Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering

TL;DR

This paper introduces DPAA, a novel GNN-based collaborative filtering framework that adaptively debiases popularity bias by weighting interactions and layers, improving long-tail item recommendation.

Contribution

DPAA integrates adaptive, embedding-aware interaction and layer-wise weighting directly into message passing to effectively mitigate popularity bias in GNN-based CF.

Findings

DPAA outperforms existing methods on real-world datasets.

It effectively amplifies long-range, underexposed item interactions.

Experimental results demonstrate improved recommendation diversity.

Abstract

Collaborative filtering (CF) models based on graph neural networks (GNNs) achieve strong performance in recommender systems by propagating user-item signals over interaction graphs. However, they are highly susceptible to popularity bias, since skewed interaction distributions and repeated message passing across high-order neighborhoods amplify the influence of popular items while suppressing long-tail ones. Existing debiasing approaches, including re-weighting objectives, regularization, causal methods, and post-processing, are less effective in GNN-based settings because they do not directly counteract bias propagated through the aggregation process, and recent in-aggregation weighting methods often rely on static heuristics or unstable embedding estimates. We propose Debiasing Popularity Amplification in Aggregation (DPAA), a popularity debiasing framework for GNN-based CF that integrates adaptive, embedding-aware interaction weighting and layer-wise weighting directly into message passing. DPAA assigns interaction-level weights from a representation-aware popularity signal, stabilized by a smooth transition from pre-trained to evolving model embeddings during training. It further introduces a layer-wise weighting that amplifies higher-order neighborhoods, surfacing long-range interactions with diverse and underexposed items. Experiments on real-world and semi-synthetic datasets show that DPAA outperforms state-of-the-art popularity-bias correction methods for GNN-based CF.