2 papers
cs.CL2024
Aligned at the Start: Conceptual Groupings in LLM Embeddings
Mehrdad Khatir, Sanchit Kabra, Chandan K. Reddy
This paper shifts focus to the often-overlooked input embeddings - the initial representations fed into transformer blocks. Using fuzzy graph, k-nearest neighbor (k-NN), and commun…
cs.LG2022
A Unification Framework for Euclidean and Hyperbolic Graph Neural Networks
Mehrdad Khatir, Nurendra Choudhary, Sutanay Choudhury +2
Hyperbolic neural networks can effectively capture the inherent hierarchy of graph datasets, and consequently a powerful choice of GNNs. However, they entangle multiple incongruent…