Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval - Citegraph

Paper Info

Title
Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval

Abstract
Many recent advances in neural information retrieval models, which predict top-K items given a query, learn directly from a large training set of (query, item) pairs. However, they are often insufficient when there are many previously unseen (query, item) combinations, often referred to as the cold start problem. Furthermore, the search system can be biased towards items that are frequently shown to a query previously, also known as the 'rich get richer' (a.k.a. feedback loop) problem. In light of these problems, we observed that most online content platforms have both a search and a recommender system that, while having heterogeneous input spaces, can be connected through their common output item space and a shared semantic representation. In this paper, we propose a new Zero-Shot Heterogeneous Transfer Learning framework that transfers learned knowledge from the recommender system component to improve the search component of a content platform. First, it learns representations of items and their natural-language features by predicting (item, item) correlation graphs derived from the recommender system as an auxiliary task. Then, the learned representations are transferred to solve the target search retrieval task, performing query-to-item prediction without having seen any (query, item) pairs in training. We conduct online and offline experiments on one of the world's largest search and recommender systems from Google, and present the results and lessons learned. We demonstrate that the proposed approach can achieve high performance on offline search retrieval tasks, and more importantly, achieved significant improvements on relevance and user interactions over the highly-optimized production system in online experiments.

Year	DOI	Venue
2020	10.1145/3340531.3412752	CIKM '20: The 29th ACM International Conference on Information and Knowledge Management Virtual Event Ireland October, 2020
DocType	ISBN	Citations
Conference	978-1-4503-6859-9	2
PageRank	References	Authors
0.37	21	18

Authors (18 rows)

Cited by (2 rows)

References (21 rows)

Name	Order	Citations	PageRank
Tao Wu	1	2	1.04
Ellie Ka-In Chio	2	2	0.37
Heng-Tze Cheng	3	612	26.54
Yu Du	4	2	0.37
Steffen Rendle	5	1963	70.68
Dima Kuzmin	6	2	0.71
Ritesh Agarwal	7	2	0.37
Li Zhang	8	4	1.39
John Anderson	9	42	7.10
Sarvjeet Singh	10	2	1.04
Tushar Deepak Chandra	11	5163	388.99
Ed H. Chi	12	4806	371.21
Wen Li	13	2	0.37
Ankit Kumar	14	2	1.72
Xiang Ma	15	2	0.37
Alex Soares	16	2	0.37
Nitin Jindal	17	1087	55.67
Pei Cao	18	29	6.44

1