FADTI: Fourier and Attention-Based Diffusion Model for Multivariate Time Series Imputation
Researchers have proposed FADTI, a diffusion-based machine learning framework that uses Fourier frequency analysis and attention mechanisms to fill in missing values in multivariate time series data. Existing transformer- and diffusion-based models struggle with structured missing patterns and distribution shifts due to a lack of frequency awareness. FADTI addresses these gaps and demonstrates consistent improvements over state-of-the-art methods, particularly when data is heavily incomplete.
FADTI (Fourier and Attention Driven Diffusion for Time Series Imputation) is a new framework designed to handle missing values in multivariate time series, a common challenge in domains such as healthcare, traffic forecasting, and biological modeling. The core innovation is a learnable Fourier Bias Projection (FBP) module that injects frequency-domain inductive bias into the generative imputation process, supporting multiple spectral bases to adaptively encode both stationary and non-stationary temporal patterns. This is combined with self-attention and gated convolution for temporal modeling. The authors evaluated FADTI on multiple established benchmarks as well as a newly introduced biological time series dataset, finding that it consistently outperforms existing state-of-the-art approaches, with the advantage most pronounced under high missing-data rates. The paper, submitted to IEEE for possible publication, is accompanied by publicly available code. The work represents an incremental but targeted advance over prior diffusion and transformer models by explicitly addressing their lack of spectral inductive bias.
What's missing
The preprint has not yet undergone peer review, as it is submitted to IEEE but not yet accepted. The paper does not report statistical significance tests or confidence intervals for benchmark comparisons, making it difficult to assess whether performance gains are robust.
What different sources said
- arXiv cs.AICenter
FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
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.