Memory Augmented Neural Model for Incremental Session-based Recommendation
2020
28 citations recorded by the source corpus.
Increasing concerns with privacy have stimulated interests in Session-based Recommendation (SR) using no personal data other than what is observed in the current browser session. Existing methods are evaluated in static settings which rarely occur in real-world applications. To better address the dynamic nature of SR tasks, we study an incremental SR scenario, where new items and preferences appear continuously. We show that existing neural recommenders can be used in incremental SR scenarios with small incremental updates to alleviate computation overhead and catastrophic forgetting. More importantly, we propose a general framework called Memory Augmented Neural model (MAN). MAN augments a base neural recommender with a continuously queried and updated nonparametric memory, and the predictions from the neural and the memory components are combined through another lightweight gating network. We empirically show that MAN is well-suited for the incremental SR task, and it consistently outperforms state-oft-he-art neural and nonparametric methods. We analyze the results and demonstrate that it is particularly good at incrementally learning preferences on new and infrequent items.
Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research
Citations in the corpus
- Online Continual Learning in Image Classification: An Empirical Survey (2021, background): “Recommender systems have also started to adopt CL [146, 147, 148, 149].”
- CLEAR: Contrastive-Prototype Learning with Drift Estimation for Resource Constrained Stream Mining (2021, background): “Predicting labels for a large number of instances occurring continuously in the stream setting is a crucial problem in many real-world applications, such as online product classification in e-commerce systems that incrementally classify new products by their images [27, 47]; online tweets/news summa”
- A Survey on Session-based Recommender Systems (2019, methodology): “Memory Long, incremental or noisy sessions Dynamically store the latest information Cannot capture sequential information [15],[67],[89], [96],[112]”
- ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation (2020, background): “Recently, the incremental and steaming nature of SR is pointed out by [9, 27].”