PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation

Li, Yang; Zhu, Jieming; Liu, Weiwen; Su, Liangcai; Cai, Guohao; Zhang, Qi; Tang, Ruiming; Xiao, Xi; He, Xiuqiang

doi:10.1145/3487553.3524208

Cited by 9 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Deep Listwise Context Model proposed by Ai et al [1] also models the list context with a recurrent neural network, yet this model is not used to actually predict listwide signals. The most related work to ours is the Personalized Re-ranking with Contextualized Transformer for Recommendation (PEAR), recently proposed by Li et al [24]. In the personalized recommendation setting, the PEAR model combines a pointwise ranking objective, i.e.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

RankFormer: Listwise Learning-to-Rank Using Listwide Labels

Buyl,

Missault,

Sondag

2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Web applications where users are presented with a limited selection of items have long employed ranking models to put the most relevant results first. Any feedback received from users is typically assumed to reflect a relative judgement on the utility of items, e.g. a user clicking on an item only implies it is better than items not clicked in the same ranked list. Hence, the objectives optimized in Learning-to-Rank (LTR) tend to be pairwise or listwise.Yet, by only viewing feedback as relative, we neglect the user's absolute feedback on the list's overall quality, e.g. when no items in the selection are clicked. We thus reconsider the standard LTR paradigm and argue the benefits of learning from this listwide signal. To this end, we propose the RankFormer as an architecture that, with a Transformer at its core, can jointly optimize a novel listwide assessment objective and a traditional listwise LTR objective.We simulate implicit feedback on public datasets and observe that the RankFormer succeeds in benefitting from listwide signals. Additionally, we conduct experiments in e-commerce on Amazon Search data and find the RankFormer to be superior to all baselines offline. An online experiment shows that knowledge distillation can be used to find immediate practical use for the RankFormer. CCS CONCEPTS• Information systems → Learning to rank; • Computing methodologies → Learning from implicit feedback.

show abstract

Section: Related Workmentioning

confidence: 99%

“…This kind of transformation can be learned end-to-end by applying an attention mechanism over 𝑿 𝐼 , e.g. through the use of the Transformer [38] architecture that has seen tremendous success in Natural Language Processing (NLP) and has recently also been applied to ranking problems [24,30,34,37].…”

Section: The Listwise Transformermentioning

confidence: 99%