# Spectra-Guided Neural Tucker Factorization

arXiv: https://arxiv.org/abs/2606.00584 · HTML: https://mlsanity.com/paper/2606.00584/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 86 references that are in the map.
- First posted on arXiv 30 May 2026.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Bayesian Temporal Factorization for Multidimensional Time Series Prediction](https://mlsanity.com/paper/1910.06366/) (2019)
- [FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data Imputation](https://mlsanity.com/paper/2410.15248/) (2024)
- [An Adaptive Alternating-direction-method-based Nonnegative Latent Factor Model](https://mlsanity.com/paper/2204.04843/) (2022)

## Abstract (arXiv)

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.