Unsupervised Graph Embeddings for Session-based Recommendation with Item Features

2025-02-19

AI Summary

To address the insufficient item representation capability in session-based recommendation, this paper proposes GCNext: a novel framework that for the first time directly incorporates item attribute features into the graph convolution process, constructing a feature-enriched item co-occurrence graph and learning semantically richer item embeddings via an unsupervised graph convolutional network. GCNext enhances session sequence modeling without requiring labeled data and is compatible with mainstream sequential recommendation models. Experiments on three benchmark datasets demonstrate significant performance improvements—up to 12.79% gain in MRR@20—and consistently boost representation quality for both nearest-neighbor methods and deep models. The core contribution lies in a feature-driven, unsupervised graph embedding paradigm that jointly models item semantics and co-occurrence structure.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Recommender Systems
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In session-based recommender systems, predictions are based on the user's preceding behavior in the session. State-of-the-art sequential recommendation algorithms either use graph neural networks to model sessions in a graph or leverage the similarity of sessions by exploiting item features. In this paper, we combine these two approaches and propose a novel method, Graph Convolutional Network Extension (GCNext), which incorporates item features directly into the graph representation via graph convolutional networks. GCNext creates a feature-rich item co-occurrence graph and learns the corresponding item embeddings in an unsupervised manner. We show on three datasets that integrating GCNext into sequential recommendation algorithms significantly boosts the performance of nearest-neighbor methods as well as neural network models. Our flexible extension is easy to incorporate in state-of-the-art methods and increases the MRR@20 by up to 12.79%.

Problem

• Enhance session-based recommendation accuracy
• Integrate item features in graph models
• Unsupervised learning of item embeddings

Innovation

• Graph Convolutional Network Extension
• Unsupervised item embeddings
• Feature-rich item co-occurrence graph