Najwa Laabid

I am Ph.D. student at Aalto University, working with Dr. Vikas Garg on machine learning applied to drug discovery. Previously, I worked on modling single-cell and bulk sequencing data with deep learning methods as a junior researcher in the Systems Genomics - Heinäniemi Lab at the University of Eastern Finland. You can find out more about me by browsing this website or looking at my resume (here is the one page version).

selected publications

ICLR
Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

Najwa Laabid, Severi Rissanen, Markus Heinonen, and 2 more authors

In The Thirteenth International Conference on Learning Representations, 2025

Abs Bib PDF

Graph diffusion models, dominant in graph generative modeling, remain underexplored for graph-to-graph translation tasks like chemical reaction prediction. We demonstrate that standard permutation equivariant denoisers face fundamental limitations in these tasks due to their inability to break symmetries in noisy inputs. To address this, we propose aligning input and target graphs to break input symmetries while preserving permutation equivariance in non-matching graph portions. Using retrosynthesis (i.e., the task of predicting precursors for synthesis of a given target molecule) as our application domain, we show how alignment dramatically improves discrete diffusion model performance from 5% to a SOTA-matching 54.7% top-1 accuracy.
@inproceedings{laabid2025diffalign, title = {Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models}, author = {Laabid, Najwa and Rissanen, Severi and Heinonen, Markus and Solin, Arno and Garg, Vikas}, booktitle = {The Thirteenth International Conference on Learning Representations}, year = {2025}, url = {https://openreview.net/forum?id=onIro14tHv}, }