Position: Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution

Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Schölkopf, Mario Fritz
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:169543-169560, 2026.

Abstract

As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), are increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously, especially while preserving utility. This position paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI. We ground our arguments in re-interpreting trustworthy AI trade-offs as incompatible invariance requirements under different changes to the data-generating process. We then illustrate this argument through case-study analyses from the literature and a stylized synthetic-data simulation, showing that causality provides a unifying framework for understanding how trade-offs in trustworthy AI arise and how they can be softened or resolved through selective invariance. This perspective applies to both classical ML models and large-scale FMs. Our paper discusses how causal assumptions may be applied explicitly or implicitly in modern large-scale systems. Finally, we outline open challenges and opportunities for using causality to build both trustworthy and high-performing AI.

Cite this Paper


BibTeX
@InProceedings{pmlr-v306-binkyte26a, title = {Position: Trustworthy {AI} Suffers from Invariance Conflicts and Causality is The Solution}, author = {Binkyte, Ruta and Sheth, Ivaxi and Jin, Zhijing and Havaei, Mohammad and Sch\"{o}lkopf, Bernhard and Fritz, Mario}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {169543--169560}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/binkyte26a/binkyte26a.pdf}, url = {https://proceedings.mlr.press/v306/binkyte26a.html}, abstract = {As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), are increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously, especially while preserving utility. This position paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI. We ground our arguments in re-interpreting trustworthy AI trade-offs as incompatible invariance requirements under different changes to the data-generating process. We then illustrate this argument through case-study analyses from the literature and a stylized synthetic-data simulation, showing that causality provides a unifying framework for understanding how trade-offs in trustworthy AI arise and how they can be softened or resolved through selective invariance. This perspective applies to both classical ML models and large-scale FMs. Our paper discusses how causal assumptions may be applied explicitly or implicitly in modern large-scale systems. Finally, we outline open challenges and opportunities for using causality to build both trustworthy and high-performing AI.} }
Endnote
%0 Conference Paper %T Position: Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution %A Ruta Binkyte %A Ivaxi Sheth %A Zhijing Jin %A Mohammad Havaei %A Bernhard Schölkopf %A Mario Fritz %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-binkyte26a %I PMLR %P 169543--169560 %U https://proceedings.mlr.press/v306/binkyte26a.html %V 306 %X As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), are increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously, especially while preserving utility. This position paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI. We ground our arguments in re-interpreting trustworthy AI trade-offs as incompatible invariance requirements under different changes to the data-generating process. We then illustrate this argument through case-study analyses from the literature and a stylized synthetic-data simulation, showing that causality provides a unifying framework for understanding how trade-offs in trustworthy AI arise and how they can be softened or resolved through selective invariance. This perspective applies to both classical ML models and large-scale FMs. Our paper discusses how causal assumptions may be applied explicitly or implicitly in modern large-scale systems. Finally, we outline open challenges and opportunities for using causality to build both trustworthy and high-performing AI.
APA
Binkyte, R., Sheth, I., Jin, Z., Havaei, M., Schölkopf, B. & Fritz, M.. (2026). Position: Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:169543-169560 Available from https://proceedings.mlr.press/v306/binkyte26a.html.

Related Material