Related papers: Instant Representation Learning for Recommendation over Large Dynamic Graphs

Instant Representation Learning for Recommendation over Large Dynamic Graphs

URL: http://arxiv.org/abs/2305.18622v1
Date: Mon, 22 May 2023 15:36:10 GMT
Title: Instant Representation Learning for Recommendation over Large Dynamic Graphs
Authors: Cheng Wu, Chaokun Wang, Jingcao Xu, Ziwei Fang, Tiankai Gu, Changping Wang, Yang Song, Kai Zheng, Xiaowei Wang, Guorui Zhou
Abstract summary: We propose SUPA, a novel graph neural network for dynamic multiplex heterogeneous graphs. For each new edge, SUPA samples an influenced subgraph, updates the representations of the two interactive nodes, and propagates the interaction information to the sampled subgraph. To train SUPA incrementally online, we propose InsLearn, an efficient workflow for single-pass training of large dynamic graphs.
Score: 29.41179019520622
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Recommender systems are able to learn user preferences based on user and item representations via their historical behaviors. To improve representation learning, recent recommendation models start leveraging information from various behavior types exhibited by users. In real-world scenarios, the user behavioral graph is not only multiplex but also dynamic, i.e., the graph evolves rapidly over time, with various types of nodes and edges added or deleted, which causes the Neighborhood Disturbance. Nevertheless, most existing methods neglect such streaming dynamics and thus need to be retrained once the graph has significantly evolved, making them unsuitable in the online learning environment. Furthermore, the Neighborhood Disturbance existing in dynamic graphs deteriorates the performance of neighbor-aggregation based graph models. To this end, we propose SUPA, a novel graph neural network for dynamic multiplex heterogeneous graphs. Compared to neighbor-aggregation architecture, SUPA develops a sample-update-propagate architecture to alleviate neighborhood disturbance. Specifically, for each new edge, SUPA samples an influenced subgraph, updates the representations of the two interactive nodes, and propagates the interaction information to the sampled subgraph. Furthermore, to train SUPA incrementally online, we propose InsLearn, an efficient workflow for single-pass training of large dynamic graphs. Extensive experimental results on six real-world datasets show that SUPA has a good generalization ability and is superior to sixteen state-of-the-art baseline methods. The source code is available at https://github.com/shatter15/SUPA.