Unsupervised Recognition of Informative Features via Tensor Network Machine Learning and Quantum Entanglement Variations
This work addresses the challenge of interpreting feature importance in unsupervised learning for applications like image segmentation and object detection, though it appears incremental by combining existing quantum-inspired methods with new measurements.
The paper tackles the problem of unsupervised recognition of informative features in images, such as identifying white pixels in a 'white shoe' image, by proposing a scheme using tensor network machine learning and quantum entanglement variations, and tests it on toy, MNIST, fashion-MNIST, and brain cell datasets.
Given an image of a white shoe drawn on a blackboard, how are the white pixels deemed (say by human minds) to be informative for recognizing the shoe without any labeling information on the pixels? Here we investigate such a ``white shoe'' recognition problem from the perspective of tensor network (TN) machine learning and quantum entanglement. Utilizing a generative TN that captures the probability distribution of the features as quantum amplitudes, we propose an unsupervised recognition scheme of informative features with the variations of entanglement entropy (EE) caused by designed measurements. In this way, a given sample, where the values of its features are statistically meaningless, is mapped to the variations of EE that statistically characterize the gain of information. We show that the EE variations identify the features that are critical to recognize this specific sample, and the EE itself reveals the information distribution of the probabilities represented by the TN model. The signs of the variations further reveal the entanglement structures among the features. We test the validity of our scheme on a toy dataset of strip images, the MNIST dataset of hand-drawn digits, the fashion-MNIST dataset of the pictures of fashion articles, and the images of brain cells. Our scheme opens the avenue to the quantum-inspired and interpreted unsupervised learning, which can be applied to, e.g., image segmentation and object detection.