Sequential User-based Recurrent Neural Network Recommendations

By Tim Donkers, Benedikt Loepp, Jürgen Ziegler. 2017

387 citations recorded by the source corpus.

Recurrent Neural Networks are powerful tools for modeling sequences. They are flexibly extensible and can incorporate various kinds of information including temporal order. These properties make them well suited for generating sequential recommendations. In this paper, we extend Recurrent Neural Networks by considering unique characteristics of the Recommender Systems domain. One of these characteristics is the explicit notion of the user recommendations are specifically generated for. We show how individual users can be represented in addition to sequences of consumed items in a new type of Gated Recurrent Unit to effectively produce personalized next item recommendations. Offline experiments on two real-world datasets indicate that our extensions clearly improve objective performance when compared to state-of-the-art recommender algorithms and to a conventional Recurrent Neural Network.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, 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. Yongfeng Zhang
3. Xu Chen
4. Xiang Wang
5. Wayne Xin Zhao
6. Tat-seng Chua
7. Meng Wang
8. Ji-rong Wen

In Electrical and Electronic Engineering

1. Yongfeng Zhang
2. Aminu Da’u
3. Yi Tay
4. Zheng Qin
5. Ji-rong Wen
6. Naomie Binti Salim
7. Bolin Ding
8. Longbing Cao

In Information Systems

1. Xiangnan He
2. Yongfeng Zhang
3. Xu Chen
4. Xiang Wang
5. Meng Wang
6. Tat-seng Chua
7. Wayne Xin Zhao
8. Fuli Feng

Citations in the corpus

• Explainable Recommendation: A Survey and New Perspectives (2018, methodology): “Feature-based explanation is closely related to content-based recommendation methods, where the system provides personalized recommendations by matching the user preference with the available content features of items (Pazzani and Billsus [2007], Ferwerda et al. [2012], Cramer et al.”
• Neural Input Search for Large Scale Recommendation Models (2019, background): “For large scale recommendation problems, great results have also been reported by leveraging advanced representation learning components, such as CNN ([10], [18]), RNN ([1], [8]), etc.”
• Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks (2018, methodology): “With the revival of neural networks, many studies try to adapt powerful sequential neural models, i.e., Recurrent Neural Networks (RNN), to sequential recommendation [35], including session-based RNN [15], user-based RNN [5] and attention-based RNN [18].”
• A Survey on Session-based Recommender Systems (2019, positive): “In Reference [20], the authors designed a unique user-based GRU model that incorporates user characteristic to generalize personalized next item recommendations.”
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer (2019, background): “7https://github.com/hexiangnan/neural_collaborative_filtering 8https://github.com/hidasib/GRU4Rec 9https://github.com/graytowne/caser_pytorch 10https://github.com/kang205/SASRec We implement BERT4Rec11 with TensorFlow.”
• Dynamic Explainable Recommendation Based on Neural Attentive Models (2019, methodology): “…to capture user multi-step behaviors based on the recurrent neural network (RNN) (Yu et al. 2016; Hidasi et al. 2016; Tan, Xu, and Liu 2016; Donkers, Loepp, and Ziegler 2017; Liu et al. 2016; Song, Elkahky, and He 2016), the convolutional neural network (CNN) (Tang and Wang 2018) or the…”
• Recommendation system based on deep learning methods: a systematic review and new directions (2019, methodology): “Unlike session-based RS where user-identifiers are not used, in this review, we also identified several studies that use RNN model with known user identifications (Christako-poulou et al. 2018; Wu et al. 2017; Donkers et al. 2017) for RS.”
• Contrastive Learning for Sequential Recommendation (2022, methodology): “With the recent advance of deep learning, Recurrent Neural Networks (RNN) [6], and its variants, such as Long Short-Term Memory (LSTM) [20], and Gated Recurrent Unit (GRU) [11, 19], are applied for user behavior sequences.”
• TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation (2023, methodology): “Moving forward, we plan to explore more efficient methods to activate the recommendation ability of larger models and tune LLMs to handle multiple recommendation tasks simultaneously.”
• In2Rec: Influence-based Interpretable Recommendation (2019, background): “Recently, due to the powerful ability in representation learning, deep learning is adopted in recommendation to model textual content and generate the explanations [7–9 , 29].”
• Deep Learning Based Recommender System (2017, methodology): “Sequential Information w/t User ID [16, 29, 33, 35, 73, 91, 118, 134, 144, 161, 174, 176, 190, 195, 199, 206]”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “…Recommender Networks (RRN) is one of the Recurrent neural networks to capture temporal evolution ARSE [153],RRN [204] [205], [206], [207], [208], [209] Memory network based models NMRN [210], MANN [211], STAMP [212] Sequential Models RNN based models that rely on sessions to construct input and…”
• A survey on sentiment analysis methods, applications, and challenges (2022, background): “Variants of RNN (Pham and Le-Hong 2017) like LSTM (Bandara et al. 2020), GRU (Cheng et al. 2020), Bi-LSTM (Abid et al. 2019; Cho and Lee 2019) have been used extensively in Sentiment analysis and related NLP task (Abid et al. 2019; Khan et al. 2016).”