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

2026-07-28

AI Summary

This work addresses the cold-start problem of sparse interactions with new items in dynamic recommendation settings by proposing a novel approach that integrates semantic and temporal modeling. The method combines a Titans-based semantic encoder, which leverages a neural memory mechanism to extract enriched observations from textual content, with a time-aware Kalman filter that tracks the evolution of latent states under irregular interaction intervals. Innovatively, the posterior covariance is introduced as an uncertainty signal to dynamically guide semantic memory retrieval and enable adaptive fusion of static and temporal features. Experiments on Amazon Video Games and MovieLens-32M demonstrate that the proposed method significantly outperforms existing approaches, achieving high recommendation accuracy, well-calibrated internal uncertainty estimates, and strong robustness.

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.

Problem

• item cold-start
• time-aware recommendation
• sparse interactions
• temporal dynamics
• recommendation systems

Innovation

• cold-start recommendation
• Kalman filtering
• semantic-temporal fusion
• uncertainty calibration
• time-aware recommendation