Research map / Graph learning / Graph self-supervised learning
iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
Yang Song, Yixuan Zhang, Lingfa Meng, Tongyuan Hu, Haizhou Shi, Hao Wang, Samir Bhatt, Hengguan Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add iLoRA graph-conditioned LoRA vs MLE LoRA | LoRA · Molweni | F1: 72.83 -> 74.51 | Improved |
| add iLoRA vs MLE LoRA | LoRA · Molweni | EM: 57.78 -> 60.57 | Improved |
| add iLoRA vs MLE LoRA | LoRA · IBD diagnosis | AUROC: 0.7617 -> 0.7990 | Improved |
| add iLoRA vs MLE LoRA | LoRA · IBD diagnosis | ECE: 0.2533 -> 0.0980 | Improved |
| add iLoRA vs MLE LoRA | LoRA · IBD diagnosis | AUPRC: 0.7570 -> 0.7617 | No clear effect |
| add Poisson graph branch to vanilla LoRA (ablation) | LoRA · IBD diagnosis | ECE: 0.2533 -> 0.1032 | Improved |
| add Poisson graph branch without Laplace to vanilla LoRA (ablation) | LoRA · IBD diagnosis | AUROC: 0.7617 -> 0.7557 | No clear effect |
| add Laplace sparsification to Poisson graph (ablation) | iLoRA · IBD diagnosis | AUROC: 0.7557 -> 0.7990 | Improved |
| add Laplace sparsification to Poisson graph (ablation) | iLoRA · IBD diagnosis | AUPRC: 0.7440 -> 0.7617 | Improved |
| use iLoRA instead of tabular models on selected taxa | iLoRA · IBD diagnosis | AUROC: 0.6151 -> 0.7990 | Improved |
| use inferred graph instead of random graph | iLoRA · Molweni relation prediction | error rate: 50.0 -> 26.7 | Improved |
| use inferred graph instead of random graph | iLoRA · IBD relation prediction | error rate: 50.0 -> 27.3 | Improved |
Closest papers by meaning
- Whole Genome Transformer for Gene Interaction Effects in Microbiome Habitat Specificity (AAAI 2025 · similarity 0.84)
- LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation (ICLR 2025 · similarity 0.83)
- Modelling Microbial Communities with Graph Neural Networks (ICML 2024 · similarity 0.83)
- Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment (ICML 2025 · similarity 0.82)
- Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval (ICLR 2025 · similarity 0.82)
- On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference (NeurIPS 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
