GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems

By Yishi Xu, Yingxue Zhang, Wei Guo, Huifeng Guo, Ruiming Tang, Mark J. Coates. 2020

110 citations recorded by the source corpus.

Given the convenience of collecting information through online services, recommender systems now consume large scale data and play a more important role in improving user experience. With the recent emergence of Graph Neural Networks (GNNs), GNN-based recommender models have shown the advantage of modeling the recommender system as a user-item bipartite graph to learn representations of users and items. However, such models are expensive to train and difficult to perform frequent updates to provide the most up-to-date recommendations. In this work, we propose to update GNN-based recommender models incrementally so that the computation time can be greatly reduced and models can be updated more frequently. We develop a Graph Structure Aware Incremental Learning framework, GraphSAIL, to address the commonly experienced catastrophic forgetting problem that occurs when training a model in an incremental fashion. Our approach preserves a user's long-term preference (or an item's long-term property) during incremental model updating. GraphSAIL implements a graph structure preservation strategy which explicitly preserves each node's local structure, global structure, and self-information, respectively. We argue that our incremental training framework is the first attempt tailored for GNN based recommender systems and demonstrate its improvement compared to other incremental learning techniques on two public datasets. We further verify the effectiveness of our framework on a large-scale industrial dataset.

Subfields: Artificial Intelligence, 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. Fei Sun
2. Jaewoo Kang
3. Bin Cui
4. Scott Sanner
5. Zheda Mai
6. Dacheng Tao
7. David Quispe
8. Hyunwoo J. Kim

In Information Systems

1. Fei Sun
2. Jaewoo Kang
3. Bin Cui
4. Scott Sanner
5. Shiwen Wu
6. Fei Sun
7. Hongzhi Yin
8. Charu C. Aggarwal

Citations in the corpus

• Online Continual Learning in Image Classification: An Empirical Survey (2021, methodology): “Recommender systems have also started to adopt CL [146, 147, 148, 149].”
• CGLB: Benchmark Tasks for Continual Graph Learning (2022, background): “Recently, continual graph learning (CGL) is attracting significant amount of attention from the community due to its practical importance [47, 55, 10, 27, 1, 7, 46].”
• Graph Neural Networks in Recommender Systems: A Survey (2020, methodology): “App recommendation has also attempted to utilize GNN-basedmodels, e.g., GraphSAIL is deployed in the recommender system of a mainstream App Store, which selects several hundred apps from the universal set for each user [188].”
• DyGRAIN: An Incremental Learning Framework for Dynamic Graphs (2022, methodology): “GraphSAIL [ Xu et al. , 2020 ] proposed the online learning framework for dynamic user preferences, but it is limited to recommender systems and catastrophic forgetting.”