Inductive Transfer Learning for Graph-Based Recommenders

TL;DR

This paper introduces NBF-Rec, a graph-based recommender system capable of inductive transfer learning, enabling recommendations across different datasets without retraining, and demonstrating strong zero-shot performance.

Contribution

The paper presents NBF-Rec, a novel graph-based recommendation model that supports inductive transfer learning across disjoint datasets by computing node embeddings dynamically at inference time.

Findings

NBF-Rec achieves competitive zero-shot recommendation performance.

The method improves with lightweight fine-tuning.

Inductive transfer is feasible in graph-based recommenders.

Abstract

Graph-based recommender systems are commonly trained in transductive settings, which limits their applicability to new users, items, or datasets. We propose NBF-Rec, a graph-based recommendation model that supports inductive transfer learning across datasets with disjoint user and item sets. Unlike conventional embedding-based methods that require retraining for each domain, NBF-Rec computes node embeddings dynamically at inference time. We evaluate the method on seven real-world datasets spanning movies, music, e-commerce, and location check-ins. NBF-Rec achieves competitive performance in zero-shot settings, where no target domain data is used for training, and demonstrates further improvements through lightweight fine-tuning. These results show that inductive transfer is feasible in graph-based recommendation and that interaction-level message passing supports generalization across datasets without requiring aligned users or items.