iLoRA is the first Bayesian graph-conditioned LoRA framework that infers latent interaction graphs to generate input-dependent low-rank updates, jointly learning predictions and structure for microbiome diagnosis.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
iLoRA is the first Bayesian graph-conditioned LoRA framework that infers latent interaction graphs to generate input-dependent low-rank updates, jointly learning predictions and structure for microbiome diagnosis.