5 papers
Detecting Diffusion-Generated Time Series Under Generator Shift
Zhi Wen Soi, Aditya Shankar, Gert Lek +4
The boundary between real and diffusion-generated time series is becoming increasingly difficult to draw, yet detection in this domain remains underexplored, especially when the ge…
Federated Time Series Generation on Feature and Temporally Misaligned Data
Zhi Wen Soi, Chenrui Fan, Aditya Shankar +2
Distributed time series data presents a challenge for federated learning, as clients often possess different feature sets and have misaligned time steps. Existing federated time se…
Asynchronous Byzantine Federated Learning
Bart Cox, Abele MÄlan, Lydia Y. Chen +1
Federated learning (FL) enables a set of geographically distributed clients to collectively train a model through a server. Classically, the training process is synchronous, but ca…
CCBNet: Confidential Collaborative Bayesian Networks Inference
Abele MÄlan, Jérémie Decouchant, Thiago Guzella +1
Effective large-scale process optimization in manufacturing industries requires close cooperation between different human expert parties who encode their knowledge of related domai…
DALLMi: Domain Adaption for LLM-based Multi-label Classifier
Miruna BeÅ£ianu, Abele MÄlan, Marco Aldinucci +2
Large language models (LLMs) increasingly serve as the backbone for classifying text associated with distinct domains and simultaneously several labels (classes). When encountering…