Nonnegative Matrix Factorization Based Heterogeneous Graph Embedding Method for Trigger-Action Programming in IoT

Nowadays, users can personalize Internet of Things (IoT) devices/web services via trigger-action programming (TAP). As the number of connected entities grows, the relations of triggers and actions become progressively complex (i.e., the heterogeneity of TAP), which becomes a challenge for existing models to completely preserve the heterogeneous data and semantic information in trigger and action. To address this issue, in this article, we propose IoT nonnegative matrix factorization (IoT-NMF), a NMF-based heterogeneous graph embedding method for TAP. Prior to using IoT-NMF, we map triggers and actions to an IoT heterogeneous information network, from which we can extract three structures that preserve heterogeneous relations in triggers and actions. IoT-NMF can factorize the structures simultaneously for getting low-dimensional representation vectors of the triggers and actions, which can be further utilized in Artificial Intelligence of Things applications (e.g., TAP rule recommendation). Finally, we demonstrate the proposed approach using an if this then that (IFTTT) dataset. The result shows that IoT-NMF outperforms the state-of-the-art approaches.

Automated summary

In this article, a NMF-based heterogeneous graph embedding method called IoT nonnegative matrix factorization (IoT-NMF) is proposed for trigger-action programming (TAP) in Internet of Things (IoT) devices/web services. By mapping triggers and actions to an IoT heterogeneous information network, three structures that preserve heterogeneous relations are extracted, and IoT-NMF is used to simultaneously factorize these structures to obtain low-dimensional representation vectors. The proposed approach outperforms the state-of-the-art methods, as demonstrated using an if this then that (IFTTT) dataset.