Rethinking Multi-objective Ranking Ensemble in Recommender System: From Score Fusion to Rank Consistency

TL;DR

This paper introduces HarmonRank, a novel multi-objective ensemble framework for recommender systems that optimizes rank consistency and shared objectives alignment, outperforming existing methods and improving real-world e-commerce performance.

Contribution

HarmonRank is the first method to simultaneously optimize for rank consistency and shared objective commonality in multi-objective ranking ensembles.

Findings

Significantly outperforms state-of-the-art methods in offline tests.

Demonstrates robustness to label skew in industrial scenarios.

Achieves 2.6% purchase gain in live deployment.

Abstract

The industrial recommender systems always pursue more than one business goals. The inherent intensions between objectives pose significant challenges for ranking stage. A popular solution is to build a multi-objective ensemble (ME) model to integrate multi-objective predictions into a unified score. Although there have been some exploratory efforts, few work has yet been able to systematically delineate the core requirements of ME problem. We rethink ME problem from two perspectives. From the perspective of each individual objective, to achieve its maximum value the scores should be as consistent as possible with the ranks of its labels. From the perspective of entire set of objectives, an overall optimum can be achieved only when the scores align with the commonality shared by the majority of objectives. However, none of existing methods can meet these two requirements. To fill this gap, we propose a novel multi-objective ensemble framework HarmonRank to fulfill both requirements. For rank consistency, we formulate rank consistency (AUC) metric as a rank-sum problem and make the model optimized towards rank consistency in an end-to-end differentiable manner. For commonality modeling, we change the original relation-agnostic ensemble paradigm to a relation-aware one. Extensive offline experimental results on two industrial datasets and online experiments demonstrate that our approach significantly outperforms existing state-of-the-art methods. Besides, our method exhibits superior robustness to label skew situations which is common in industrial scenarios. The proposed method has been fully deployed in Kuaishou's live-streaming e-commerce recommendation platform with 400 million DAUs, contributing 2.6% purchase gain.