Hierarchical Graph Neural Network with Cross-Attention for Cross-Device User Matching
This addresses the problem of linking devices belonging to the same person for applications like advertising and cybersecurity, representing an incremental improvement.
The paper tackles cross-device user matching by proposing a hierarchical graph neural network with a cross-attention mechanism, achieving a 5% performance improvement over the state-of-the-art TGCE method.
Cross-device user matching is a critical problem in numerous domains, including advertising, recommender systems, and cybersecurity. It involves identifying and linking different devices belonging to the same person, utilizing sequence logs. Previous data mining techniques have struggled to address the long-range dependencies and higher-order connections between the logs. Recently, researchers have modeled this problem as a graph problem and proposed a two-tier graph contextual embedding (TGCE) neural network architecture, which outperforms previous methods. In this paper, we propose a novel hierarchical graph neural network architecture (HGNN), which has a more computationally efficient second level design than TGCE. Furthermore, we introduce a cross-attention (Cross-Att) mechanism in our model, which improves performance by 5% compared to the state-of-the-art TGCE method.