Inductive Transfer Learning for Graph-Based Recommenders
This addresses the challenge of applying graph-based recommenders to new users, items, or datasets without retraining, which is incremental as it builds on existing methods to enable cross-domain generalization.
The paper tackled the problem of graph-based recommender systems being limited to transductive settings by proposing NBF-Rec, a model that supports inductive transfer learning across datasets with disjoint user and item sets, achieving competitive performance in zero-shot settings and improvements with fine-tuning on seven real-world datasets.
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.