Zzong's Notes

Unbiased Learning-to-Rank with Biased Feedback

1 min read

Abstract

implicit feedback 을 Learning-to-Rank 방식에 학습할 때 발생하는 bias (e.g., position bias) 를 줄이기 위해 counterfactual inference framework 를 제안

In contrast to most conventional approaches to de-bias the data using click models, 이 방식은 allows training of ranking functions even in settings where queries do not repeat.

B) Related

C) References

링크된 언급

1
position bias

...e) unbiased learning to rank framework by treating the bias as a counterfactual effect Unbiased Learning to Rank with Biased Feedback B) Papers Addressing Trust Bias for Unbiased Learning to Rank (WWW, 2019) 좀 더 진화한 구글 논...