Time Interval Aware Self-Attention for Sequential Recommendation

By Jiacheng Li, Yujie Wang, Julian McAuley. Web Search and Data Mining, 2020

764 citations recorded by the source corpus.

Sequential recommender systems seek to exploit the order of users' interactions, in order to predict their next action based on the context of what they have done recently. Traditionally, Markov Chains(MCs), and more recently Recurrent Neural Networks (RNNs) and Self Attention (SA) have proliferated due to their ability to capture the dynamics of sequential patterns. However a simplifying assumption made by most of these models is to regard interaction histories as ordered sequences, without regard for the time intervals between each interaction (i.e., they model the time-order but not the actual timestamp). In this paper, we seek to explicitly model the timestamps of interactions within a sequential modeling framework to explore the influence of different time intervals on next item prediction. We propose TiSASRec (Time Interval aware Self-attention based sequential recommendation), which models both the absolute positions of items as well as the time intervals between them in a sequence. Extensive empirical studies show the features of TiSASRec under different settings and compare the performance of self-attention with different positional encodings. Furthermore, experimental results show that our method outperforms various state-of-the-art sequential models on both sparse and dense datasets and different evaluation metrics.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/9c7a455b1e48d01a99e58e884a6c1acb75074ad0

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. Wayne Xin Zhao
2. Ji-rong Wen
3. Qiang Liu
4. Kun Zhou
5. Julian McAuley
6. Jiacheng Li
7. Yingtao Luo
8. Zhaocheng Liu

In Information Systems

1. Wayne Xin Zhao
2. Ji-rong Wen
3. Jiacheng Li
4. Kun Zhou
5. Qiang Liu
6. Yingtao Luo
7. Zhaocheng Liu
8. Jia Li

In Management Science and Operations Research

1. Yingtao Luo
2. Zhaocheng Liu
3. Qiang Liu
4. Jiacheng Li
5. Ming Wang
6. Jin Li
7. Jingbo Shang
8. Xin Shen

Citations in the corpus

• STAN: Spatio-Temporal Attention Network for Next Location Recommendation (2021, methodology): “• EWTI (Element-Wise Temporal Intervals): This denotes the element-wise temporal intervals following the structure of TiSASRec [17].”
• Text Is All You Need: Learning Language Representations for Sequential Recommendation (2023, methodology): “Various methods have been proposed to improve the performance of sequential recommendation, including Markov Chains [9, 25], RNN/CNN models [11, 17, 28, 34] and self-attentive models [14, 19, 27].”
• Filter-enhanced MLP is All You Need for Sequential Recommendation (2022, background): “,memory network [9, 20] and self-attention mechanism [26, 27]) to enhance the modeling capacity for effectively capturing dynamic user preference.”
• Intent Contrastive Learning for Sequential Recommendation (2022, background): “With the success of deep learning, deep Sequential Recommendation (SR) [13, 35] models, which aims at dynamically characterizing the behaviors of users with different deep neural networks [43, 46], arguably represents the current state-of-theart [6, 13, 19, 27, 35, 45, 51].”