Tag: Knowledge and Information Systems

A new framework discretizes time-series data and splits it between global rule-based and Transformer-based local detectors, reporting higher F1 scores ...

A new method called CEGDSR combines global and disentangled intent-aware representations to improve sequential recommendation, outperforming several strong baselines on ...

A new review in Knowledge and Information Systems synthesizes a decade of anomaly detection research across images, videos, and compressed ...

A new hybrid architecture combining graph convolutions with a lite capsule network delivers an average 9.1 percent improvement in link ...

Researchers have developed a conceptual and logical modeling methodology that treats measures, granularity hierarchies, and business-process states as explicit constructs, ...

Researchers at Central South University have developed a cluster-based domain adaptation method that aligns only semantically similar portions of source ...

A new neuro-symbolic framework called Delta Semantics keeps machine learning outputs provably consistent with evolving ontologies by attaching checker-validated proof ...

A new shapelet-based soft contrastive learning framework called SCLS improves multivariate time series clustering by avoiding noisy data augmentation and ...

Researchers in China have developed CADEE, an online ensemble learning framework that simultaneously handles multi-class imbalance, concept drift, and limited ...

Researchers have developed BHyGNN+, a self-supervised framework that learns representations of heterophilic hypergraphs without labels by contrasting each hypergraph against ...