A Temporal Graph Network Framework for Dynamic Recommendation

Yejin Kim, Youngbin Lee, Vincent Yuan, Annika Lee, Yongjae Lee
3/24/2024
cs.AI

No official code found. Best implementation: yejining99/TGN_Rec (4 stars, last commit 2023-11-09).

Abstract

Recommender systems, crucial for user engagement on platforms like e-commerce and streaming services, often lag behind users' evolving preferences due to static data reliance. After Temporal Graph Networks (TGNs) were proposed, various studies have shown that TGN can significantly improve situations where the features of nodes and edges dynamically change over time. However, despite its promising capabilities, it has not been directly applied in recommender systems to date. Our study bridges this gap by directly implementing Temporal Graph Networks (TGN) in recommender systems, a first in this field. Using real-world datasets and a range of graph and history embedding methods, we show TGN's adaptability, confirming its effectiveness in dynamic recommendation scenarios.

View on arXivView PDF

Code Implementations(1)

yejining99/TGN_RecCommunity100%

Temporal Graph Networks for Recommender System

40Shell, PythonNov 7, 20232 years ago

Similar Papers

DynLLM: When Large Language Models Meet Dynamic Graph Recommendation

86% match2024

A Recommender System for NFT Collectibles with Item Feature

85% match2024

Using LLMs to Capture Users' Temporal Context for Recommendation

84% match2025

Dynamic User Interest Augmentation via Stream Clustering and Memory Networks in Large-Scale Recommender Systems

82% match2024

HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling

82% match1 repo6252024

Continual Recommender Systems

82% match2025

Cite this paper

@article{kim2024temporal,
  title  = {A Temporal Graph Network Framework for Dynamic Recommendation},
  author = {Yejin Kim and Youngbin Lee and Vincent Yuan and Annika Lee and Yongjae Lee},
  year   = {2024},
  eprint = {2403.16066},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.16066v2}
}

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/2403.16066.svg)](https://codeofpaper.com/paper/2403.16066)

Discussion