---
title: "Variational Graph Auto-Encoder Driven Graph Enhancement for Sequential Recommendation"
authors:
  - "Yuwen Liu"
  - "Lianyong Qi"
  - "Xingyuan Mao"
  - "Weiming Liu"
  - "Shichao Pei"
  - "Fan Wang"
  - "Xuyun Zhang"
  - "Amin Beheshti"
  - "Xiaokang Zhou"
doi: "10.24963/ijcai.2025/350"
url: "https://ijcai.org/proceedings/2025/350"
pdf: "https://ijcai.org/proceedings/2025/0350.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "3144-3152"
track: "Main Track"
keywords:
  - "Data Mining: DM: Recommender systems"
  - "Data Mining: DM: Mining spatial and/or temporal data"
---

# Variational Graph Auto-Encoder Driven Graph Enhancement for Sequential Recommendation

Yuwen Liu, Lianyong Qi, Xingyuan Mao, Weiming Liu, Shichao Pei, Fan Wang, Xuyun Zhang, Amin Beheshti, Xiaokang Zhou

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 3144-3152. DOI: [10.24963/ijcai.2025/350](https://doi.org/10.24963/ijcai.2025/350)

## Abstract

Recommender systems play a critical role in many applications by providing personalized recommendations based on user interactions. However, it remains a major challenge to capture complex sequential patterns and address noise in user interaction data. While advanced neural networks have enhanced sequential recommendation by modeling high-order item dependencies, they typically assume that the noisy interaction data as the user's preferred preferences. This assumption can lead to suboptimal recommendation results. We propose a Variational Graph Auto-Encoder driven Graph Enhancement (VGAE-GE) method for robust augmentation in sequential recommendation. Specifically, our method first constructs an item transition graph to capture higher-order interactions and employs a Variational Graph Auto-Encoder (VGAE) to generate latent variable distributions. By utilizing these latent variable distributions for graph reconstruction, we can improve the item representation. Next, we use a Graph Convolutional Network (GCN) to transform these latent variables into embeddings and infer more robust user representations from the updated item embeddings. Finally, we obtain the reconstructed user check-in data, and then use a Mamba-based recommender to make the recommendation process more efficient and the recommendation results more accurate. Extensive experiments on five public datasets demonstrate that our VGAE-GE model improves recommendation performance and robustness.