← Research overview

DGDNN: Decoupled Graph Diffusion Neural Network for Stock Movement Prediction

Zinuo You, Zijian Shi, Hongbo Bo, John Cartlidge, Li Zhang, Yan Ge
ICAART 2024

Keep feature transformation separate from relational mixing over a dynamic stock graph.

First author and implementation author · 2023–2025

Relational and individual structure

Stocks carry individual temporal features as well as changing relationships to other stocks. Repeatedly interleaving transformations with graph propagation can make those roles hard to separate.

Decoupled representation learning

DGDNN builds dynamic graphs using entropy-driven edge generation, learns dependencies through graph diffusion, and separates the representation-learning stage from relational propagation. The extended publication develops the same research direction.

Reading the demonstration

Start with six signed features, apply a fixed nonlinear encoder once, then diffuse its output over a ring. Controls vary the encoder gain and the number of diffusion steps. This is an operational illustration of decoupling, not the trained encoder, learned graph, or full DGDNN architecture.

Interactive toy experiment

Encode once. Then diffuse.

Set the encoder gain and step through graph propagation. The encoded features stay fixed while their mixture changes.

Encode once. Then diffuse.A-0.90B0.80C0.10D-0.30E0.65F-0.55A-0.87B0.83C0.15D-0.42E0.75F-0.68A-0.23B0.06C0.15D0.08E-0.04F-0.26Raw inputEncode onceDiffuse × 2→→ABCDEFSigned node featuresNode

Gray: raw input · Light blue: encoded once · Dark blue: diffused representation

Encoder gain 1.5 · 2 diffusion steps · Node A: -0.90 → -0.874 → -0.233. Zero steps preserves the encoded features.

How this toy works

Encode hᵢ = tanh(gxᵢ) once. Each step uses hᵢ ← 0.5hᵢ + 0.25hᵢ₋₁ + 0.25hᵢ₊₁ on a six-node ring.

This fixed encoder and graph isolate decoupling. They do not reproduce entropy-driven graph construction, learned features, or the full DGDNN operator.

Synthetic illustration · Not a trained-model output or a published benchmark.

Extended publication

Multi-Stock Movements Classification: A Decoupled Graph Diffusion Neural Network Approach
LNCS 2025 · ICAART 2024 revised selected papers