Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba

By Jizhe Wang, Pipei Huang, Huan Zhao, Zhibo Zhang, Binqiang Zhao, Dik Lun Lee. 2018

569 citations recorded by the source corpus.

Recommender systems (RSs) have been the most important technology for increasing the business in Taobao, the largest online consumer-to-consumer (C2C) platform in China. There are three major challenges facing RS in Taobao: scalability, sparsity and cold start. In this paper, we present our technical solutions to address these three challenges. The methods are based on a well-known graph embedding framework. We first construct an item graph from users' behavior history, and learn the embeddings of all items in the graph. The item embeddings are employed to compute pairwise similarities between all items, which are then used in the recommendation process. To alleviate the sparsity and cold start problems, side information is incorporated into the graph embedding framework. We propose two aggregation methods to integrate the embeddings of items and the corresponding side information. Experimental results from offline experiments show that methods incorporating side information are superior to those that do not. Further, we describe the platform upon which the embedding methods are deployed and the workflow to process the billion-scale data in Taobao. Using A/B test, we show that the online Click-Through-Rates (CTRs) are improved comparing to the previous collaborative filtering based methods widely used in Taobao, further demonstrating the effectiveness and feasibility of our proposed methods in Taobao's live production environment.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Meng Wang
5. Hongwei Wang
6. Jie Tang
7. Wenjie Li
8. Fuzheng Zhang

In Computer Networks and Communications

1. Xiang Wang
2. Meng Wang
3. Shaojie Tang
4. Dik Lun Lee
5. Yongdong Zhang
6. Jure Leskovec
7. Jingren Zhou
8. Jie Tang

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Meng Wang
4. Tat-seng Chua
5. Wenjie Li
6. Hongwei Wang
7. Miao Zhao
8. Fuzheng Zhang

Citations in the corpus

• Secure Federated Submodel Learning (2019, background): “For example, as the largest online consumerto-consumer platform in China, Taobao (owned by Alibaba) has roughly two billion goods in total [10], which is far larger than the 10,000 word vocabulary in the natural language scenario of Google’s Gboard [2], [11], [12].”
• DAPPLE: a pipelined data parallel approach for training large models (2020, background): “, NLP[39], search/recommendation systems[13, 45]) have billions of parameters, demanding tens to hundreds of GBs of device memory for training.”
• Representation Learning for Attributed Multiplex Heterogeneous Network (2019, background): “Real networks usually have billions of nodes and tens or hundreds of billions of edges [40].”
• Multi-Interest Network with Dynamic Routing for Recommendation at Tmall (2019, background): “) that have been proved to be useful for cold-start items [25] from Fi , corresponding embeddings are further passed through an average pooling layer to form the label item embedding − →e i .”
• Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems (2019, background): “Recommender systems are widely used in Internet applications to meet user’s personalized interests and alleviate the information overload [4, 29, 32].”
• Practical Privacy Preserving POI Recommendation (2020, background): “The recommender system has been drawing much attention in recent decades, and achieving great successes in many real-world applications such as vidio [17], E-commerce [57], and Point-ofInterest (POI) (e.”
• Simplifying Architecture Search for Graph Neural Network (2020, background): “, recommendation [24, 29], fraud detection [18], chemistry [11].”
• Inductive Representation Learning on Temporal Graphs (2020, methodology): “The technique of learning lower-dimensional vector embeddings on graphs have been widely applied to graph analysis tasks (Perozzi et al., 2014; Tang et al., 2015; Wang et al., 2016) and deployed in industrial systems (Ying et al., 2018; Wang et al., 2018a).”
• Behavior sequence transformer for e-commerce recommendation in Alibaba (2019, background): “As introduced in our previous work [15], the item_id and category_id are good enough for the performance, we choose these two as sparse features to represent each item in embedding the user’s behavior sequences.”
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation (2020, background): “With the prevalence of linked graph data in real applications, graph-based models are becoming increasingly important in recommendation [12, 37]; by explicitly exploiting the relations among entities in the predictive model, they are advantageous to traditional supervised learning scheme like factor”
• This paper is included in the Proceedings of the 19th USENIX Symposium on Networked Systems Design and Implementation. (background): “These include e-commerce mar-ketplaces (e.g. Amazon, Alibaba) for recommending items to purchase [30,33], social media platforms (e.g. Facebook, Twitter) for providing the most relevant content [14], enter-tainment services (e.g. Netflix, Youtube) for promoting new playlists [7,12], and storage…”