Density Weighting for Multi-Interest Personalized Recommendation

TL;DR

This paper introduces an iterative density weighting scheme to enhance multi-interest recommendation systems, making them more robust to data imbalance and tail item performance issues.

Contribution

The paper proposes a novel iterative density weighting method with user tower calibration to improve multi-interest recommendation under skewed data distributions.

Findings

IDW outperforms existing methods on real-world benchmarks.

Synthetic data experiments show IDW's robustness to data imbalance.

Improved tail item recommendation performance.

Abstract

Using multiple user representations (MUR) to model user behavior instead of a single user representation (SUR) has been shown to improve personalization in recommendation systems. However, the performance gains observed with MUR can be sensitive to the skewness in the item and/or user interest distribution. When the data distribution is highly skewed, the gains observed by learning multiple representations diminish since the model dominates on head items/interests, leading to poor performance on tail items. Robustness to data sparsity is therefore essential for MUR-based approaches to achieve good performance for recommendations. Yet, research in MUR and data imbalance have largely been done independently. In this paper, we delve deeper into the shortcomings of MUR inferred from imbalanced data distributions. We make several contributions: (1) Using synthetic datasets, we demonstrate the sensitivity of MUR with respect to data imbalance, (2) To improve MUR for tail items, we propose an iterative density weighting scheme (IDW) with user tower calibration to mitigate the effect of training over long-tail distribution on personalization, and (3) Through extensive experiments on three real-world benchmarks, we demonstrate IDW outperforms other alternatives that address data imbalance.