Differentiable Convex Optimization Layers in Neural Architectures: Foundations and Perspectives
This ~15 page paper on convex differentiable optimization layers in neural architecture was submitted as a final project for S&DS431 at Yale.
Dec 30, 2024
Attention-Driven Metapath Encoding in Heterogeneous Graphs
In this paper, I propose and implement a novel heterogeneous graph neural network architecture for CPSC483 at Yale. The model implements an original attention-based mechanism to extract features from semantically meaningful relations (“metapaths”) inside a graph. I derive key results and conduct extensive testing of the model, documenting it in the detailed report.
Dec 30, 2024