Machine Learning

Product Manifold Representations for Learning on Biological Pathways
Machine learning models that embed graphs in non-Euclidean spaces have shown substantial benefits in a variety of contexts, but their …
Daniel McNeela, Frederic Sala, Anthony Gitter
PDF Cite Project URL
Product Manifold Representations for Learning on Biological Pathways
GROG - Reducing LLM Hallucinations for Improved Legal Reasoning
In this work we introduce Graph Retrieval-Optimized Generation (GROG), a method for reducing LLM hallucinations in contexts where …
Daniel McNeela
PDF Cite URL
GROG - Reducing LLM Hallucinations for Improved Legal Reasoning
Almost Equivariance via Lie Algebra Convolutions
Recently, the equivariance of models with respect to a group action has become an important topic of research in machine learning. …
Daniel McNeela
PDF Cite URL
Almost Equivariance via Lie Algebra Convolutions