Topology-Aware Robust Representation Balancing for Estimating Causal Effects

Amirhossein Farzam, Ahmed Aloui, Vahid Tarokh, Guillermo Sapiro

Keywords: Topological Deep Learning, Robustness, Causal Inference

TL;DR: We extend the stability properties of topological summaries to deep learning, improving robustness of representation-balancing neural networks used for treatment effect estimation through a ractable and effective framework.

Abstract:

Representation learning in high-dimensional spaces faces significant robustness challenges with noisy inputs, particularly with heavy-tailed noise.
Arguing that topological data analysis (TDA) offers a solution, we leverage TDA to enhance representation stability in neural networks.
Our theoretical analysis establishes conditions under which incorporating topological summaries improves robustness to input noise, especially for heavy-tailed distributions.
Extending these results to representation-balancing methods used in causal inference, we propose the *Topology-Aware Treatment Effect Estimation* (TATEE) framework, through which we demonstrate how topological awareness can lead to learning more robust representations.
A key advantage of this approach is that it requires no ground-truth or validation data, making it suitable for observational settings common in causal inference.
The method remains computationally efficient with overhead scaling linearly with data size while staying constant in input dimension.
Through extensive experiments with $\alpha$-stable noise distributions, we validate our theoretical results, demonstrating that TATEE consistently outperforms existing methods across noise regimes.
This work extends stability properties of topological summaries to representation learning via a tractable framework scalable for high-dimensional inputs, providing insights into how it can enhance robustness, with applications extending to domains facing challenges with noisy data, such as causal inference.

Student Paper: Yes

Submission Number: 40