Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
E (n) equivariant topological neural networks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
SCOPE-BENCH shows state-of-the-art molecular models suffer up to 8x higher errors under extreme OOD, while POMA reduces mean absolute error by up to 11.2% via target-aware source selection and dual-scale adaptation.
Introduces an adjusted cup-product neural layer whose output on closed cycles depends only on the adjustment coefficient and is exactly invariant under gauge transformations.
citing papers explorer
-
Unsupervised Causal Abstractions Discovery
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
-
Rethinking Molecular OOD Generalization via Target-Aware Source Selection
SCOPE-BENCH shows state-of-the-art molecular models suffer up to 8x higher errors under extreme OOD, while POMA reduces mean absolute error by up to 11.2% via target-aware source selection and dual-scale adaptation.
-
Adjusted Cup-Product Neural Layer
Introduces an adjusted cup-product neural layer whose output on closed cycles depends only on the adjustment coefficient and is exactly invariant under gauge transformations.