Bias-aware Boolean Matrix Factorization Using Disentangled Representation Learning

Xiao Wang, Jia Wang, Tong Zhao, Yijie Wang, Nan Zhang, Yong Zang, Sha Cao, Chi Zhang
Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, PMLR 244:3630-3642, 2024.

Abstract

Boolean matrix factorization (BMF) has been widely utilized in fields such as recommendation systems, graph learning, text mining, and -omics data analysis. Traditional BMF methods decompose a binary matrix into the Boolean product of two lower-rank Boolean matrices plus homoscedastic random errors. However, real-world binary data typically involves biases arising from heterogeneous row- and column-wise signal distributions. Such biases can lead to suboptimal fitting and unexplainable predictions if not accounted for. In this study, we reconceptualize the binary data generation as the Boolean sum of three components: a binary pattern matrix, a background bias matrix influenced by heterogeneous row or column distributions, and random flipping errors. We introduce a novel Disentangled Representation Learning for Binary matrices (DRLB) method, which employs a dual auto-encoder network to reveal the true patterns. DRLB can be seamlessly integrated with existing BMF techniques to facilitate bias-aware BMF. Our experiments with both synthetic and real-world datasets show that DRLB significantly enhances the precision of traditional BMF methods while offering high scalability. Moreover, the bias matrix detected by DRLB accurately reflects the inherent biases in synthetic data, and the patterns identified in the bias-corrected real-world data exhibit enhanced interpretability.

Cite this Paper

BibTeX
@InProceedings{pmlr-v244-wang24f, title = {Bias-aware Boolean Matrix Factorization Using Disentangled Representation Learning}, author = {Wang, Xiao and Wang, Jia and Zhao, Tong and Wang, Yijie and Zhang, Nan and Zang, Yong and Cao, Sha and Zhang, Chi}, booktitle = {Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence}, pages = {3630--3642}, year = {2024}, editor = {Kiyavash, Negar and Mooij, Joris M.}, volume = {244}, series = {Proceedings of Machine Learning Research}, month = {15--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v244/main/assets/wang24f/wang24f.pdf}, url = {https://proceedings.mlr.press/v244/wang24f.html}, abstract = {Boolean matrix factorization (BMF) has been widely utilized in fields such as recommendation systems, graph learning, text mining, and -omics data analysis. Traditional BMF methods decompose a binary matrix into the Boolean product of two lower-rank Boolean matrices plus homoscedastic random errors. However, real-world binary data typically involves biases arising from heterogeneous row- and column-wise signal distributions. Such biases can lead to suboptimal fitting and unexplainable predictions if not accounted for. In this study, we reconceptualize the binary data generation as the Boolean sum of three components: a binary pattern matrix, a background bias matrix influenced by heterogeneous row or column distributions, and random flipping errors. We introduce a novel Disentangled Representation Learning for Binary matrices (DRLB) method, which employs a dual auto-encoder network to reveal the true patterns. DRLB can be seamlessly integrated with existing BMF techniques to facilitate bias-aware BMF. Our experiments with both synthetic and real-world datasets show that DRLB significantly enhances the precision of traditional BMF methods while offering high scalability. Moreover, the bias matrix detected by DRLB accurately reflects the inherent biases in synthetic data, and the patterns identified in the bias-corrected real-world data exhibit enhanced interpretability.} }
Endnote
%0 Conference Paper %T Bias-aware Boolean Matrix Factorization Using Disentangled Representation Learning %A Xiao Wang %A Jia Wang %A Tong Zhao %A Yijie Wang %A Nan Zhang %A Yong Zang %A Sha Cao %A Chi Zhang %B Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2024 %E Negar Kiyavash %E Joris M. Mooij %F pmlr-v244-wang24f %I PMLR %P 3630--3642 %U https://proceedings.mlr.press/v244/wang24f.html %V 244 %X Boolean matrix factorization (BMF) has been widely utilized in fields such as recommendation systems, graph learning, text mining, and -omics data analysis. Traditional BMF methods decompose a binary matrix into the Boolean product of two lower-rank Boolean matrices plus homoscedastic random errors. However, real-world binary data typically involves biases arising from heterogeneous row- and column-wise signal distributions. Such biases can lead to suboptimal fitting and unexplainable predictions if not accounted for. In this study, we reconceptualize the binary data generation as the Boolean sum of three components: a binary pattern matrix, a background bias matrix influenced by heterogeneous row or column distributions, and random flipping errors. We introduce a novel Disentangled Representation Learning for Binary matrices (DRLB) method, which employs a dual auto-encoder network to reveal the true patterns. DRLB can be seamlessly integrated with existing BMF techniques to facilitate bias-aware BMF. Our experiments with both synthetic and real-world datasets show that DRLB significantly enhances the precision of traditional BMF methods while offering high scalability. Moreover, the bias matrix detected by DRLB accurately reflects the inherent biases in synthetic data, and the patterns identified in the bias-corrected real-world data exhibit enhanced interpretability.
APA
Wang, X., Wang, J., Zhao, T., Wang, Y., Zhang, N., Zang, Y., Cao, S. & Zhang, C.. (2024). Bias-aware Boolean Matrix Factorization Using Disentangled Representation Learning. Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 244:3630-3642 Available from https://proceedings.mlr.press/v244/wang24f.html.

Related Material