Contrastive representations of high-dimensional, structured treatments
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912136908767232 |
|---|---|
| author | Andreu, Oriol Corcoll Vlontzos, Athanasios O'Riordan, Michael Gilligan-Lee, Ciaran M. |
| author_facet | Andreu, Oriol Corcoll Vlontzos, Athanasios O'Riordan, Michael Gilligan-Lee, Ciaran M. |
| contents | Estimating causal effects is vital for decision making. In standard causal effect estimation, treatments are usually binary- or continuous-valued. However, in many important real-world settings, treatments can be structured, high-dimensional objects, such as text, video, or audio. This provides a challenge to traditional causal effect estimation. While leveraging the shared structure across different treatments can help generalize to unseen treatments at test time, we show in this paper that using such structure blindly can lead to biased causal effect estimation. We address this challenge by devising a novel contrastive approach to learn a representation of the high-dimensional treatments, and prove that it identifies underlying causal factors and discards non-causally relevant factors. We prove that this treatment representation leads to unbiased estimates of the causal effect, and empirically validate and benchmark our results on synthetic and real-world datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_19245 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Contrastive representations of high-dimensional, structured treatments Andreu, Oriol Corcoll Vlontzos, Athanasios O'Riordan, Michael Gilligan-Lee, Ciaran M. Machine Learning Artificial Intelligence Estimating causal effects is vital for decision making. In standard causal effect estimation, treatments are usually binary- or continuous-valued. However, in many important real-world settings, treatments can be structured, high-dimensional objects, such as text, video, or audio. This provides a challenge to traditional causal effect estimation. While leveraging the shared structure across different treatments can help generalize to unseen treatments at test time, we show in this paper that using such structure blindly can lead to biased causal effect estimation. We address this challenge by devising a novel contrastive approach to learn a representation of the high-dimensional treatments, and prove that it identifies underlying causal factors and discards non-causally relevant factors. We prove that this treatment representation leads to unbiased estimates of the causal effect, and empirically validate and benchmark our results on synthetic and real-world datasets. |
| title | Contrastive representations of high-dimensional, structured treatments |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2411.19245 |