Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding
By Jiaxi Tang, Ke Wang. 2018
2,242 citations recorded by the source corpus.
Top-N sequential recommendation models each user as a sequence of items interacted in the past and aims to predict top-N ranked items that a user will likely interact in a »near future». The order of interaction implies that sequential patterns play an important role where more recent items in a sequence have a larger impact on the next item. In this paper, we propose a Convolutional Sequence Embedding Recommendation Model »Caser» as a solution to address this requirement. The idea is to embed a sequence of recent items into an »image» in the time and latent spaces and learn sequential patterns as local features of the image using convolutional filters. This approach provides a unified and flexible network structure for capturing both general preferences and sequential patterns. The experiments on public data sets demonstrated that Caser consistently outperforms state-of-the-art sequential recommendation methods on a variety of common evaluation metrics.
Subfields: Artificial Intelligence, Information Systems, Transportation
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
- Xiangnan He
- Wayne Xin Zhao
- Yongfeng Zhang
- Ji-rong Wen
- Xiang Wang
- Yi Tay
- Julian McAuley
- Tat-seng Chua
In Information Systems
In Transportation
Citations in the corpus
- Explainable Recommendation: A Survey and New Perspectives (2018, background): “The deep explainable recommendation models cover a wide range of deep learning techniques, including CNN (Seo et al., 2017; Tang and Wang, 2018), RNN/LSTM (Donkers et al.”
- Large Language Models are Zero-Shot Rankers for Recommender Systems (2023, methodology): “5-turbo to (1) LLMs that have not been instruction-tuned, like LLaMA [28], and (2) LLMs that have been fine-tuned on instructions, including Vicuna [3] and text-davinci-003 2 , and then instruct these LLMs to perform the ranking task.”
- Incorporating Interpretability into Latent Factor Models via Fast Influence Analysis (2018, background): “Existing works on enhancing recommender systems with interpretability can be classified into different categories based on the type of recommendation models, including latent factor models [1, 3, 23, 26, 39], memory-based models [29, 32], graph-based models [5, 15, 35], deep learning models [8, 24, ”
- A Simple Convolutional Generative Network for Next Item Recommendation (2018, methodology): “(3) ( see [20, 25, 29, 30]).”
- Is ChatGPT a Good Recommender? A Preliminary Study (2023, methodology): “For sequential recommendation, we adopt Caser [51], HGN [35], GRU4Rec [21], BERT4Rec [49], FDSA [64], SASRec [24] and S 3 -Rec [68] as baselines for comparison.”
- A Survey on Session-based Recommender Systems (2019, methodology): “Furthermore, most of co-occurrence-based dependencies among interactions are collective dependencies [101, 141], i.”
- Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation (2021, methodology): “• Caser [42] is a CNN-based method capturing high-order patterns by applying horizontal and vertical convolutional operations for sequential recommendation.”
- Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation (2021, methodology): “• Caser [24]: Caser uses horizontal and vertical CNN to capture the information.”
- BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer (2019, methodology): “Other than recurrent neural networks, various deep learning models are also introduced for sequential recommendation [3, 22, 33, 49].”
- RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms (2020, neutral): “Caser [62] WSDM 2018 MovieLens, Gowalla, Foursquare, Tmall”
- Recommender Systems with Generative Retrieval (2023, methodology): “• Caser [32] uses a CNN architecture for capturing high-order Markov Chains by applying horizontal and vertical convolutional operations for sequential recommendation.”
- STAN: Spatio-Temporal Attention Network for Next Location Recommendation (2021, background): “Besides, they modified neural architectures [28, 35, 43] or stacked extra modules [2, 8, 27] to integrate these additional information.”
- Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems (2019, background): “In addition, recent works have applied sequence models for dynamic recommender systems [12, 31, 35] as well.”
- Hierarchical Gating Networks for Sequential Recommendation (2019, methodology): “xisting methods have proposed effective models and achieved satisfactory results, we argue that there are still several factors to be considered for enhancing the performance. First, previous studies [12, 13, 28, 34] learn the user action sequence by CNN or RNN structures, which does not consider th”
- Federated User Representation Learning (2019, background): “…a simple, communication-efficient, scalable, privacy-preserving scheme, called FURL, to extend existing neural-network personalization to FL. FURL can personalize models in FL by learning task-specific user representations (i.e., embeddings) [15, 8, 23, 14, 11] or by personalizing model weights [29].”
- Handling Information Loss of Graph Neural Networks for Session-based Recommendation (2020, methodology): “Following [14, 21], for each method, grid search is applied to find the optimal hyper-parameters using the last 20% of the training set as the validation set.”
- AMER: Automatic Behavior Modeling and Interaction Exploration in Recommender System (2020, methodology): “(10) in [67]), and replace by summation, to avoid the unfair use of the embedding with double dimension.”
- Self-attention with Functional Time Representation Learning (2019, methodology): “For the recommendation tasks on MovieLens dataset, we choose the seminal session-based RNN recommendation model (GRU4Rec) [8], convolutional sequence embedding method (Caser) [19] and translation-based recommendation model (TransRec) [10] as baselines.”