Spectra-Guided Neural Tucker Factorization
For practitioners dealing with high-dimensional tensor completion, SG-NTF offers a parameter-efficient method that maintains accuracy, though it is an incremental improvement over existing approaches.
SG-NTF tackles high-dimensional incomplete tensor completion by mapping timestamps to a continuous spectral space and using a spatio-temporal co-gating mechanism. It achieves competitive completion accuracy with parameter efficiency on real-world datasets.
This paper proposes Spectra-Guided Neural Tucker Factorization (SG-NTF) for High-Dimensional and Incomplete (HDI) tensor completion. Circumventing discrete representational limits, SG-NTF maps scalar timestamps into a continuous spectral space to abstract temporal periodicities. Concurrently, a Spatio-Temporal Co-Gating (STCG) mechanism explicitly filters latent interactions via multiplicative modulation on spatiotemporal contexts. Evaluations on real-world HDI tensors verify that SG-NTF maintains competitive completion accuracy with parameter efficiency.