On Transferring Expert Knowledge from Tabular Data to Images

Jun-Peng Jiang, Han-Jia Ye, Leye Wang, Yang Yang, Yuan Jiang, De-Chuan Zhan
Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models, PMLR 243:102-115, 2024.

Abstract

Transferring knowledge across modalities has garnered significant attention in the field of machine learning as it enables the utilization of expert knowledge from diverse domains. In particular, the representation of expert knowledge in tabular form, commonly found in fields such as medicine, can greatly enhance the comprehensiveness and accuracy of image-based learning. However, the transfer of knowledge from tabular to image data presents unique challenges due to the distinct characteristics of these data types, making it challenging to determine "how to reuse" and "which subset to reuse". To address this, we propose a novel method called CHannel tAbulaR alignment with optiMal tranSport (CHARMS) that automatically and effectively transfers relevant tabular knowledge. Specifically, by maximizing the mutual information between a group of channels and tabular features, our method modifies the visual embedding and captures the semantics of tabular knowledge. The alignment between channels and attributes helps select the subset of tabular data which contains knowledge to images. Experimental results demonstrate that {\sc Charms} effectively reuses tabular knowledge to improve the performance and interpretability of visual classifiers.

Cite this Paper


BibTeX
@InProceedings{pmlr-v243-jiang24a, title = {On Transferring Expert Knowledge from Tabular Data to Images}, author = {Jiang, Jun-Peng and Ye, Han-Jia and Wang, Leye and Yang, Yang and Jiang, Yuan and Zhan, De-Chuan}, booktitle = {Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models}, pages = {102--115}, year = {2024}, editor = {Fumero, Marco and Rodol√°, Emanuele and Domine, Clementine and Locatello, Francesco and Dziugaite, Karolina and Mathilde, Caron}, volume = {243}, series = {Proceedings of Machine Learning Research}, month = {15 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v243/jiang24a/jiang24a.pdf}, url = {https://proceedings.mlr.press/v243/jiang24a.html}, abstract = {Transferring knowledge across modalities has garnered significant attention in the field of machine learning as it enables the utilization of expert knowledge from diverse domains. In particular, the representation of expert knowledge in tabular form, commonly found in fields such as medicine, can greatly enhance the comprehensiveness and accuracy of image-based learning. However, the transfer of knowledge from tabular to image data presents unique challenges due to the distinct characteristics of these data types, making it challenging to determine "how to reuse" and "which subset to reuse". To address this, we propose a novel method called CHannel tAbulaR alignment with optiMal tranSport (CHARMS) that automatically and effectively transfers relevant tabular knowledge. Specifically, by maximizing the mutual information between a group of channels and tabular features, our method modifies the visual embedding and captures the semantics of tabular knowledge. The alignment between channels and attributes helps select the subset of tabular data which contains knowledge to images. Experimental results demonstrate that {\sc Charms} effectively reuses tabular knowledge to improve the performance and interpretability of visual classifiers.} }
Endnote
%0 Conference Paper %T On Transferring Expert Knowledge from Tabular Data to Images %A Jun-Peng Jiang %A Han-Jia Ye %A Leye Wang %A Yang Yang %A Yuan Jiang %A De-Chuan Zhan %B Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models %C Proceedings of Machine Learning Research %D 2024 %E Marco Fumero %E Emanuele Rodol√° %E Clementine Domine %E Francesco Locatello %E Karolina Dziugaite %E Caron Mathilde %F pmlr-v243-jiang24a %I PMLR %P 102--115 %U https://proceedings.mlr.press/v243/jiang24a.html %V 243 %X Transferring knowledge across modalities has garnered significant attention in the field of machine learning as it enables the utilization of expert knowledge from diverse domains. In particular, the representation of expert knowledge in tabular form, commonly found in fields such as medicine, can greatly enhance the comprehensiveness and accuracy of image-based learning. However, the transfer of knowledge from tabular to image data presents unique challenges due to the distinct characteristics of these data types, making it challenging to determine "how to reuse" and "which subset to reuse". To address this, we propose a novel method called CHannel tAbulaR alignment with optiMal tranSport (CHARMS) that automatically and effectively transfers relevant tabular knowledge. Specifically, by maximizing the mutual information between a group of channels and tabular features, our method modifies the visual embedding and captures the semantics of tabular knowledge. The alignment between channels and attributes helps select the subset of tabular data which contains knowledge to images. Experimental results demonstrate that {\sc Charms} effectively reuses tabular knowledge to improve the performance and interpretability of visual classifiers.
APA
Jiang, J., Ye, H., Wang, L., Yang, Y., Jiang, Y. & Zhan, D.. (2024). On Transferring Expert Knowledge from Tabular Data to Images. Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models, in Proceedings of Machine Learning Research 243:102-115 Available from https://proceedings.mlr.press/v243/jiang24a.html.

Related Material