Theo Saulus

theo.saulus@mila.quebec

Doctorat - UdeM

Superviseur⋅e principal⋅e

Simon Lacoste-Julien

Co-supervisor

Dhanya Sridhar

Sujets de recherche

Apprentissage profond

Apprentissage sur graphes

Biologie computationnelle

Causalité

Modèles génératifs

Modèles probabilistes

Modélisation moléculaire

Site web

Publications

Unsupervised Causal Abstractions Discovery

Theo Saulus

Simon Lacoste-Julien

Dhanya Sridhar

Causal abstractions formalize when a high-level structural causal model (SCM) captures the interventional behavior of a lower-level SCM. Exi… (voir plus)sting applications of this notion largely follow a hypothesis-testing paradigm: an expert proposes a candidate high-level model and then evaluates if the low-level system implements it. We study the complementary problem of learning a high-level model directly from low-level measurements. Our contributions leverage hypotheses from low-rank causal discovery, and can be summarized as follows: (1) we show that observations generated by a low-rank graph induce latents that form a causal abstraction, (2) we provide identifiability results about these latents, and (3) we propose a practical objective to learn this high-level SCM.

2026-07-02

CDM @ Conference on Uncertainty in Artificial Intelligence (publié)

doi.org

openreview.net

Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations

Wieland Brendel

Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with k… (voir plus)nown ground-truth factors. These metrics are assumed to reflect recovery up to the equivalence class guaranteed by identifiability theory. We show that this assumption holds only under specific structural conditions: each metric implicitly encodes assumptions about both the data-generating process (DGP) and the encoder. When these assumptions are violated, metrics become misspecified and can produce systematic false positives and false negatives. Such failures occur both within classical identifiability regimes and in post-hoc settings where identifiability is most needed. We introduce a taxonomy separating DGP assumptions from encoder geometry, use it to characterise the validity domains of existing metrics, and release an evaluation suite for reproducible stress testing and comparison.

2026-05-30

Conference on Uncertainty in Artificial Intelligence (poster)

doi.org

proceedings.mlr.press

Improving Molecular Modeling with Geometric GNNs: an Empirical Study

Fragkiskos D. Malliaros

Alexandre AGM Duval