Meta-learning from Heterogeneous Tensors for Few-shot Tensor Completion

Tomoharu Iwata, Atsutoshi Kumagai
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:3007-3015, 2025.

Abstract

We propose neural network-based models for tensor completion in few observation settings. The proposed model can meta-learn inductive bias from multiple heterogeneous tensors without shared modes. Although many tensor completion methods have been proposed, the existing methods cannot leverage knowledge across heterogeneous tensors, and their performance is low when only a small number of elements are observed. The proposed model encodes each element of a given tensor by considering information about other elements while reflecting the tensor structure via a self-attention mechanism. The missing values are predicted by tensor-specific linear projection from the encoded vectors. The proposed model is shared across different tensors, and it is meta-learned such that the expected tensor completion performance is improved using multiple tensors. By experiments using synthetic and real-world tensors, we demonstrate that the proposed method achieves better performance than the existing meta-learning and tensor completion methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-iwata25a, title = {Meta-learning from Heterogeneous Tensors for Few-shot Tensor Completion}, author = {Iwata, Tomoharu and Kumagai, Atsutoshi}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {3007--3015}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/iwata25a/iwata25a.pdf}, url = {https://proceedings.mlr.press/v258/iwata25a.html}, abstract = {We propose neural network-based models for tensor completion in few observation settings. The proposed model can meta-learn inductive bias from multiple heterogeneous tensors without shared modes. Although many tensor completion methods have been proposed, the existing methods cannot leverage knowledge across heterogeneous tensors, and their performance is low when only a small number of elements are observed. The proposed model encodes each element of a given tensor by considering information about other elements while reflecting the tensor structure via a self-attention mechanism. The missing values are predicted by tensor-specific linear projection from the encoded vectors. The proposed model is shared across different tensors, and it is meta-learned such that the expected tensor completion performance is improved using multiple tensors. By experiments using synthetic and real-world tensors, we demonstrate that the proposed method achieves better performance than the existing meta-learning and tensor completion methods.} }
Endnote
%0 Conference Paper %T Meta-learning from Heterogeneous Tensors for Few-shot Tensor Completion %A Tomoharu Iwata %A Atsutoshi Kumagai %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-iwata25a %I PMLR %P 3007--3015 %U https://proceedings.mlr.press/v258/iwata25a.html %V 258 %X We propose neural network-based models for tensor completion in few observation settings. The proposed model can meta-learn inductive bias from multiple heterogeneous tensors without shared modes. Although many tensor completion methods have been proposed, the existing methods cannot leverage knowledge across heterogeneous tensors, and their performance is low when only a small number of elements are observed. The proposed model encodes each element of a given tensor by considering information about other elements while reflecting the tensor structure via a self-attention mechanism. The missing values are predicted by tensor-specific linear projection from the encoded vectors. The proposed model is shared across different tensors, and it is meta-learned such that the expected tensor completion performance is improved using multiple tensors. By experiments using synthetic and real-world tensors, we demonstrate that the proposed method achieves better performance than the existing meta-learning and tensor completion methods.
APA
Iwata, T. & Kumagai, A.. (2025). Meta-learning from Heterogeneous Tensors for Few-shot Tensor Completion. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:3007-3015 Available from https://proceedings.mlr.press/v258/iwata25a.html.

Related Material