---
title: A hybrid graph neural network for realized volatility forecasting: Multi-relation attention and dual-path fusion
url: https://www.ml-quant.com/papers/ssrn/7576359/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-09
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 7576359
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7576359
featured: 2026-10-09
citations: unknown
topic: ML & AI Methods
---


# A hybrid graph neural network for realized volatility forecasting: Multi-relation attention and dual-path fusion

A graph neural network combining temporal and cross-asset volatility patterns reduces mean squared error and quasi-likelihood loss by approximately 9.9% and 3.4% on Dow stocks.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7576359
- Identifier: SSRN 7576359
- Released: 2026-10-07
- First featured: Quant Letter No. 134 (2026-10-09): https://www.ml-quant.com/issues/2026-10-09/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods
- Authors: Jongu Lee, Woojin Chang, Jungyoon Song

## Related

- [Graph Mamba: Towards Learning on Graphs with State Space Models](https://www.ml-quant.com/papers/arxiv/2402.08678/): Graph Mamba Networks, a new type of Graph Neural Networks, have been introduced, which achieve excellent performance in various benchmark datasets despite lower computational cost.
- [Edge Directionality Improves Learning on Heterophilic Graphs](https://www.ml-quant.com/papers/arxiv/2305.10498/): The study presents Directed Graph Neural Network (Dir-GNN), a new deep learning framework for directed graphs that surpasses traditional models in heterophilic benchmarks.
- [Explainable Graph Neural Networks via Structural Externalities](https://www.ml-quant.com/papers/arxiv/2507.17848/): GraphEXT, a new explainability framework for Graph Neural Networks, improves their explainability by focusing on node interactions and the effect of structural changes on predictions.
- [Decoding Quantum LDPC Codes Using Graph Neural Networks](https://www.ml-quant.com/papers/arxiv/2408.05170/): A new decoding method for Quantum Low-Density Parity-Check codes based on Graph Neural Networks outperforms conventional and neural-enhanced decoding algorithms in performance and complexity.
- [GraphCNNpred: A stock market indices prediction using a Graph based deep learning system](https://www.ml-quant.com/papers/arxiv/2407.03760/): Stock Prediction: The paper introduces a graph neural network-based convolutional neural network model for predicting stock market prices, using custom feature engineering on diverse data sources.
- [GNN-VPA: A Variance-Preserving Aggregation Strategy for Graph Neural Networks](https://www.ml-quant.com/papers/arxiv/2403.04747/): A new variance-preserving aggregation function for Graph Neural Networks is proposed, which could lead to more efficient and self-normalizing networks.