Papers › Neural Dynamics on Complex Networks

Neural Dynamics on Complex Networks

18 Aug 2019arXiv:1908.06491archive 2025-07-28

Chengxi Zang, Fei Wang

Learning continuous-time dynamics on complex networks is crucial for understanding, predicting and controlling complex systems in science and engineering. However, this task is very challenging due to the combinatorial complexities in the structures of high dimensional systems, their elusive continuous-time nonlinear dynamics, and their structural-dynamic dependencies. To address these challenges, we propose to combine Ordinary Differential Equation Systems (ODEs) and Graph Neural Networks (GNNs) to learn continuous-time dynamics on complex networks in a data-driven manner. We model differential equation systems by GNNs. Instead of mapping through a discrete number of neural layers in the forward process, we integrate GNN layers over continuous time numerically, leading to capturing continuous-time dynamics on graphs. Our model can be interpreted as a Continuous-time GNN model or a Graph Neural ODEs model. Our model can be utilized for continuous-time network dynamics prediction, structured sequence prediction (a regularly-sampled case), and node semi-supervised classification tasks (a one-snapshot case) in a unified framework. We validate our model by extensive experiments in the above three scenarios. The promising experimental results demonstrate our model's capability of jointly capturing the structure and dynamics of complex systems in a unified framework.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

calvin-zcx/ndcn officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Weather Forecasting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weather Forecasting LA NDCN MSE (t+1) 0.5380 ± 0.0469 #4 of 4 Archive leaderboard report
Weather Forecasting LA NDCN MSE (t+6) 1.2588 ± 0.0654 #4 of 4 Archive leaderboard report
Weather Forecasting NOAA Atmospheric Temperature Dataset NDCN MAE (t+1) 0.3151 ± 0.0122 #4 of 5 Archive leaderboard report
Weather Forecasting NOAA Atmospheric Temperature Dataset NDCN MAE (t+10) 2.2967 ± 0.0415 #4 of 5 Archive leaderboard report
Weather Forecasting SD RNN-GNN MSE (t+1) 0.5291 ± 0.0578 #5 of 10 Archive leaderboard report
Weather Forecasting SD RNN-GNN MSE (t+6) 0.7862 ± 0.0475 #5 of 10 Archive leaderboard report
Weather Forecasting SD NDCN MSE (t+1) 0.5296 ± 0.0274 #6 of 10 Archive leaderboard report
Weather Forecasting SD NDCN MSE (t+6) 0.7542 ± 0.0730 #6 of 10 Archive leaderboard report
Weather Forecasting SD GRU-GNN MSE (t+1) 0.5705 ± 0.0057 #7 of 10 Archive leaderboard report
Weather Forecasting SD GRU-GNN MSE (t+6) 0.7414 ± 0.0294 #7 of 10 Archive leaderboard report
Weather Forecasting SD LSTM-GNN MSE (t+1) 0.5754 ± 0.0180 #8 of 10 Archive leaderboard report
Weather Forecasting SD LSTM-GNN MSE (t+6) 0.7954 ± 0.0110 #8 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections