Program

The workshop takes place on Friday 11th of September in Building 1, Via Claudio, Room II2.

10:20–10:30 — Welcome and short introduction by the organisers

10:30–11:30 — Keynote

11:30–12:00 — Poster pitch presentations

(~4 min each: 1 slide for 2mins pitch + time for turn over)

• [130] Modeling Information Blackouts in Missing Not-At-Random Time Series Data
  Aman Sunesh, Allan Ma, Siddarth Nilol

• [263] Beyond Stationarity in Time Series: Discovering Causal Structures and Latent Regimes via Markov Blankets
  Lei Zan, Charles K. Assaad, Emilie Devijver, Eric Gaussier

• [265] Revisiting WEASEL 2.0: Reproduction, Sensitivity, and an Adaptive Ensemble-Size Rule
  Cian Higgins, Gerard Carrigan, Pinar Sungu Isiacik, Georgiana Ifrim

• [283] Beyond Simulated Benchmarks: Evaluating Motion Representations for Fall Detection Under Real-World Data Scarcity
  Timilehin B. Aderinola, Ilaria D’Ascanio, Luca Palmerini, Lorenzo Chiari, Jochen Klenk, Clemens Becker, Brian Caulfield, Georgiana Ifrim

• [284] Beyond Aggregate Error Metrics: Revealing Hidden Error Structures in Graph-Based Traffic Forecasting
  Selma Kerdous, Ilham BenYahia

• [318] ALSAX: Alternative Empirical SAX for Time Series Symbolic Representation
  Damien Porcher, Ali Ayadi, Ali Ismail-Fawaz, Maxime Devanne, Jonathan Weber, Cédric Wemmert

• [330] Reservoir Computing for Temporal Sequence Learning: Overcoming the Hyperparameter Tuning Bottleneck via Free-Probability Kernels
  Sara Malacarne, Andrea Ceni, Claudio Gallicchio

12:00–1:30 — Poster session

1:30–2:30 — Lunch break

2:30–4:00 — Oral session 1

(~15 min each, 6 papers: 10mins talk + 3-5mins QA)

• [142] Scaling Time Series Classification via XAI-Driven Data Reduction
  Davide Italo Serramazza, Thach Le Nguyen, Georgiana Ifrim

• [165] Mitigating Exposure Bias in IMU Handwriting Recognition with Noise Injection and Hybrid CTC–AR Training
  Muhammad Ajlal, Jindong Li, Dario Zanca, Vincent Christlein, Björn Eskofier

• [195] RAMC: A Regime-Adaptive Meta-Classifier for Explainable Trend Prediction
  Hanxue Yao, Irena Koprinska

• [204] On the Post-Training Quantization of Deep Convolutional Neural Network for Time Series Classification
  Cyril Meyer, Ali Ismail-Fawaz, Germain Forestier

• [210] Deep2DO: Deep Decoupled Diagnostic Observer for Unsupervised Anomaly Detection
  Assmaa Alsamadi, Fannia Pacheco, Paul Honeine

• [213] CLARTÉ - Channel-adaptive Lightweight Aggregation for Retrieval and Temporal Explainability
  Martin Royer, Maxence Gagnant, Martin Gonzalez, Milad Leyli-Abadi

4:00–4:30 — Coffee break and poster discussion

4:30–6:00 — Oral session 2

(~15 min each, 5 papers: 10mins talk + 3-5mins QA)

• [230] Analysis of Long Short-Term Memory Models Forecasting Performance on Chaotic Systems with Changing Parameters
  Roland Bolboacă, Piroska Haller

• [310] When Does Decomposition Benefit Time Series Forecasting?
  Konstantinos Tsikonofilos, Jelena Zdravkovic, Panagiotis Papapetrou

• [344] Time Series Extrinsic Regression of Plasma Parameters For a Candidate Fusion Reactor Diagnostic
  Ethan Attwood, J.W.S. Cook, Peter Hill

• [353] Multisource Time Series Classification Models for Urban Tree Species
  Victor Thiebaut, Ali Ismail-Fawaz, Cyril Meyer, Romain Wenger, Anne Puissant, Germain Forestier

• [433] Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series Forecasting
  Tamanna Kumavat, Georg Brunner, Kyriakos Flouris