Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems

By Jiaxuan You, Yichen Wang, Aditya Pal, Pong Eksombatchai, Chuck Rosenberg, Jure Leskovec. 2019

143 citations recorded by the source corpus.

Recommender systems that can learn from cross-session data to dynamically predict the next item a user will choose are crucial for online platforms. However, existing approaches often use out-of-the-box sequence models which are limited by speed and memory consumption, are often infeasible for production environments, and usually do not incorporate cross-session information, which is crucial for effective recommendations. Here we propose Hierarchical Temporal Convolutional Networks (HierTCN), a hierarchical deep learning architecture that makes dynamic recommendations based on users' sequential multi-session interactions with items. HierTCN is designed for web-scale systems with billions of items and hundreds of millions of users. It consists of two levels of models: The high-level model uses Recurrent Neural Networks (RNN) to aggregate users' evolving long-term interests across different sessions, while the low-level model is implemented with Temporal Convolutional Networks (TCN), utilizing both the long-term interests and the short-term interactions within sessions to predict the next interaction. We conduct extensive experiments on a public XING dataset and a large-scale Pinterest dataset that contains 6 million users with 1.6 billion interactions. We show that HierTCN is 2.5x faster than RNN-based models and uses 90% less data memory compared to TCN-based models. We further develop an effective data caching scheme and a queue-based mini-batch generator, enabling our model to be trained within 24 hours on a single GPU. Our model consistently outperforms state-of-the-art dynamic recommendation methods, with up to 18% improvement in recall and 10% in mean reciprocal rank.

Subfields: Artificial Intelligence, 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

In Information Systems

Citations in the corpus

Recurrent Event Network for Reasoning over Temporal Knowledge Graphs (2019, methodology): “8; Trivedi et al., 2019), knowledge graph reasoning (Trivedi et al., 2017; Nguyen et al., 2018; Kazemi et al., 2019), event forecasting (Du et al., 2016), and recommender systems (Kumar et al., 2019; You et al., 2019). Previous methods over dynamic graphs mainly focus on learning time-sensitive stru”
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (2019, methodology): “8; Trivedi et al., 2019), knowledge graph reasoning (Trivedi et al., 2017; Nguyen et al., 2018; Kazemi et al., 2019), event forecasting (Du et al., 2016), and recommender systems (Kumar et al., 2019; You et al., 2019). Previous methods over dynamic graphs mainly focus on learning time-sensitive stru”
A Survey on Session-based Recommender Systems (2019, methodology): “Furthermore, Temporal Convolutional Networks (TCN) were utilized to model the interactions within sessions to predict the next interaction [146].”
Identity-aware Graph Neural Networks (2021, background): “…(Kipf and Welling 2017), GraphSAGE (Hamilton, Ying, and Leskovec 2017), and GAT (Velickovic et al. 2018), are dominantly used today due to their simplicity, efﬁciency and strong performance in real-world applications (Zitnik and Leskovec 2017; Ying et al. 2018; You et al. 2018a, 2019b, 2020a,b).”
Design Space for Graph Neural Networks (2020, background): “These architectures are then applied to a growing number of applications, such as social networks [39, 46], chemistry [13, 44], and biology [52].”
Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks (2019, background): “First, a majority of the existing meth-ods generate an embedding for a user only when she takes an action [8, 11, 47, 48, 50].”