2026-01-22 東京大学,京都大学
テンソルツリー生成モデルによる因果構造の推定
＜関連情報＞
- https://www.issp.u-tokyo.ac.jp/maincontents/news2.html?pid=29696
- https://www.issp.u-tokyo.ac.jp/news/wp-content/uploads/2026/01/press_0121_tensor-tree.pdf
- https://iopscience.iop.org/article/10.1088/2632-2153/ae3048
解釈可能な生成モデリングのための塑性テンソルネットワーク Plastic tensor networks for interpretable generative modeling
Katsuya O Akamatsu, Kenji Harada, Tsuyoshi Okubo and Naoki Kawashima
Machine Learning: Science and Technology Published: 21 January 2026
DOI:10.1088/2632-2153/ae3048
Abstract
A structural optimization scheme for a single-layer nonnegative adaptive tensor tree (NATT) that models a target probability distribution is proposed as an alternative paradigm for generative modeling. The NATT scheme, by construction, automatically searches for a tree structure that best fits a given discrete dataset whose features serve as inputs, and has the advantage that it is interpretable as a probabilistic graphical model. We consider the NATT scheme and a recently proposed Born machine ATT optimization scheme and demonstrate their effectiveness on a variety of generative modeling tasks where the objective is to infer the hidden structure of a provided dataset. Our results show that in terms of minimizing the negative log-likelihood, the single-layer scheme has model performance comparable to the Born machine scheme, though not better. The tasks include deducing the structure of binary bitwise operations, learning the internal structure of random Bayesian networks given only visible sites, and a real-world example related to hierarchical clustering where a cladogram is constructed from mitochondrial DNA sequences. In doing so, we also show the importance of the choice of network topology and the versatility of a least-mutual information criterion in selecting a candidate structure for a tensor tree, as well as discuss aspects of these tensor tree generative models including their information content and interpretability.
