907 citations
- Agency for Science, Technology and ResearchSG135 papers
- National University of SingaporeSG48 papers
- Nanyang Technological UniversitySG25 papers
- Singapore University of Technology and DesignSG12 papers
- Institute of Materials Research and EngineeringSG11 papers
- Dalian University of TechnologyCN7 papers
- Centre for Quantum TechnologiesSG6 papers
- Chinese Academy of SciencesCN6 papers
- Institute for Infocomm ResearchSG5 papers
- Institute of Metal Superplasticity ProblemsRU5 papers
- Massachusetts Institute of TechnologyUS4 papers
- National Research Tomsk State UniversityRU4 papers
7 papers · 1 filter
Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
Ponhvoan Srey, Yaxin Shi, Hangwei Qian +2
Fully Test-Time Adaptation (FTTA) addresses domain shifts without access to source data and training protocols of the pre-trained models. Traditional strategies that align source a…
Co-Learning Bayesian Optimization
Zhendong Guo, Yew-Soon Ong, Tiantian He +1
Bayesian optimization (BO) is well known to be sample-efficient for solving black-box problems. However, the BO algorithms can sometimes get stuck in suboptimal solutions even with…
Maximizing Uncertainty for Federated learning via Bayesian Optimisation-based Model Poisoning
Marios Aristodemou, Xiaolan Liu, Yuan Wang +3
As we transition from Narrow Artificial Intelligence towards Artificial Super Intelligence, users are increasingly concerned about their privacy and the trustworthiness of machine…
PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation
Yinghua Yao, Yuangang Pan, Jing Li +2
Recent advancements in the realm of deep generative models focus on generating samples that satisfy multiple desired properties. However, prevalent approaches optimize these proper…
Hierarchical Weight Averaging for Deep Neural Networks
Xiaozhe Gu, Zixun Zhang, Yuncheng Jiang +4
Despite the simplicity, stochastic gradient descent (SGD)-like algorithms are successful in training deep neural networks (DNNs). Among various attempts to improve SGD, weight aver…
Graph Neural Network Based Surrogate Model of Physics Simulations for Geometry Design
Jian Cheng Wong, Chin Chun Ooi, Joyjit Chattoraj +6
Computational Intelligence (CI) techniques have shown great potential as a surrogate model of expensive physics simulation, with demonstrated ability to make fast predictions, albe…