.png){kind=icon}
.png){kind=icon}
Return
Utility-Oriented Reranking with Counterfactual Context
.png){kind=icon}
OA
AI
DOI：10.1145/3671004.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
As a critical task for large-scale commercial recommender systems, reranking rearranges items in the initialranking lists from the previous ranking stage to better meet users' demands. Foundational work in rerankinghas shown the potential of improving recommendation results by uncovering mutual influence among items.However, rather than considering the context of initial lists as most existing methods do, an ideal rerankingalgorithm should consider thecounterfactual context-the position and the alignment of the items in thereranked lists. In this work, we propose a novel pairwise reranking framework, Utility-oriented Reranking withCounterfactual Context (URCC), which maximizes the overall utility after reranking efficiently. Specifically,we first design a utility-oriented evaluator, which applies Bi-LSTM and graph attention mechanism to estimatethe listwise utility via thecounterfactual contextmodeling. Then, under the guidance of the evaluator, wepropose a pairwise reranker model to find the most suitable position for each item by swapping misplaced itempairs. Extensive experiments on two benchmark datasets and a proprietary real-world dataset demonstratethat URCC significantly outperforms the state-of-the-art models in terms of both relevance-based metrics andutility-based metrics
Keywords:
Recommender system
reranking
utility maximization
implicit feedback
Journal
IF:
4.8
Papers:
1.3K
Citations:
4.4K