作者位次 #4/5SIGIR 2026Poster· Information Retrieval (Resource)
ERASE - A Real-World Aligned Benchmark for Unlearning in Recommender Systems
Pierre Sicco Lubitzsch (BIFOLD & · Sebastian Schelter · Sebastian Schelter · Sebastian Schelter (BIFOLD & · Sebastian Schelter
摘要
Machine unlearning (MU) enables the removal of selected training data from models to address privacy compliance, security, and liability issues in recommender systems. Existing MU benchmarks poorly reflect real-world recommender settings: they focus primarily on collaborative filtering, assume un...