# Actively learning a Bayesian matrix fusion model with deep side information

arXiv: https://arxiv.org/abs/2306.05331 · HTML: https://mlsanity.com/paper/2306.05331/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Active Learning with Label Comparisons](https://mlsanity.com/paper/2204.04670/) (2022)
- [Incorporating Side Information in Probabilistic Matrix Factorization with Gaussian Processes](https://mlsanity.com/paper/1408.2039/) (2014)
- [Active Matrix Factorization for Surveys](https://mlsanity.com/paper/1902.07634/) (2019)

## Built on by (most cited first, 1 of 1)

- [Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition](https://mlsanity.com/paper/2602.19385/) (2026)

## Abstract (arXiv)

High-dimensional deep neural network representations of images and concepts can be aligned to predict human annotations of diverse stimuli. However, such alignment requires the costly collection of behavioral responses, such that, in practice, the deep-feature spaces are only ever sparsely sampled. Here, we propose an active learning approach to adaptively sampling experimental stimuli to efficiently learn a Bayesian matrix factorization model with deep side information. We observe a significant efficiency gain over a passive baseline. Furthermore, with a sequential batched sampling strategy, the algorithm is applicable not only to small datasets collected from traditional laboratory experiments but also to settings where large-scale crowdsourced data collection is needed to accurately align the high-dimensional deep feature representations derived from pre-trained networks.