KCKai Fong Ernest Chong
Kai Fong Ernest Chong
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Kai Fong Ernest Chong has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Eran Nevo
1 shared publication- Howard H. Yang
ZJU-UIUC Institute, Zhejiang University, Haining, China
1 shared publication - Tony Q. S. Quek
Singapore University of Technology and Design
1 shared publication - Xia Huang
Singapore University of Technology and Design, Singapore, Singapore
1 shared publication - Zihan Chen
Information Systems Technology and Design, Singapore University of Technology and Design, Tampines, Singapore
1 shared publication
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 11403-11416
Asymmetric Partial Model Transmission for Federated Edge Learning
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 11403-11416
Asymmetric Partial Model Transmission for Federated Edge Learning
- Open Access
- 15 July 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (11) , 3035-3059
GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence
Web image datasets curated online inherently contain ambiguous in-distribution instances and out-of-distribution instances, which we collectively callnon-conforming(NC) instances. In many recent approaches for mitigating the negative effects of NC instances, the core implicit assumption is that the NC instances can be found via entropy maximization. For “entropy” to be well-defined, we are interpreting the output prediction vector of an instance as the parameter vector of a multinomial random variable, with respect to some trained model with a softmax output layer. Hence, entropy maximization is based on the idealized assumption that NC instances have predictions that are “almost” uniformly distributed. However, in real-world web image datasets, there are numerous NC instances whose predictions are far from being uniformly distributed. To tackle the limitation of entropy maximization, we propose $$(\alpha , \beta )$$ -generalized KL divergence, $${\mathcal {D}}_{\text {KL}}^{\alpha , \beta }(p\Vert q)$$ , which can be used to identify significantly more NC instances. Theoretical properties of $${\mathcal {D}}_{\text {KL}}^{\alpha , \beta }(p\Vert q)$$ are proven, and we also show empirically that a simple use of $${\mathcal {D}}_{\text {KL}}^{\alpha , \beta }(p\Vert q)$$ outperforms all baselines on the NC instance identification task. Building upon $$(\alpha ,\beta )$$ -generalized KL divergence, we also introduce a new iterative training framework,GenKL, that identifies and relabels NC instances. When evaluated on three web image datasets, Clothing1M, Food101/Food101N, and mini WebVision 1.0, we achieved new state-of-the-art classification accuracies: $$81.34\%$$ , $$85.73\%$$ and $$78.99\%$$ / $$92.54\%$$ (top-1/top-5), respectively.- 15 July 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (11) , 3035-3059
Open AccessGenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence
Web image datasets curated online inherently contain ambiguous in-distribution instances and out-of-distribution instances, which we collectively callnon-conforming(NC) instances. In many recent approaches for mitigating the negative effects of NC instances, the core implicit assumption is that the NC instances can be found via entropy maximization. For “entropy” to be well-defined, we are interpreting the output prediction vector of an instance as the parameter vector of a multinomial random variable, with respect to some trained model with a softmax output layer. Hence, entropy maximization is based on the idealized assumption that NC instances have predictions that are “almost” uniformly distributed. However, in real-world web image datasets, there are numerous NC instances whose predictions are far from being uniformly distributed. To tackle the limitation of entropy maximization, we propose $$(\alpha , \beta )$$ -generalized KL divergence, $${\mathcal {D}}_{\text {KL}}^{\alpha , \beta }(p\Vert q)$$ , which can be used to identify significantly more NC instances. Theoretical properties of $${\mathcal {D}}_{\text {KL}}^{\alpha , \beta }(p\Vert q)$$ are proven, and we also show empirically that a simple use of $${\mathcal {D}}_{\text {KL}}^{\alpha , \beta }(p\Vert q)$$ outperforms all baselines on the NC instance identification task. Building upon $$(\alpha ,\beta )$$ -generalized KL divergence, we also introduce a new iterative training framework,GenKL, that identifies and relabels NC instances. When evaluated on three web image datasets, Clothing1M, Food101/Food101N, and mini WebVision 1.0, we achieved new state-of-the-art classification accuracies: $$81.34\%$$ , $$85.73\%$$ and $$78.99\%$$ / $$92.54\%$$ (top-1/top-5), respectively. - 1 August 2021
- Published by Elsevier in Journal of Combinatorial Theory, Series A
- Vol. 182
Flag complexes and homology
- 1 August 2021
- Published by Elsevier in Journal of Combinatorial Theory, Series A
- Vol. 182
Flag complexes and homology