Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2606.00584 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917550232698880 |
|---|---|
| author | Wang, Fusheng Hou, Yikai |
| author_facet | Wang, Fusheng Hou, Yikai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00584 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Spectra-Guided Neural Tucker Factorization Wang, Fusheng Hou, Yikai Machine Learning 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. |
| title | Spectra-Guided Neural Tucker Factorization |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2606.00584 |