Portrait de Xiusi Li

Xiusi Li

xiusi.li@mila.quebec
Doctorat - McGill
Superviseur⋅e principal⋅e
Siamak Ravanbakhsh
Sujets de recherche
Apprentissage de représentations
Apprentissage profond
Causalité
Modèles génératifs
Site web
Google Scholar
GitHub

Publications

On the Identifiability of Causal Abstractions
Xiusi Li
Sékou-Oumar Kaba
Siamak Ravanbakhsh
Causal representation learning (CRL) enhances machine learning models' robustness and generalizability by learning structural causal models … (voir plus)associated with data-generating processes. We focus on a family of CRL methods that uses contrastive data pairs in the observable space, generated before and after a random, unknown intervention, to identify the latent causal model. (Brehmer et al., 2022) showed that this is indeed possible, given that all latent variables can be intervened on individually. However, this is a highly restrictive assumption in many systems. In this work, we instead assume interventions on arbitrary subsets of latent variables, which is more realistic. We introduce a theoretical framework that calculates the degree to which we can identify a causal model, given a set of possible interventions, up to an abstraction that describes the system at a higher level of granularity.
2025-04-23
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics (publié)
doi.org
openreview.net
On the Identifiability of Causal Abstractions
Xiusi Li
Sékou-Oumar Kaba
Siamak Ravanbakhsh
Causal representation learning methods seek to enhance machine learning models' robustness and generalization capabilities by learning laten… (voir plus)t representations and causal graphs aligned with the data generating process. In many systems, fully recovering the true causal structure is challenging because we cannot intervene on all latent variables individually. We introduce a theoretical framework that calculates the degree to which we can identify a causal structure in the more realistic setting of interventions on arbitrary subsets of latent variables. We find that in that case, we can only identify a causal model up to a \emph{causal abstraction}. These causal abstractions are still meaningful in that they describe the system at a higher level of granularity. Conversely, given a causal abstraction, our framework provides sufficient conditions for its identifiability. Our findings extend existing identifiability results in two areas: those that address abstractions of latent variables without considering graphical structures and those that focus on graphical structures without incorporating their abstractions.
2025-01-22
aistats.org/AISTATS/2025/Conference (poster)
openreview.net
openreview.net