Inductive Transfer Learning for Graph-Based Recommenders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grötschla, Florian, Trachsel, Elia, Lanzendörfer, Luca A., Wattenhofer, Roger
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917044602011648
author Grötschla, Florian
Trachsel, Elia
Lanzendörfer, Luca A.
Wattenhofer, Roger
author_facet Grötschla, Florian
Trachsel, Elia
Lanzendörfer, Luca A.
Wattenhofer, Roger
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22799
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inductive Transfer Learning for Graph-Based Recommenders
Grötschla, Florian
Trachsel, Elia
Lanzendörfer, Luca A.
Wattenhofer, Roger
Machine Learning
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.
title Inductive Transfer Learning for Graph-Based Recommenders
topic Machine Learning
url https://arxiv.org/abs/2510.22799