Controlled Differential Equations (Graph Neural CDEs) successfully adapted Neural CDEs from paths on Euclidean domains to paths on graph domains. Building on this foundation, we introduce Permutation Equivariant Neural Graph CDEs, which project Graph Neural CDEs onto permutation equivariant function spaces. This significantly reduces the model's parameter count without compromising representational power, resulting in more efficient training and improved generalisation. We empirically demonstrate the advantages of our approach through experiments on simulated dynamical systems and real-world tasks, showing improved performance in both interpolation and extrapolation scenarios.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 41 of its 67 references that are in the map. First posted on arXiv 25 Jun 2025.
Builds on
41 of 67 references.
References · 41
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
- 2019Graph Neural Networks for Social Recommendationcited by 714
- 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
- 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
- 2020Inductive Representation Learning on Temporal Graphscited by 462
- 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
29 more
- 2018Invariant and Equivariant Graph Networkscited by 346
- 2022On Neural Differential Equationscited by 268
- 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
- 2021GRAND: Graph Neural Diffusioncited by 258
- 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 193
- 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 157
- 2019Graph Neural Ordinary Differential Equationscited by 154
- 2021Equinox: neural networks in JAX via callable PyTrees and filtered transformationscited by 148
- 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 143
- 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 138
- 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
- 2021PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Modelscited by 118
- 2021PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equationscited by 106
- 2024Theoretical Foundations of Deep Selective State-Space Modelscited by 74
- 2021TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learningcited by 68
- 2022Understanding convolution on graphs via energiescited by 59
- 2022GREAD: Graph Neural Reaction-Diffusion Networkscited by 54
- 2020word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Datacited by 38
- 2024TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphscited by 36
- 2024Log Neural Controlled Differential Equations: The Lie Brackets Make a Differencecited by 35
- 2023Feature Transportation Improves Graph Neural Networkscited by 15
- 2018Representation Learning over Dynamic Graphscited by 14
- 2022Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecastingcited by 14
- 2023Graph Neural Rough Differential Equations for Traffic Forecastingcited by 14
- 2024On The Temporal Domain of Differential Equation Inspired Graph Neural Networkscited by 9
- 2023Learning Dynamic Graph Embeddings with Neural Controlled Differential Equationscited by 7
- 2024Graph Neural Reaction Diffusion Modelscited by 6
- 2024Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identificationcited by 6
- 2024Graph Fourier Neural ODEs: Modeling Spatial-temporal Multi-scales in Molecular Dynamicscited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.