5 papers
Be Wary of Your Time Series Preprocessing
Sofiane Ennadir, Tianze Wang, Oleg Smirnov +2
Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from a theoretical perspecti…
Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospects
Levente Zólyomi, Levente Zólyomi, Tianze Wang +3
The proliferation of digital interactions across diverse domains, such as healthcare, e-commerce, gaming, and finance, has resulted in the generation of vast volumes of event strea…
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…
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…
Expressivity of Representation Learning on Continuous-Time Dynamic Graphs: An Information-Flow Centric Review
Sofiane Ennadir, Gabriela Zarzar Gandler, Filip Cornell +6
Graphs are ubiquitous in real-world applications, ranging from social networks to biological systems, and have inspired the development of Graph Neural Networks (GNNs) for learning…