7 papers
Exact Federated Continual Unlearning for Ridge Heads on Frozen Foundation Models
Yijun Quan, Wentai Wu, Giovanni Montana
Foundation models are commonly deployed as frozen feature extractors with a small trainable head to adapt to private, user-generated data in federated settings. The ``right to be f…
\textsc{Lethe}: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning
Wentai Wu, Hanwei Tan, Yijun Quan +4
Federated unlearning (FU) aims to erase knowledge from a global model. Existing studies commonly assume that federated collaboration terminates after unlearning, overlooking a depl…
Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
Yutszyuk Wong, Wentai Wu, Yuen-Ying Yeung +1
Log anomaly detection is a critical task for system operations and security assurance. However, in networked systems at scale, log data are generated at massive scale while instanc…
HaS: Accelerating RAG through Homology-Aware Speculative Retrieval
Peng Peng, Weiwei Lin, Wentai Wu +2
Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) at inference by retrieving external documents as context. However, retrieval bec…
Task-Agnostic Federation over Decentralized Data: Research Landscape and Visions
Wentai Wu, Ligang He, Saiqin Long +4
Increasing legislation and regulations on private and proprietary information results in scattered data sources also known as the "data islands". Although Federated Learning-based…
CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
Shengsheng Lin, Weiwei Lin, Xinyi Hu +3
The stable periodic patterns present in time series data serve as the foundation for conducting long-horizon forecasts. In this paper, we pioneer the exploration of explicitly mode…