collaborators

8 papers

cs.LG2025

Frequency Matters: When Time Series Foundation Models Fail Under Spectral Shift

Tianze Wang, Sofiane Ennadir, John Pertoft +7

Time series foundation models (TSFMs) have shown strong results on public benchmarks, prompting comparisons to a "BERT moment" for time series. Their effectiveness in industrial se…

cs.LG2025

If You Want to Be Robust, Be Wary of Initialization

Sofiane Ennadir, Johannes F. Lutzeyer, Michalis Vazirgiannis +1

Graph Neural Networks (GNNs) have demonstrated remarkable performance across a spectrum of graph-related tasks, however concerns persist regarding their vulnerability to adversaria…

cs.LG2025

Enhancing Graph Classification Robustness with Singular Pooling

Sofiane Ennadir, Oleg Smirnov, Yassine Abbahaddou +2

Graph Neural Networks (GNNs) have achieved strong performance across a range of graph representation learning tasks, yet their adversarial robustness in graph classification remain…

cs.LG2025

Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models

Sofiane Ennadir, Levente Zólyomi, Oleg Smirnov +4

Transformer models have become the dominant backbone for sequence modeling, leveraging self-attention to produce contextualized token representations. These are typically aggregate…

cs.LG2025

Joint Embeddings Go Temporal

Sofiane Ennadir, Siavash Golkar, Leopoldo Sarra

Self-supervised learning has seen great success recently in unsupervised representation learning, enabling breakthroughs in natural language and image processing. However, these me…

q-bio.QM2025

Efficient Data Selection for Training Genomic Perturbation Models

George Panagopoulos, Johannes F. Lutzeyer, Sofiane Ennadir +2

Genomic studies face a vast hypothesis space, while interventions such as gene perturbations remain costly and time-consuming. To accelerate such experiments, gene perturbation mod…