Heterogeneous graph
We propose AcuGRL, a graph representation learning-based framework that models the relationships between acupoints and disease phenotypes as a heterogeneous graph. This framework incorporates a domain knowledge-guided scheme to capture both the structural and semantic features of the network, generating effective embeddings for downstream tasks. Additionally, we integrate micro-level genetic targets with macro-level disease phenotypes to further enhance network connectivity and provide richer contextual information.
- Categories:
12 Views
eterogeneous graph representation learning is crit-
ical for analyzing complex data structures. Metapaths within this
field are vital as they elucidate high-order relationships across the
graph, significantly enhancing the model’s accuracy and depth of
understanding. However, metapaths tend to prioritize long-range
dependencies of the target node, which can lead to the oversight of
potentially crucial 1st-order heterogeneous neighbors or short-
range dependencies. To address this challenge and circumvent
- Categories:
36 Views