AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Learning Dynamic Graph Embeddings With Neural Controlled Differential Equations

Tiexin Qin, Benjamin Walker, Terry Lyons, Hong Yan, Haoliang Li

TPAMI 2025 · Graph learning › Knowledge and temporal graphs · approach: Temporal graph neural architectures

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use natural cubic instead of rectilinear interpolation (ablation)GN-CDE · Heat Diffusion (Grid)MAE: 0.873 -> 0.369Improved
use natural cubic instead of linear interpolation (ablation)GN-CDE · Heat Diffusion (Grid)MAE: 0.453 -> 0.369Improved
use natural cubic instead of cubic Hermite interpolation (ablation)GN-CDE · Heat Diffusion (Random)MAE: 0.523 -> 0.521Improved
put the graph adjacency into the CDE vector field (GN-CDE) instead of plain Neural CDENeural CDE · Heat Diffusion (Community)MAE: 1.857 -> 0.457Improved
put the graph adjacency into the CDE vector field (GN-CDE) instead of plain Neural CDENeural CDE · Gene Regulation (Random)MAE: 6.107 -> 2.193Improved
replace STG-NCDE by GN-CDESTG-NCDE · Gene Regulation (Grid)MAE: 6.554 -> 1.388Improved
use continuous graph path control instead of Neural ODENeural ODE · Heat Diffusion (Random)MAE: 0.629 -> 0.521Improved
use GN-CDE instead of Neural CDE on real dataNeural CDE · tgbn-genreNDCG@10: 0.478 -> 0.529Improved
use GN-CDE instead of Neural ODE on real dataNeural ODE · tgbn-tradeNDCG@10: 0.725 -> 0.731No clear effect
use GN-CDE instead of task-tailored TGNv2TGNv2 · tgbn-tradeNDCG@10: 0.736 -> 0.731Hurt
use GN-CDE instead of DyGFormerDyGFormer · tgbn-genreNDCG@10: 0.365 -> 0.529Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy