PULSE: Socially-Aware User Representation Modeling Toward Parameter-Efficient Graph Collaborative Filtering

2026-01-21

AI Summary

This work proposes a novel graph-based collaborative filtering framework that eliminates the need for explicit user embeddings, thereby addressing the high parameter count and poor scalability of existing graph collaborative filtering and social recommendation methods. By integrating social relationship signals directly into user representations through a graph neural network, the approach enables parameter-efficient, socially aware representation learning and multi-hop collaborative signal extraction. The resulting model reduces the number of parameters by up to 50% while consistently outperforming 13 state-of-the-art baselines across diverse sparsity scenarios—from cold-start to highly active users—demonstrating a superior balance between efficiency and recommendation performance.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Social Networks and Social Media: Social mining and social search on the Web

Abstract

Graph-based social recommendation (SocialRec) has emerged as a powerful extension of graph collaborative filtering (GCF), which leverages graph neural networks (GNNs) to capture multi-hop collaborative signals from user-item interactions. These methods enrich user representations by incorporating social network information into GCF, thereby integrating additional collaborative signals from social relations. However, existing GCF and graph-based SocialRec approaches face significant challenges: they incur high computational costs and suffer from limited scalability due to the large number of parameters required to assign explicit embeddings to all users and items. In this work, we propose PULSE (Parameter-efficient User representation Learning with Social Knowledge), a framework that addresses this limitation by constructing user representations from socially meaningful signals without creating an explicit learnable embedding for each user. PULSE reduces the parameter size by up to 50% compared to the most lightweight GCF baseline. Beyond parameter efficiency, our method achieves state-of-the-art performance, outperforming 13 GCF and graph-based social recommendation baselines across varying levels of interaction sparsity, from cold-start to highly active users, through a time- and memory-efficient modeling process.

Problem

• graph collaborative filtering
• social recommendation
• parameter efficiency
• user representation
• scalability

Innovation

• Parameter-efficient
• User representation
• Graph collaborative filtering
• Social recommendation
• GNN