Researchers Achieve Major Performance Improvements in NeurASP Neurosymbolic AI Framework
A new implementation of NeurASP, a neurosymbolic AI framework combining neural networks with answer set programming, achieves speedups of multiple orders of magnitude for larger tasks through vectorization, batch processing, and caching. NeurASP trains neural networks to predict concepts and reasons over them using symbolic rules, but its reliance on a non-differentiable component has historically made training computationally expensive. The improvements could significantly expand the practical applicability of neurosymbolic AI to more complex, real-world problems.
Neurosymbolic AI frameworks like NeurASP aim to combine the pattern-recognition strengths of neural networks with the interpretability and reasoning capabilities of symbolic programs. NeurASP specifically uses answer set programming (ASP) to reason over neural network outputs, with supervision provided only at the level of downstream task predictions rather than intermediate concepts. However, backpropagating through the non-differentiable ASP component requires costly probability and gradient calculations, limiting scalability. The new implementation addresses these bottlenecks via vectorization, batch processing, and caching of intermediate computations during training. Benchmarks comparing the original and new implementations show speedups of multiple orders of magnitude on larger tasks. To rigorously evaluate the enhanced system, the authors also introduce a new dataset of difficult playing-card-based tasks. The work is accepted for publication in the Theory and Practice of Logic Programming journal as part of the 42nd International Conference on Logic Programming proceedings.
What's missing
It is unclear whether the speedups generalize beyond the playing-card dataset to other established NeurASP benchmarks, or whether the caching strategy introduces memory trade-offs that could limit applicability on resource-constrained hardware.
What different sources said
- arXiv cs.AICenter
Accelerating NeurASP with vectorization and caching
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.