Search Results for author:
Found 5 papers, 4 papers with code
Diet-ODIN: A Novel Framework for Opioid Misuse Detection with Interpretable Dietary Patterns
The opioid crisis has been one of the most critical society concerns in the United States.
Graph Inference Acceleration by Learning MLPs on Graphs without Supervision
Graph Neural Networks (GNNs) have demonstrated effectiveness in various graph learning tasks, yet their reliance on message-passing constraints their deployment in latency-sensitive applications such as financial fraud detection.
Tackling Negative Transfer on Graphs
To mitigate this, we bring a new insight: for semantically similar graphs, although structural differences lead to significant distribution shift in node embeddings, their impact on subgraph embeddings could be marginal.
TPGNN: Learning High-order Information in Dynamic Graphs via Temporal Propagation
We argue that when learning high-order information from temporal graphs, we encounter two challenges, i. e., computational inefficiency and over-smoothing, that cannot be solved by conventional techniques applied on static graphs.
Heterogeneous Graph Contrastive Multi-view Learning
How to mitigate the sampling bias for heterogeneous GCL is another important problem.
