Lightweight Inference-Time Personalization for Frozen Knowledge Graph Embeddings

TL;DR

GatedBias is a lightweight, inference-time personalization method for frozen knowledge graph embeddings that improves individual user preference alignment without retraining, using only about 300 trainable parameters.

Contribution

It introduces a structure-gated adaptation framework enabling personalized biases in frozen KG embeddings with minimal parameters, maintaining global accuracy.

Findings

Significant improvements in personalization metrics on benchmark datasets.

Counterfactual experiments confirm causal responsiveness of the method.

Parameter-efficient adaptation with only ~300 trainable parameters.

Abstract

Foundation models for knowledge graphs (KGs) achieve strong cohort-level performance in link prediction, yet fail to capture individual user preferences; a key disconnect between general relational reasoning and personalized ranking. We propose GatedBias, a lightweight inference-time personalization framework that adapts frozen KG embeddings to individual user contexts without retraining or compromising global accuracy. Our approach introduces structure-gated adaptation: profile-specific features combine with graph-derived binary gates to produce interpretable, per-entity biases, requiring only ${\sim}300$ trainable parameters. We evaluate GatedBias on two benchmark datasets (Amazon-Book and Last-FM), demonstrating statistically significant improvements in alignment metrics while preserving cohort performance. Counterfactual perturbation experiments validate causal responsiveness; entities benefiting from specific preference signals show 6--30$\times$ greater rank improvements when those signals are boosted. These results show that personalized adaptation of foundation models can be both parameter-efficient and causally verifiable, bridging general knowledge representations with individual user needs.