LoTUS: New Machine Unlearning Method Removes Training Data Influence Without Full Retraining
Researchers have developed LoTUS, a machine unlearning technique that removes the influence of specific training samples from pre-trained AI models without requiring complete retraining from scratch. The method works by smoothing prediction probabilities to an information-theoretic bound, addressing over-confidence caused by data memorization. This approach is significant because it enables practical data removal at scale, particularly for large datasets like ImageNet1k where full retraining would be computationally prohibitive.
LoTUS is a novel machine unlearning method designed to eliminate the influence of training samples from pre-trained models while avoiding the computational expense of retraining from scratch. The technique smooths prediction probabilities up to an information-theoretic bound to mitigate over-confidence stemming from data memorization. The researchers evaluated LoTUS on Transformer and ResNet18 models against eight baseline methods across five public datasets, and notably tested it on ImageNet1k, a large-scale dataset where retraining is impractical. To enable evaluation under real-world conditions, the team introduced the Retrain-Free Jensen-Shannon Divergence (RF-JSD) metric. Experimental results demonstrate that LoTUS outperforms state-of-the-art methods in both efficiency and effectiveness. The work has been accepted as a main conference paper at CVPR 2025.
What different sources said
- arXiv cs.AICenter
Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.