article · IEEE Access
Recommender systems increasingly rely on contextual data to enhance the quality of their suggestions. Such systems commonly formulate recommendations as link prediction tasks on bipartite graphs, where nodes representing users and items are connected by edges that indicate interactions or ratings. A novel model, named Dynamic Graph Attention Network with Adaptive Edge Attributes, has been developed to process contextual recommendations through multilayer dynamic graph attention networks. The system updates representations of users and items while dynamically adapting the attributes of the edges linking them throughout the learning phase. This mechanism allows the model to capture intricate interactions influenced by context. By refining model parameters and customising edge attributes to reflect the relationships between users, items, and contextual details, the framework improves both accuracy and novelty over existing techniques across benchmark datasets.
Digital platforms depend heavily on recommender engines to guide users toward relevant products or content. Incorporating contextual factors, such as situation or timing, helps systems make more appropriate suggestions. By adapting connection features dynamically, this approach provides a more sophisticated way to understand user behaviour, leading to more accurate and diverse recommendations that better reflect shifting real-world circumstances.
The architecture targets contextual recommendation tasks, which are directly relevant to operators of e-commerce platforms, streaming services, and online marketplaces seeking improved accuracy and novel suggestions for their users. Evaluated on benchmark datasets, the technology remains at the stage of algorithm design and experimental validation. Further testing in production environments, scalability assessments, and integration with existing data pipelines would be needed before deployment in commercial platforms.
AI-generated from the published abstract. Always read the original work before citing.
Recommender systems have witnessed a great shift in leveraging contextual information as an auxiliary resource to improve the quality of the recommendations. These recommendation problems are addressed as link prediction tasks within bipartite graphs, where user and item nodes are connected by edges labeled with binary values or rating information. This paper introduces a new architecture: Dynamic Graph Attention Network with Adaptive Edge Attributes (DGAT-AEA). Comprising multiple layers of dynamic Graph Attention Networks, designed to efficiently handle contextual recommendations. Our method is distinguished by its ability to update user and item representations while adapting the attributes of the connections between them during learning. This enables the capture of complex relationships within user-item interactions using contextual information. By optimizing model parameters and adapting edge features according to the user-item-context relationship, our approach outperforms existing methods regarding recommendation accuracy and novelty, as demonstrated by experiments on benchmark datasets.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3477956
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
