recommender systems

NMKFR: A Robust Framework for Time-Aware Cold-Start Recommendation

arXiv:2607.26429

summary

The paper introduces NMKFR, a neural framework that fuses semantic text encoding with time-aware Kalman state tracking to improve recommendation of new items under changing temporal conditions, using uncertainty estimates to adaptively combine static and temporal signals.

Abstract

Item cold-start recommendation is difficult when new items have sparse early interactions and appear in recommendation environments that keep changing over time. Static content, early feedback, and temporal-state evidence are all useful, but their reliability varies across the item lifecycle. This work proposes a framework--Neural Memory Kalman Fusion Recommender (NMKFR), which combines a Titans-based semantic encoder with time-aware Kalman state tracking. The semantic branch extracts memory-enhanced item observations from text, while the temporal branch estimates latent states under irregular interaction intervals. The NMKFR further uses posterior covariance as an uncertainty signal to calibrate semantic memory retrieval and adaptive static-temporal fusion. Experiments on Amazon Video Games and MovieLens-32M evaluate NMKFR under time-aware and item cold-start protocols using sampled candidate ranking. Across the reported comparisons, ablations, diagnostics, and robustness analyses, NMKFR achieves the strongest retained results and exhibits bounded uncertainty-related internal behavior. These findings provide empirical evidence for posterior-covariance-guided semantic-temporal fusion under the evaluated offline settings.

9 pages, 6 figures

Topics & keywords

#cold-start recommendation#time-aware recommendation#semantic encoding#Kalman filter#uncertainty estimationNeural Memory Kalman Fusion Recommendersemantic encoderKalman state trackingposterior covarianceitem cold-starttemporal dynamics