New Activation Function Improves Robustness and Interpretability in Machine Learning Models
Researchers have introduced the Similarity-Distance-Magnitude (SDM) activation function, an improved alternative to the standard softmax function that adds awareness of prediction similarity and distance from training data. The SDM function has been accepted to ACL 2026 and shows enhanced robustness to out-of-distribution inputs when applied to pre-trained language models. This advancement could improve the reliability and interpretability of machine learning systems, particularly in applications requiring selective classification.
A new activation function called Similarity-Distance-Magnitude (SDM) has been developed to address limitations in the widely-used softmax activation function. Beyond the existing magnitude awareness (decision-boundary information), SDM adds two new dimensions: similarity awareness (tracking correctly predicted depth-matches in training data) and distance-to-training-distribution awareness. The researchers also introduced an SDM estimator that uses data-driven partitioning of class-wise empirical cumulative distribution functions to control prediction accuracy. When applied as a final-layer activation in pre-trained language models for selective classification tasks, the SDM approach demonstrates greater robustness to covariate shifts and out-of-distribution inputs compared to existing calibration methods, while maintaining informativeness on in-distribution data. The work has been accepted to the Findings of the Association for Computational Linguistics at ACL 2026.
What's missing
The arXiv admin note indicates substantial text overlap with arXiv:2502.20167, suggesting this may be a related or revised submission; the relationship between these papers and whether they represent duplicate work is not clarified in the provided abstract.
What different sources said
- arXiv cs.LGCenter
Similarity-Distance-Magnitude Activations
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.