359 citations · 796 across the 15 of their papers we have counts for
7 papers · 1 filter
Extracting Forgotten Prompts from Targeted Unlearned Models
Au Ashley Hoi-Ting, Meghdad Kurmanji, William F. Shen +2
Recent unlearning methods (e.g. NPO, DPO, LUNAR) make use of refusal alignment to suppress forgotten data. However, it has been shown that refusal responses might leave traces of u…
DG-CoLearn: An Efficient Collaborative Learning Framework for Dynamic Graphs
Ashley Hoi-Ting Au, Zikun Zhang, Ligang He +1
Dynamic graph learning (DGL) is essential for modelling evolving graph data, but existing methods suffer from significant computational overhead due to repeated full-snapshot retra…
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…
Variation-Incentive Loss Re-weighting for Regression Analysis on Biased Data
Wentai Wu, Ligang He, Weiwei Lin
Both classification and regression tasks are susceptible to the biased distribution of training data. However, existing approaches are focused on the class-imbalanced learning and…
FedProf: Selective Federated Learning with Representation Profiling
Wentai Wu, Ligang He, Weiwei Lin +1
Federated Learning (FL) has shown great potential as a privacy-preserving solution to learning from decentralized data that are only accessible to end devices (i.e., clients). In m…
An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee
Tiansheng Huang, Weiwei Lin, Wentai Wu +3
The issue of potential privacy leakage during centralized AI's model training has drawn intensive concern from the public. A Parallel and Distributed Computing (or PDC) scheme, ter…
Developing an Unsupervised Real-time Anomaly Detection Scheme for Time Series with Multi-seasonality
Wentai Wu, Ligang He, Weiwei Lin +4
On-line detection of anomalies in time series is a key technique used in various event-sensitive scenarios such as robotic system monitoring, smart sensor networks and data center…