Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution

Cong Xu, Jun Wang, Jianyong Wang, Wei Zhang
2/12/2026

No official code found. Best implementation: MTandHJ/SEvo (5 stars, MIT, last commit 2024-10-16).

Abstract

Embedding plays a key role in modern recommender systems because they are virtual representations of real-world entities and the foundation for subsequent decision-making models. In this paper, we propose a novel embedding update mechanism, Structure-aware Embedding Evolution (SEvo for short), to encourage related nodes to evolve similarly at each step. Unlike GNN (Graph Neural Network) that typically serves as an intermediate module, SEvo is able to directly inject graph structural information into embedding with minimal computational overhead during training. The convergence properties of SEvo along with its potential variants are theoretically analyzed to justify the validity of the designs. Moreover, SEvo can be seamlessly integrated into existing optimizers for state-of-the-art performance. Particularly SEvo-enhanced AdamW with moment estimate correction demonstrates consistent improvements across a spectrum of models and datasets, suggesting a novel technical route to effectively utilize graph structural information beyond explicit GNN modules.

View on arXivView PDF

Code Implementations(1)

MTandHJ/SEvoCommunity100%
MIT

SEvo, NeurIPS 2024

50Shell, PythonSep 22, 20232 years agoMIT

Similar Papers

Lighter-X: An Efficient and Plug-and-play Strategy for Graph-based Recommendation through Decoupled Propagation

80% match2025

Coarse-to-Fine Lightweight Meta-Embedding for ID-Based Recommendation

80% match1 repo22025

E2E-GRec: An End-to-End Joint Training Framework for Graph Neural Networks and Recommender Systems

79% match2025

Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems

79% match2025

Heterogeneous Sequel-Aware Graph Neural Networks for Sequential Learning

79% match2025

Instant Representation Learning for Recommendation over Large Dynamic Graphs

79% match1 repo92023

Cite this paper

@article{xu2026graphenhanced,
  title  = {Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution},
  author = {Cong Xu and Jun Wang and Jianyong Wang and Wei Zhang},
  year   = {2026},
  eprint = {2310.03032},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2310.03032},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.03032.svg)](https://codeofpaper.com/paper/2310.03032)

Discussion