Abstract
Click-through rate (CTR) prediction plays an important role in search and recommendation, which are the two most prominent scenarios in e-commerce. A number of models have been proposed to predict CTR by mining user behaviors, especially users’ interactions with items. But the sparseness of user behaviors is an obstacle to the improvement of CTR prediction. Previous works only focused on one scenario, either search or recommendation. However, on a practical e-commerce platform, search and recommendation share the same set of users and items, which means joint learning of both scenarios may alleviate the sparseness of user behaviors. In this paper, we propose a novel Search and Recommendation Joint Graph (SRJGraph) neural network to jointly learn a better CTR model for both scenarios. A key question of joint learning is how to effectively share information across search and recommendation, in spite of their differences. A notable difference between search and recommendation is that there are explicit queries in search, whereas no query exists in recommendation. We address this difference by constructing a unified graph to share representations of users and items across search and recommendation, as well as represent user-item interactions uniformly. In this graph, users and items are heterogeneous nodes, and search queries are incorporated into the user-item interaction edges as attributes. For recommendation where no query exists, a special attribute is attached on user-item interaction edges. We further propose an intention and upstream-aware aggregator to explore useful information from high-order connections among users and items. We conduct extensive experiments on a large-scale dataset collected from Taobao.com, the largest e-commerce platform in China. Empirical results show that SRJGraph significantly outperforms the state-of-the-art ap- proaches of CTR prediction in both search and recommendation tasks.
Plain Text
복사
Summary
•
검색, 추천에서 CTR 예측은 중요한 role임
◦
이를 위해 유저-아이템 상호작용을 이해하는 과정 필요
◦
sparseness of user behaviors 는 CTR 예측의 장애물
•
이전 연구들은 검색과 추천 둘 중에 하나의 시나리오만 다룸
◦
둘 다 같은 유저와 아이템을 사용, 두 시나리오를 함께 이용해 joint learning을 하면 sparsness 문제를 완화할 수 있음
◦
key question : 어떻게 검색과 추천 사이의 정보를 효과적으로 공유할 것인가?
•
검색, 추천 주요한 차이 : 검색은 explicit queries 존재 / 추천은 쿼리 없음
◦
이 차이를 해결하기 위해 unified graph 구성
◦
그래프에서 user, item은 heterogeneous node / search queries는 edge의 attribute로 통합
•
검색, 추천 시나리오에서 모두 좋은 성능 보여줌