Neural FIM for learning Fisher information metrics from point cloud data

Oluwadamilola Fasina, Guillaume Huguet, Alexander Tong, Yanlei Zhang, Guy Wolf, Maximilian Nickel, Ian Adelstein, Smita Krishnaswamy
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9814-9826, 2023.

Abstract

Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the underlying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature. To this end, we propose neural FIM, a method for computing the Fisher information metric (FIM) from point cloud data - allowing for a continuous manifold model for the data. Neural FIM creates an extensible metric space from discrete point cloud data such that information from the metric can inform us of manifold characteristics such as volume and geodesics. We demonstrate Neural FIM’s utility in selecting parameters for the PHATE visualization method as well as its ability to obtain information pertaining to local volume illuminating branching points and cluster centers embeddings of a toy dataset and two single-cell datasets of IPSC reprogramming and PBMCs (immune cells).

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-fasina23a, title = {Neural {FIM} for learning {F}isher information metrics from point cloud data}, author = {Fasina, Oluwadamilola and Huguet, Guillaume and Tong, Alexander and Zhang, Yanlei and Wolf, Guy and Nickel, Maximilian and Adelstein, Ian and Krishnaswamy, Smita}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {9814--9826}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/fasina23a/fasina23a.pdf}, url = {https://proceedings.mlr.press/v202/fasina23a.html}, abstract = {Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the underlying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature. To this end, we propose neural FIM, a method for computing the Fisher information metric (FIM) from point cloud data - allowing for a continuous manifold model for the data. Neural FIM creates an extensible metric space from discrete point cloud data such that information from the metric can inform us of manifold characteristics such as volume and geodesics. We demonstrate Neural FIM’s utility in selecting parameters for the PHATE visualization method as well as its ability to obtain information pertaining to local volume illuminating branching points and cluster centers embeddings of a toy dataset and two single-cell datasets of IPSC reprogramming and PBMCs (immune cells).} }
Endnote
%0 Conference Paper %T Neural FIM for learning Fisher information metrics from point cloud data %A Oluwadamilola Fasina %A Guillaume Huguet %A Alexander Tong %A Yanlei Zhang %A Guy Wolf %A Maximilian Nickel %A Ian Adelstein %A Smita Krishnaswamy %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-fasina23a %I PMLR %P 9814--9826 %U https://proceedings.mlr.press/v202/fasina23a.html %V 202 %X Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the underlying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature. To this end, we propose neural FIM, a method for computing the Fisher information metric (FIM) from point cloud data - allowing for a continuous manifold model for the data. Neural FIM creates an extensible metric space from discrete point cloud data such that information from the metric can inform us of manifold characteristics such as volume and geodesics. We demonstrate Neural FIM’s utility in selecting parameters for the PHATE visualization method as well as its ability to obtain information pertaining to local volume illuminating branching points and cluster centers embeddings of a toy dataset and two single-cell datasets of IPSC reprogramming and PBMCs (immune cells).
APA
Fasina, O., Huguet, G., Tong, A., Zhang, Y., Wolf, G., Nickel, M., Adelstein, I. & Krishnaswamy, S.. (2023). Neural FIM for learning Fisher information metrics from point cloud data. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:9814-9826 Available from https://proceedings.mlr.press/v202/fasina23a.html.

Related Material