Time-based Sequence Model for Personalization and Recommendation Systems
arXiv:2008.11922
Abstract
In this paper we develop a novel recommendation model that explicitly incorporates time information. The model relies on an embedding layer and TSL attention-like mechanism with inner products in different vector spaces, that can be thought of as a modification of multi-headed attention. This mechanism allows the model to efficiently treat sequences of user behavior of different length. We study the properties of our state-of-the-art model on statistically designed data set. Also, we show that it outperforms more complex models with longer sequence length on the Taobao User Behavior dataset.
17 pages, 7 figures
References in corpus (14)
- xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
- Deep Learning Recommendation Model for Personalization and Recommendation Systems
- Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
- Training Deep AutoEncoders for Collaborative Filtering
- Gradient Boosting Neural Networks: GrowNet
- Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems
- Fast Transformer Decoding: One Write-Head is All You Need
- FLEN: Leveraging Field for Scalable CTR Prediction
- On the Dimensionality of Embeddings for Sparse Features and Data
- Large-scale Collaborative Filtering with Product Embeddings
- Sequential Evaluation and Generation Framework for Combinatorial Recommender System
- Latent Factor Interpretations for Collaborative Filtering
- Deep Neural Network Ensembles